天文信息自动处理及目标检测的研究
|
摘要
宇宙的形成、发展和演化是人类永恒的研究课题。宇宙包含了所有的空间、时间、物质和能量。对于宇宙的研究水平,标志着一个国家在科技发展中的位置,对自然科学的众多学科有着特殊的重要意义,也是当代科学技术,特别是尖端空间技术发展的巨大推动力。
天文学研究的途径在光学波段主要有两种：天体光谱和天文图像。前者是一维数据,后者是二维数据,二者之间联系密切。光谱分析可以定性或定量地测定天体的化学组成,通过直接或间接的方法确定天体的光度、表面温度、直径、质量、视向速度及自转。因此,光谱分析在天文学中占有重要的地位。对天文图像的分析是另一种研究宇宙天体的途径。利用天文图像可以对天体目标的形态结构信息,包括天体的年龄、状态、演变趋势等进行研究,为天文目标观测与研究提供重要的技术支持。
国家大科学项目LAMOST(Large Sky Area Multi-Object Fiber Spectroscopic Telescope)于1997年正式立项,2009年6月通过国家验收,并逐步投入运行。它具有4米口径,可以观测到20.5星等的暗弱天体。在5度视场上可以放置4000根光纤,最多可以同时获得4000个天体的光谱,成为世界上光谱获取率最高的望远镜。LAMOST的观测目标是宇宙中星系与恒星。随着LAMOST的运行,在每个观测夜晚都能够采集万余条光谱,得到的光谱数据量是数十亿字节。因此,在光谱数据的自动识别和分析方面,急需研究海量天体光谱的自动识别与分析方法,包括天体光谱的自动识别、分类以及物理参数自动测量等。
山东大学威海天文台WOSDU (Weihai Observatory of Shandong University)用于搜寻太阳系小行星和超新星巡天。每天会产生大量的天文图像数据。以小行星搜索为例,每天都会拍摄大量的天文图像,图像尺寸为2048x2048×16bit,数据量为8M。要发现新的小行星,首先要在图像中快速检测各个星体,然后根据图像坐标换算成天球坐标,再在星表中进行比对。若发现星表里不存在,则将其作为候选体继续追踪观测,并计算出相应轨道,以便确认是否是新的小行星。由于天文图像数量很大,这一流程涉及到大量的处理工作,而天体目标检测就是一个重要的步骤。图像识别中,准确度和速度成为主要的指标。如何快速有效地识别图像中的天体便成为我们研究的一个课题。由此可见,海量天文图像的快速及有效的处理,向计算机信息技术提出了迫切的需求,同时,天文数据所具有的海量性和开放性也为计算机信息技术展开了一个重要的研究和应用领域。对这些海量数据及时有效的处理,需要借助于图像处理、数据挖掘、信号处理等多项现代信息处理技术。
本课题利用数据挖掘、图像处理、人工智能、信号处理等先进的信息技术,在国家自然基金项目的支持下,以LAMOST与WOSDU的天文数据为研究和应用背景,针对天文数据的预处理、天文图像的目标检测、高维天体光谱数据的自动分类、稀少天体的数据挖掘等若干关键问题展开研究,设计和验证了一系列有效的算法,并开发出可供LAMOST使用的天体光谱自动识别与分析系统。本研究属于天文和信息交叉学科的研究,是将最新的计算机信息技术在天文领域的一项具体的应用,以期在天文研究中取得新的科学成果。因此,本课题的研究具有非常好的理论和应用价值。
本课题研究的内容包括四个方面：(1)天文数据预处理及发射线识别；(2)图像的目标检测；(3)天文光谱的自动分类；(4)稀少天体的数据挖掘。
针对上述关键问题,开展了如下的研究和创新工作：
首先是天文光谱去噪的研究。通过望远镜观测到的一维光谱数据在探测阶段因噪声而受到影响,导致信噪比降低,因而去噪工作非常重要。作为信号估计的一个组成部分,去噪问题一直在信号处理领域被广泛研究。信号降噪的目的是从被加性噪声污染的信号中还原原始信号。在过去的二十多年中,许多研究集中在使用小波变换去除噪声。已经提出了许多基于正交小波的阈值规则。然而,正如Coifman和Donoho指出的,基于正交小波的去噪算法在不连续信号的邻域中会表现出伪吉布斯现象。因此他们提出了一种平移不变的降噪模式来减少这种影响。另外,就均方根误差和信噪比而言,相对于非冗余的信号表示,冗余的信号表示显示了相当好的优越性。因此,这种平移不变的冗余转变是非常适合于光谱信号的降噪的。Kingsbury提出的双树复小波变换是冗余而且近似于平移不变的。本文提出一种基于双树复小波变换(DTCWT)的光谱降噪算法,该算法处理的光谱具有更高的信噪比和光谱质量。针对天文光谱的预处理,本文研究了基于双树复小波变换的自适应降噪方法。该方法利用最大后验估计理论来对复小波系数进行自适应收缩,在保护谱线等重要信息的前提下,抑制噪声和伪吉布斯现象,提高去噪算法运行效率,为光谱的后续处理提供了有效的工具。此外,我们还进行了具有发射线恒星的自动检测研究。恒星光谱一般具有明显的吸收线或者吸收带特征,而具有发射线的恒星光谱对应着特殊类型的恒星,如激变变星、Herbig Ae/Be等。对这些光谱的后续研究有着重要的意义。本文提出了一种能够自动识别发射线恒星光谱的方法。该方法首先对光谱进行连续谱归一化,然后通过比较谱线对应的流量及其邻域流量的均值和标准差,来判断是否存在发射线。对SDSS DR8大样本数据的实验表明,该方法能够完整、准确地识别发射线恒星。而且,由于该方法不涉及复杂的变换和运算,因而识别速度非常快,可用于诸如LAMOST、SDSS这样大型光谱巡天项目中发现发射线恒星光谱。
其次,是天体目标的检测。在天文研究中,通过天体观测而得到的CCD图像(Charge Coupled Device,电荷耦合器件)通常以FITS文件(Flexible Image Transport System)格式存储。每幅图像都很大,可以达到8M或更大。此外,通过连续观测而得到的这类图像的数量又是非常大的,因此如何对这些图像进行实时的处理是非常重要的,也是具有挑战性的。而天体的检测又是天文图像处理的一个重要步骤。本文设计并实现了基于空域的天文图像目标检测方法。利用递归方式,设计并实现了扫描加速器。实验表明,该算法大大提高了目标检测速度,实现了对目标的快速准确的检测并可获得目标的多个参数,同时建立了天球三维模型,可以根据指定天区,对满足一定条件的恒星从星表数据库中进行检索,然后在三维天球坐标系中形象地显示其分布,实现了星表查询结果的三维可视化。
再次,对于高维光谱数据分类研究。随机森林是一种高效、稳定的算法,和其他算法相比在效率和准确率上具有一定的优势。随机森林中计算效率和准确率,受树的个数和随机属性的个数影响。在保证训练时间和准确率的情况下,选择适当的阂值,可以使训练时间最短准确率最高。合适的树的个数阈值会在保证准确率的基础上,使训练时间最短；而合适的随机属性的个数会使得训练的时间最短。而阈值是和数据相关的,阈值选取的好坏直接影响效率和准确率。本文提出了利用遗传算法优化随机森林分类参数的模式。利用该模式可以快速地确定随机森林进行光谱分类时所需的关键参数,从而改变了传统单纯凭经验设定随机森林分类参数的方式,提高了分类算法的自动化和智能化程度,提高了分类准确率,减少了分类器训练时间。
最后,针对激变变星的搜寻,提出了利用PCA降维与BP人工神经网络相结合的稀少天体的数据挖掘方法。利用PCA降维,大大减少了高维光谱数据的维度空间,然后利用BP人工神经网络进行筛选,提高了激变变星搜寻的准确率,减少了模型训练时间。实验证明,该方法对于发现特殊天体是行之有效的。该方法不仅对激变变星适用,对于其它类别的特殊天体也是适用的。该方法可极大地减少人工处理的工作强度和时间。由于速度快,基本可满足LAMOST光谱数据的准实时处理。如果具备并行数据处理环境,还可以使数据的输入、降维、挖掘等操作同时进行,提高科学成果的产出率。
It is a permanent topic for human beings how the universe is formed, developed and evoluted. The universe contains all of space, time, material and energy. The research level of universe marks the position of a country in the frontier of science and technology and has special significance to many disciplines, being the great impetus to modern science and technology, especially to the sophisticated space technology development.
There are two basic ways for modern cosmic research in visible bands:stellar spectrum and astronomical image. The former is one-dimensional data, while the latter is two-dimensional data. They have close relationship between them. By analyzing spectra, people can measure many chemical components and physical parameters of stellar objects, qualitatively or quantitatively, such as the chemical composition, the surface temperature, the luminosity, the diameter, the quality, the radial velocity and rotation, directly or indirectly. Therefore, spectral analysis occupies an important position in astronomy and astrophysics. Astronomical image analysis provides another way to research celestial bodies. Using astronomical image, we can study the target morphological structure of celestial body, including celestial age, state, evolution tendency, and provide important technical support for astronomical observation and study.
The National Major Scientific Project LAMOST (Large Sky Area Multi-Object Fiber Spectroscopic Telescope) was set up in 1997 and completed an adoption of national acceptance in June,2009 and was put into operation since then. The aperture of LAMOST is 4m, enabling it to obtain the spectra of objects as faint as down to 20.5 magnitudes. Within a 5°field of view, it may accommodate as many as 4000 optical fibers. So the light from 4000 celestial objects will be led into a number of spectrographs simultaneously. Thus the telescope will be the one that possesses the highest spectrum acquiring rate in the world. The observation targets of LAMOST are galaxies and stars in the universe. With the operation of LAMOST, thousands of spectra at every observation night can be obtained and the total volume of spectrum data can as many as billions of bytes. So the automated identification and analysis of spectra data is a challenging task. It needs the methods of automated identification and analysis, including spectra identification, classification and parameter measurements.
WOSDU (Weihai Observatory of Shandong University) is set up to find asteroid and supernova. Every day, it generates large volume of astronomical image data. In asteroid detection, for example, many celestial images are produced everyday. The size of each image is 2048×2048×16bit,8M. To find new asteroids, we must first detect the celestial bodies in the image, and then transform the pixel coordinates to celestial sphere coordinates. After that, a matching process is carried out in the celestial catalog to seek out whether the targets are already in the catalog or not. If not, the targets will be considered as asteroid candidates and observed later, and their orbits will be calculated for further identification. Because of the significant number of images, a lot of processing must be involved. The target detection is one of the important processing steps. In the target detection, the accuracy and speed are the most important factors to be considered. Our effort is to find a method to detect the targets in the image fast and effectively. It follows that the fast and effective processing for such huge amounts of astronomical data puts forward an urgent need to computer information technology. In the meantime, the mass characteristics and openness of astronomical data open a new research and application field for computer information technology. The timely and effective processing of such massive data needs to resort to many modern information processing technologies, such as image processing, data mining, and signal processing, and so on.
This project, sponsored by National Science Foundation Fund, focuses on the key problems in astronomical research field, such as the astronomical data pretreatment, target detection from astronomical image, the classification of high-dimensional data, the data mining of rare celestial objects and so on, by means of data mining, image processing, artificial intelligence, signal processing and other advanced information technologies. The astronomic data to be used are from LAMOST and WOSDU. A series of effective algorithms are designed, verified and will be put into use for LAMOST celestial spectral automatic identification and analysis system. The study is an interdisciplinary research between astronomy and information; it is a concrete application of the latest computer information technologies to in the field of astronomy, so as to achieve new scientific achievements. Therefore, this research has a very good theoretical research and practical application value.
The key content of this project includes four aspects:astronomical data pretreatment (spectra denoising) and emission line identification; target detection in astronomical image, celestial spectra classification and data mining of rare celestial bodies.
The following research and innovation works have been done respecting to the key issues mentioned above:
Firstly, our research focuses on the astronomical spectrum denoising. One-dimensional astronomical spectra observed by the astronomical spectroscopic telescope are often degraded by noise in the acquisition phase and have a poor signal-to-noise ratio. The reduction of noise is highly desirable for a lot of reasons. Noise reduction, as an integral part of signal estimation, has been an extensively studied for many years in the signal processing community. The goal of signal denoising is to recover the original signal from noisy signal corrupted by additive noise. Over the past twenty years, there has been considerable interest in the use of wavelet transforms for removing the noise from signals. Many thresholding rules based on the orthonormal wavelets have been proposed. However, as Coifman and Donoho pointed out, the denoising algorithm based on the orthonormal wavelets exhibits pseudo Gibbs phenomena in the neighborhood of discontinuities. Therefore, they proposed a translation-invariant denoising scheme to reduce the artifacts. In addition, it has been shown that a redundant representation is substantially superior to a nonredundant representation for signal denoising in term of mean-squared error and signal-to-noise ratio. Therefore, the translation-invariant redundant transforms are desirable for spectra denoising. The dual-tree complex wavelet transform introduced by Kingsbury is redundant and near translation-invariant. In this paper, we propose a spectra denoising algorithm based on the dual-tree complex wavelet transform (DTCWT), which can give higher signal-to-noise ratio and better quality. In astronomical spectra preprocessing, the adaptive denoising method has been studied based on the dual-tree complex wavelet transform. This method adjusts the complex wavelet coefficients by MAP estimation theory in order to suppress the noise. On the base of protecting the spectral line and other important information, this method suppresses the noise and pseudo Gibbs phenomenon, improves the efficiency of the algorithm, and provides an efficient tool for later spectra processing. In addition, we proposed a new method to identify emission line stars (ELS) spectra automatically. Stellar spectra are characterized by obvious absorption lines or absorption bands, while those with emission lines are usually special stars such as Cataclysmic Variable stars (CVs), HerbigAe/Be etc. The further study of this kind of spectra is meaningful. The new method to identify emission line stars (ELS) spectra is like this:after the continuum normalization is done for the original spectral flux, line detection is made by comparing the normalized flux with the mean and standard deviation of the flux in its neighbor region. The results of the experiment on massive spectra from SDSS DR8 indicate that the method can identify ELS spectra completely and accurately. Since no complicated transformation and computation are involved in this method, the identifying process is fast and it is ideal for the ELS detection in large sky survey projects like LAMOST and SDSS.
Secondly, our research is on the stellar object detection. In astronomical research, the Charge Coupled Device (CCD) images obtained from celestial observations are usually stored in Flexible Image Transport System (FITS) format and the sizes of such images are usually very large,8 Megabytes or more being not unusual. In addition, the amount of such images is great due to continuous celestial observations. So the demand of real time processing of these large images is challenging. This paper proposes an efficient method to detect objects, which is an important step in astronomical image processing, by designing a scan accelerator and a recursive measure routine. A method to detect target in astronomical image has been designed and implemented based on space domain. The experiments showed that by scanning in a recursive way and using a designed accelerator, the detection process can be greatly sped up and multi-objects can be detected quickly and many other parameters of the targets can be obtained. In addition, a 3-D visual system has been established. The stars that met the specific criteria in a certain sky region can be retrieved from UCAC2 catalog and their distribution can be displayed in the 3-D celestial sphere system. In this way, the retrieval information can be visualized.
Thirdly, a scheme to optimize the Random Forests classification parameters for astronomical spectra using Genetic Algorithm has been proposed. As an efficient and stable algorithm for high-dimensional spectral data classification, random forest has some advantages compared to other algorithms in the efficiency and accuracy. Random forest's computation efficiency and classification accuracy are affected by the number of trees and the number of attributes randomly selected. The appropriate thresholds are chosen to minimize training time and get higher accuracy while ensuring that the accuracy is within an acceptable range. Appropriate threshold of the number of trees will obtain the shortest training time while ensuring the accuracy. In addition, the appropriate number of random attributes will make the training time minimized. The threshold is relevant to the data. Therefore the threshold selected will affect efficiency and accuracy. In this paper, we proposed a scheme which can quickly determine the parameters needed by Random Forests in classification applications and improve the automation and intelligence of classification by avoiding the manual parameter estimation. This method can also improve the classification accuracy and reduce the training time of the classifier.
Finally, a data mining method for searching cataclysmic variables has been proposed. This method can screen out rare celestial bodies effectively by combining PCA and BP ANN. By PCA dimension reduction, the high dimensional data space has been greatly reduced, and after that, BP ANN is used to screen out rare celestial objects with high accuracy. In this way, the training time becomes shorter. Experiments show that the proposed method is effective for the detection of specific celestial objects. The method can be used not only to search the Cataclysmic Variable stars but also to find other types of special objects. It can greatly reduce the power of work and time of manual processing. Due to the high speed, it can mainly meet the LAMOST quasi-real-time spectral processing requirements. With a parallel data processing environment, the data input, dimension reduction, data mining and other operations can be done simultaneously, thus improving the outcome of scientific research.
天文学研究的途径在光学波段主要有两种：天体光谱和天文图像。前者是一维数据,后者是二维数据,二者之间联系密切。光谱分析可以定性或定量地测定天体的化学组成,通过直接或间接的方法确定天体的光度、表面温度、直径、质量、视向速度及自转。因此,光谱分析在天文学中占有重要的地位。对天文图像的分析是另一种研究宇宙天体的途径。利用天文图像可以对天体目标的形态结构信息,包括天体的年龄、状态、演变趋势等进行研究,为天文目标观测与研究提供重要的技术支持。
国家大科学项目LAMOST(Large Sky Area Multi-Object Fiber Spectroscopic Telescope)于1997年正式立项,2009年6月通过国家验收,并逐步投入运行。它具有4米口径,可以观测到20.5星等的暗弱天体。在5度视场上可以放置4000根光纤,最多可以同时获得4000个天体的光谱,成为世界上光谱获取率最高的望远镜。LAMOST的观测目标是宇宙中星系与恒星。随着LAMOST的运行,在每个观测夜晚都能够采集万余条光谱,得到的光谱数据量是数十亿字节。因此,在光谱数据的自动识别和分析方面,急需研究海量天体光谱的自动识别与分析方法,包括天体光谱的自动识别、分类以及物理参数自动测量等。
山东大学威海天文台WOSDU (Weihai Observatory of Shandong University)用于搜寻太阳系小行星和超新星巡天。每天会产生大量的天文图像数据。以小行星搜索为例,每天都会拍摄大量的天文图像,图像尺寸为2048x2048×16bit,数据量为8M。要发现新的小行星,首先要在图像中快速检测各个星体,然后根据图像坐标换算成天球坐标,再在星表中进行比对。若发现星表里不存在,则将其作为候选体继续追踪观测,并计算出相应轨道,以便确认是否是新的小行星。由于天文图像数量很大,这一流程涉及到大量的处理工作,而天体目标检测就是一个重要的步骤。图像识别中,准确度和速度成为主要的指标。如何快速有效地识别图像中的天体便成为我们研究的一个课题。由此可见,海量天文图像的快速及有效的处理,向计算机信息技术提出了迫切的需求,同时,天文数据所具有的海量性和开放性也为计算机信息技术展开了一个重要的研究和应用领域。对这些海量数据及时有效的处理,需要借助于图像处理、数据挖掘、信号处理等多项现代信息处理技术。
本课题利用数据挖掘、图像处理、人工智能、信号处理等先进的信息技术,在国家自然基金项目的支持下,以LAMOST与WOSDU的天文数据为研究和应用背景,针对天文数据的预处理、天文图像的目标检测、高维天体光谱数据的自动分类、稀少天体的数据挖掘等若干关键问题展开研究,设计和验证了一系列有效的算法,并开发出可供LAMOST使用的天体光谱自动识别与分析系统。本研究属于天文和信息交叉学科的研究,是将最新的计算机信息技术在天文领域的一项具体的应用,以期在天文研究中取得新的科学成果。因此,本课题的研究具有非常好的理论和应用价值。
本课题研究的内容包括四个方面：(1)天文数据预处理及发射线识别；(2)图像的目标检测；(3)天文光谱的自动分类；(4)稀少天体的数据挖掘。
针对上述关键问题,开展了如下的研究和创新工作：
首先是天文光谱去噪的研究。通过望远镜观测到的一维光谱数据在探测阶段因噪声而受到影响,导致信噪比降低,因而去噪工作非常重要。作为信号估计的一个组成部分,去噪问题一直在信号处理领域被广泛研究。信号降噪的目的是从被加性噪声污染的信号中还原原始信号。在过去的二十多年中,许多研究集中在使用小波变换去除噪声。已经提出了许多基于正交小波的阈值规则。然而,正如Coifman和Donoho指出的,基于正交小波的去噪算法在不连续信号的邻域中会表现出伪吉布斯现象。因此他们提出了一种平移不变的降噪模式来减少这种影响。另外,就均方根误差和信噪比而言,相对于非冗余的信号表示,冗余的信号表示显示了相当好的优越性。因此,这种平移不变的冗余转变是非常适合于光谱信号的降噪的。Kingsbury提出的双树复小波变换是冗余而且近似于平移不变的。本文提出一种基于双树复小波变换(DTCWT)的光谱降噪算法,该算法处理的光谱具有更高的信噪比和光谱质量。针对天文光谱的预处理,本文研究了基于双树复小波变换的自适应降噪方法。该方法利用最大后验估计理论来对复小波系数进行自适应收缩,在保护谱线等重要信息的前提下,抑制噪声和伪吉布斯现象,提高去噪算法运行效率,为光谱的后续处理提供了有效的工具。此外,我们还进行了具有发射线恒星的自动检测研究。恒星光谱一般具有明显的吸收线或者吸收带特征,而具有发射线的恒星光谱对应着特殊类型的恒星,如激变变星、Herbig Ae/Be等。对这些光谱的后续研究有着重要的意义。本文提出了一种能够自动识别发射线恒星光谱的方法。该方法首先对光谱进行连续谱归一化,然后通过比较谱线对应的流量及其邻域流量的均值和标准差,来判断是否存在发射线。对SDSS DR8大样本数据的实验表明,该方法能够完整、准确地识别发射线恒星。而且,由于该方法不涉及复杂的变换和运算,因而识别速度非常快,可用于诸如LAMOST、SDSS这样大型光谱巡天项目中发现发射线恒星光谱。
其次,是天体目标的检测。在天文研究中,通过天体观测而得到的CCD图像(Charge Coupled Device,电荷耦合器件)通常以FITS文件(Flexible Image Transport System)格式存储。每幅图像都很大,可以达到8M或更大。此外,通过连续观测而得到的这类图像的数量又是非常大的,因此如何对这些图像进行实时的处理是非常重要的,也是具有挑战性的。而天体的检测又是天文图像处理的一个重要步骤。本文设计并实现了基于空域的天文图像目标检测方法。利用递归方式,设计并实现了扫描加速器。实验表明,该算法大大提高了目标检测速度,实现了对目标的快速准确的检测并可获得目标的多个参数,同时建立了天球三维模型,可以根据指定天区,对满足一定条件的恒星从星表数据库中进行检索,然后在三维天球坐标系中形象地显示其分布,实现了星表查询结果的三维可视化。
再次,对于高维光谱数据分类研究。随机森林是一种高效、稳定的算法,和其他算法相比在效率和准确率上具有一定的优势。随机森林中计算效率和准确率,受树的个数和随机属性的个数影响。在保证训练时间和准确率的情况下,选择适当的阂值,可以使训练时间最短准确率最高。合适的树的个数阈值会在保证准确率的基础上,使训练时间最短；而合适的随机属性的个数会使得训练的时间最短。而阈值是和数据相关的,阈值选取的好坏直接影响效率和准确率。本文提出了利用遗传算法优化随机森林分类参数的模式。利用该模式可以快速地确定随机森林进行光谱分类时所需的关键参数,从而改变了传统单纯凭经验设定随机森林分类参数的方式,提高了分类算法的自动化和智能化程度,提高了分类准确率,减少了分类器训练时间。
最后,针对激变变星的搜寻,提出了利用PCA降维与BP人工神经网络相结合的稀少天体的数据挖掘方法。利用PCA降维,大大减少了高维光谱数据的维度空间,然后利用BP人工神经网络进行筛选,提高了激变变星搜寻的准确率,减少了模型训练时间。实验证明,该方法对于发现特殊天体是行之有效的。该方法不仅对激变变星适用,对于其它类别的特殊天体也是适用的。该方法可极大地减少人工处理的工作强度和时间。由于速度快,基本可满足LAMOST光谱数据的准实时处理。如果具备并行数据处理环境,还可以使数据的输入、降维、挖掘等操作同时进行,提高科学成果的产出率。
It is a permanent topic for human beings how the universe is formed, developed and evoluted. The universe contains all of space, time, material and energy. The research level of universe marks the position of a country in the frontier of science and technology and has special significance to many disciplines, being the great impetus to modern science and technology, especially to the sophisticated space technology development.
There are two basic ways for modern cosmic research in visible bands:stellar spectrum and astronomical image. The former is one-dimensional data, while the latter is two-dimensional data. They have close relationship between them. By analyzing spectra, people can measure many chemical components and physical parameters of stellar objects, qualitatively or quantitatively, such as the chemical composition, the surface temperature, the luminosity, the diameter, the quality, the radial velocity and rotation, directly or indirectly. Therefore, spectral analysis occupies an important position in astronomy and astrophysics. Astronomical image analysis provides another way to research celestial bodies. Using astronomical image, we can study the target morphological structure of celestial body, including celestial age, state, evolution tendency, and provide important technical support for astronomical observation and study.
The National Major Scientific Project LAMOST (Large Sky Area Multi-Object Fiber Spectroscopic Telescope) was set up in 1997 and completed an adoption of national acceptance in June,2009 and was put into operation since then. The aperture of LAMOST is 4m, enabling it to obtain the spectra of objects as faint as down to 20.5 magnitudes. Within a 5°field of view, it may accommodate as many as 4000 optical fibers. So the light from 4000 celestial objects will be led into a number of spectrographs simultaneously. Thus the telescope will be the one that possesses the highest spectrum acquiring rate in the world. The observation targets of LAMOST are galaxies and stars in the universe. With the operation of LAMOST, thousands of spectra at every observation night can be obtained and the total volume of spectrum data can as many as billions of bytes. So the automated identification and analysis of spectra data is a challenging task. It needs the methods of automated identification and analysis, including spectra identification, classification and parameter measurements.
WOSDU (Weihai Observatory of Shandong University) is set up to find asteroid and supernova. Every day, it generates large volume of astronomical image data. In asteroid detection, for example, many celestial images are produced everyday. The size of each image is 2048×2048×16bit,8M. To find new asteroids, we must first detect the celestial bodies in the image, and then transform the pixel coordinates to celestial sphere coordinates. After that, a matching process is carried out in the celestial catalog to seek out whether the targets are already in the catalog or not. If not, the targets will be considered as asteroid candidates and observed later, and their orbits will be calculated for further identification. Because of the significant number of images, a lot of processing must be involved. The target detection is one of the important processing steps. In the target detection, the accuracy and speed are the most important factors to be considered. Our effort is to find a method to detect the targets in the image fast and effectively. It follows that the fast and effective processing for such huge amounts of astronomical data puts forward an urgent need to computer information technology. In the meantime, the mass characteristics and openness of astronomical data open a new research and application field for computer information technology. The timely and effective processing of such massive data needs to resort to many modern information processing technologies, such as image processing, data mining, and signal processing, and so on.
This project, sponsored by National Science Foundation Fund, focuses on the key problems in astronomical research field, such as the astronomical data pretreatment, target detection from astronomical image, the classification of high-dimensional data, the data mining of rare celestial objects and so on, by means of data mining, image processing, artificial intelligence, signal processing and other advanced information technologies. The astronomic data to be used are from LAMOST and WOSDU. A series of effective algorithms are designed, verified and will be put into use for LAMOST celestial spectral automatic identification and analysis system. The study is an interdisciplinary research between astronomy and information; it is a concrete application of the latest computer information technologies to in the field of astronomy, so as to achieve new scientific achievements. Therefore, this research has a very good theoretical research and practical application value.
The key content of this project includes four aspects:astronomical data pretreatment (spectra denoising) and emission line identification; target detection in astronomical image, celestial spectra classification and data mining of rare celestial bodies.
The following research and innovation works have been done respecting to the key issues mentioned above:
Firstly, our research focuses on the astronomical spectrum denoising. One-dimensional astronomical spectra observed by the astronomical spectroscopic telescope are often degraded by noise in the acquisition phase and have a poor signal-to-noise ratio. The reduction of noise is highly desirable for a lot of reasons. Noise reduction, as an integral part of signal estimation, has been an extensively studied for many years in the signal processing community. The goal of signal denoising is to recover the original signal from noisy signal corrupted by additive noise. Over the past twenty years, there has been considerable interest in the use of wavelet transforms for removing the noise from signals. Many thresholding rules based on the orthonormal wavelets have been proposed. However, as Coifman and Donoho pointed out, the denoising algorithm based on the orthonormal wavelets exhibits pseudo Gibbs phenomena in the neighborhood of discontinuities. Therefore, they proposed a translation-invariant denoising scheme to reduce the artifacts. In addition, it has been shown that a redundant representation is substantially superior to a nonredundant representation for signal denoising in term of mean-squared error and signal-to-noise ratio. Therefore, the translation-invariant redundant transforms are desirable for spectra denoising. The dual-tree complex wavelet transform introduced by Kingsbury is redundant and near translation-invariant. In this paper, we propose a spectra denoising algorithm based on the dual-tree complex wavelet transform (DTCWT), which can give higher signal-to-noise ratio and better quality. In astronomical spectra preprocessing, the adaptive denoising method has been studied based on the dual-tree complex wavelet transform. This method adjusts the complex wavelet coefficients by MAP estimation theory in order to suppress the noise. On the base of protecting the spectral line and other important information, this method suppresses the noise and pseudo Gibbs phenomenon, improves the efficiency of the algorithm, and provides an efficient tool for later spectra processing. In addition, we proposed a new method to identify emission line stars (ELS) spectra automatically. Stellar spectra are characterized by obvious absorption lines or absorption bands, while those with emission lines are usually special stars such as Cataclysmic Variable stars (CVs), HerbigAe/Be etc. The further study of this kind of spectra is meaningful. The new method to identify emission line stars (ELS) spectra is like this:after the continuum normalization is done for the original spectral flux, line detection is made by comparing the normalized flux with the mean and standard deviation of the flux in its neighbor region. The results of the experiment on massive spectra from SDSS DR8 indicate that the method can identify ELS spectra completely and accurately. Since no complicated transformation and computation are involved in this method, the identifying process is fast and it is ideal for the ELS detection in large sky survey projects like LAMOST and SDSS.
Secondly, our research is on the stellar object detection. In astronomical research, the Charge Coupled Device (CCD) images obtained from celestial observations are usually stored in Flexible Image Transport System (FITS) format and the sizes of such images are usually very large,8 Megabytes or more being not unusual. In addition, the amount of such images is great due to continuous celestial observations. So the demand of real time processing of these large images is challenging. This paper proposes an efficient method to detect objects, which is an important step in astronomical image processing, by designing a scan accelerator and a recursive measure routine. A method to detect target in astronomical image has been designed and implemented based on space domain. The experiments showed that by scanning in a recursive way and using a designed accelerator, the detection process can be greatly sped up and multi-objects can be detected quickly and many other parameters of the targets can be obtained. In addition, a 3-D visual system has been established. The stars that met the specific criteria in a certain sky region can be retrieved from UCAC2 catalog and their distribution can be displayed in the 3-D celestial sphere system. In this way, the retrieval information can be visualized.
Thirdly, a scheme to optimize the Random Forests classification parameters for astronomical spectra using Genetic Algorithm has been proposed. As an efficient and stable algorithm for high-dimensional spectral data classification, random forest has some advantages compared to other algorithms in the efficiency and accuracy. Random forest's computation efficiency and classification accuracy are affected by the number of trees and the number of attributes randomly selected. The appropriate thresholds are chosen to minimize training time and get higher accuracy while ensuring that the accuracy is within an acceptable range. Appropriate threshold of the number of trees will obtain the shortest training time while ensuring the accuracy. In addition, the appropriate number of random attributes will make the training time minimized. The threshold is relevant to the data. Therefore the threshold selected will affect efficiency and accuracy. In this paper, we proposed a scheme which can quickly determine the parameters needed by Random Forests in classification applications and improve the automation and intelligence of classification by avoiding the manual parameter estimation. This method can also improve the classification accuracy and reduce the training time of the classifier.
Finally, a data mining method for searching cataclysmic variables has been proposed. This method can screen out rare celestial bodies effectively by combining PCA and BP ANN. By PCA dimension reduction, the high dimensional data space has been greatly reduced, and after that, BP ANN is used to screen out rare celestial objects with high accuracy. In this way, the training time becomes shorter. Experiments show that the proposed method is effective for the detection of specific celestial objects. The method can be used not only to search the Cataclysmic Variable stars but also to find other types of special objects. It can greatly reduce the power of work and time of manual processing. Due to the high speed, it can mainly meet the LAMOST quasi-real-time spectral processing requirements. With a parallel data processing environment, the data input, dimension reduction, data mining and other operations can be done simultaneously, thus improving the outcome of scientific research.
引文
[1]Mallat S,杨力华.信号处理的小波导引[M].北京：机械工业出版社,2002.
[2]Donoho D. De-noising by Soft-thresholding [J]. Information Theory, IEEE Transactions on,2002,41(3):613-627.
[3]Fligge M, Solanki S. Noise Reduction in Astronomical Spectra Using Wavelet Packets [J]. Astronomy and Astrophysics Supplement Series,1997,124(3): 579-587.
[4]赵瑞珍,胡占义,胡绍海.天体光谱信号去噪的小波域复合阈值新算法[J].光谱学与光谱分析,2007,27(008)：1644-1647.
[5]Starck J, Murtagh F. Astronomical Image and Signal Processing [J]. IEEE Signal Processing Magazine,2001,18(2):30-40.
[6]罗林,王黎,程卫东,等天文图像多帧盲反卷积收敛性的增强方法[J].物理学报,2006,55(012)：6708-6714.
[7]Liu H, Guo Y, Zheng G Image Denoising Based on Least Squares Support Vector Machines:Proceedings of the 6th World Congress on Intelligent Control and Automation, Dalian, China,2006[C]. IEEE,2007:4180-4184.
[8]毛志红,马利庄,赵明喜.鲁棒估计器在3D网格降噪中的应用[J].软件学报,2007,18(2)：453-460.
[9]Niu Y, Shen L. A Novel Approach to Image Denoising Using the Pareto Optimal Curvelet Thresholds:Proceedings of the 2007 International Conference on Wavelet Analysis and Pattern Recognition, Beijing, China, 2007[C]. IEEE,2008:630-635.
[10]Ashamol V, Sreelekha Q Sathidevi P. Diffusion-based Image Denoising Combining Curvelet and Wavelet:Proceedings of the 15th International Conference on Systems, Signals and Image Processing, Bratislava 2008[C]. IEEE,2008:169-172.
[11]Wu J, Ruan Q. An Adaptive Edge Enhancing Image Denoising Model Based on Fuzzy Theory:Proceedings of the International Symposium on Intelligent Signal Processing and Communication Systems, Xiamen,2008[C]. IEEE: 216-219.
[12]Rabbani H, Vafadust M, Gazor S. Image Denoising Based on a Mixture of Laplace Distributions with Local Parameters in Complex Wavelet Domain: Proceedings of the 2006 IEEE International Conference on Image Processing, Atlanta, GA 2006[C].2007:IEEE:2597-2600.
[13]Luisier Florian, Blu, Thierry, Unser, Michael. Image denoising in mixed poissongaussian noise. IEEE Transactions on Image Processing[J], v 20, n 3, p 696-708, March 2011
[14]Tammana Q Zheng Y Image Denoising Using Multi-Resolution Coefficient Support Based Empirical Wiener Filtering:proceedings of the 2006 IEEE International Conference on Digital Object Identifier, Atlanta, GA,2006[C]. IEEE,2007:2613-2616.
[15]Ranganathan V, von Borries R. Sliced Ridgelet Transform for Image Denoising: proceedings of the 4th Digital Signal Processing Workshop and 12th Signal Processing Education Workshop, Teton National Park, WY 2006[C]. IEEE, 2006:209-213.
[16]Pan JC, Zhang C, Guo Q. Image Enhancement Based On Shearlet Transform [J]. ICIC Express Letters,2009,3(3):621-626.
[17]Pan JC, Zhang C, Guo Q. Spectra Denoising Based on the Dual-Tree Complex Wavelet Transform:Proceedings of the International Conference on Audio, Language and Image Processing, Shanghai,2008[C].IEEE,2008:1121-1125
[18]Li D, Simske S, Mersereau RM. Image Denoising Through Support Vector Regression:Proceedings of the IEEE International Conference on Image Processing, San Antonio, TX 2007[C]. IEEE,2007:1522-4880
[19]Chen B, Geng Z, Yang Y,. Dual-tree Complex Wavelets Transforms for Image Denoising:proceedings of the Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing, Qingdao 2007[C]. IEEE,2007:70-74.
[20]Huang Z-H, He X-P, Fang B. Image Denoising and Comparison by Improving Threshold Based on the Dyadic Wavelet Transform:Proceedings of the 07 International Conferences on Wavelet Analysis and Pattern Recognition, Beijing 2007[C]. IEEE,2007:35-539.
[21]Zhang W, Sui Q, Liu W. Image Denoising Based on Multiple Wavelet Representations and Universal Hidden Markov Tree:Proceedings of the IEEE International Conference on Automation and Logistics, Jinan 2007[C]. IEEE, 2007:2276-2280.
[22]Liu C, Wang H, Wang Y. Image Denoising Based on Wavelet Edge Detection by Scale Multiplication:Proceedings of the 07 IEEE International Conference on Integration Technology, Shenzhen 2007[C]. IEEE,2007:701-705.
[23]Bao Z-C, You X-Q Xing C-F. Image Denoising by Using Non-Tensor Product Wavelets Filter Banks:Proceedings of the 2007 International Conference on Machine Learning and Cybernetics, Hong Kong,2007[C]. IEEE,2007:1734-1738.
[24]Rabbani H, Vafadust M, Gazor S. Image Denoising Employing a Bivariate Cauchy Distribution with Local Variance in Complex Wavelet Domain: Proceedings of the 4th Digital Signal Processing Workshop and 12th-Signal Processing Education Workshop, Teton National Park, WY 2006[C]. IEEE, 2006:203-208.
[25]Zhang W, Wei K, Liu X. Image Denoising Using Multiple Wavelet Representations and Local Contextual Hidden Markov Model:Proceedings of the 2007 IEEE International Conference on Robotics and Biomimetics, Sanya, 2008[C]. IEEE,2008:156-161.
[26]Minasyan S, Astola J, Egiazarian K. Parametric Haar-Like Transforms in Image Denoising:Proceedings of the 2006 IEEE International Conference on Image Processing,2006[C]. IEEE,2007:2629-2632.
[27]Rabbani H, Vafadoost M, Selesnick I. Wavelet Based Image Denoising with A Mixture of Gaussian Distributions with Local Parameters:proceedings of,48th International Symposium ELMAR-2006 focused on Multimedia Signal Processing and Communications,2006[C]. IEEE,2007:85-88.
[28]Yuanyuan B, Wenbo W. Image Noise Reduction Based on Wavelet Packet and Realization with Matlab [J]. Journal of Liaoning Technical University (Natural Science),2008,27:224-226.
[29]ZHOU Y, ZHAO J, KONG M. Image Denoising Based on Wavelet [J]. Journal of West Anhui University,2007,23(5):51-53.
[30]ZHAO T, ZHANG X, ZHOU K. Wavelet Tansform in the Application of Remote Sensing Image Denoising [J]. CHINA SCIENCE AND TECHNOLOGY INFORMATION,2007,1:248-252.
[31]Li X-c, Zhu S-a. Survey of Wavelet Domain Image Denoising [J]. Journal of Image and Graphics,2006,11(9):1201-1209.
[32]Zhu J. The Image Denoising Algorithm of Principal Direction Anisotropic Difusion Wavelet Shrinkage [J]. Journal of Heilongjiang August First Land Reclamation University,2008,20(2):75-79.
[33]PENG J-x, ZHOU W-l. Infrared Background Suppression for Segmenting and Detecting Small target[J], Acta Electronica Sinica,1999,27(12):47-51.
[34]Jian-tao H, ZHANG Y, Zeng-ping C. Real Time Detection Algorithm of Weak Targets in Astronomical Images [J]. Opto-electronic Engineering,2005,12.
[35]尤育赛.关于数字图像处理在运动目标检测和医学检验中若干应用的研究[D].杭州：浙江大学,2005.
[36]雍杨.小目标检测与识别技术研究[D].北京：中国科学院光电技术研究所,2006.
[37]张海英,温玄,张田文.低信噪比多目标检测的贪心算法[J].计算机学报,2008,Vol.31 No.1 142-150.
[38]彭嘉雄,彭铁.弱目标检测的图像流法[J].红外与激光工程,1996,25(4)：34-40.
[39]周卫祥,彭嘉雄.红外图像序列运动小目标检测的预处理算法研究[J].国防科技大学学报,1999,21(005)：57-60.
[40]张兵,卢焕章.动态规划算法在运动点目标检测的应用研究[J].电子与信息学报,2004,Vol.26 No.12,1895-1900.
[41]Zhu Z, Li Z, Liang H,等Gray-scale Morphological Filter for Small-target Detection:Proceedings of the SPIE,2000[C].28-34.
[42]李国宽,彭嘉雄.基于向量小波变换的小目标检测方法[J].华中理工大学学报,2000,28(001)：73-75.
[43]周杰,彭嘉雄,丁明跃,等.基于小波变换的运动点目标检测方法[J].宇航学报,1996,17(003)：20-24.
[44]冯毅.基于独立分量分析的运动目标检测与跟踪[D].大连：大连理工大学,2008.
[45]Fernandez-Caballero A, Mira J, Fernandez M,等On Motion Detection Through a Multi-layer Neural Network Architecture [J]. Neural Networks, 2003,16(2)：205-222.
[46]余农,吴常泳,李范鸣,等.自动目标检测的形态学神经网络与模拟退火学习算法[J].中国科学：E辑,2003,33(006)：505-521.
[47]查宇飞,楚瀛,王勋,马时平,毕笃彦.一种基于Boosting判别模型的运动阴影检测方法[J].计算机学报,2007,Vol.30 No.8 1295-1301.
[48]陶卿,曹进德,孙德敏.基于支持向量机分类的回归方法[J].软件学报,2002,13(5)：1024-1028.
[49]Breiman L. Random forests [J]. Machine Learning,2001,45(1):5-32.
[50]M KE, RT N. Algorithm Forming Distance-based Outliers in Large Datasets: Proceedings of the the 24th International Conference on Very Large Data Bases, San Francisco,1988[C]. Morgan Kaufmann Publishers:392-403.
[51]Barnett V, Lewis T, Abeles F. Outliers in Statistical Data [J]. Physics Today, 1979,32:73.
[52]Arning A, Agrawal R, Raghavan P. A Linear Method for Deviation Detection in Large Databases:Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining,1996[C].164-169.
[53]Breunig M, Kriegel H, Ng R. LOF:Identifying Density-based Local Outliers [J]. Sigmod Record,2000,29(2):93-104.
[54]Jifu Z, Yi-Yong J, Li-Hua H. A Concept Lattice Based Recognition Method of Celestial Spectra Outliers [J]. Acta Automatica Sinica,2008,34(9):1060-1066.
[55]魏藜,宫学庆,钱卫宁,等.高维空间中的离群点发现[J].软件学报,2002,13(002)：280-290.
[56]Aggarwal C, Yu S. An Effective and Efficient Algorithm for High-dimensional Outlier Detection [J]. The VLDB Journalia The International Journal on Very Large Data Bases,2005,14(2):211-221.
[57]郭强.基于剪切波变换的图像统计模型及其应用研究[D].上海：上海大学,2010.
[58]Kingsbury N. Image Processing with Complex Wavelets [J]. Philosophical Transactions of the Royal Society of London Series A:Mathematical, Physical and Engineering Sciences,1999,357(1760):2543.
[59]Selesnick I, Baraniuk R, Kingsbury N. The Dual-tree Complex Wavelet Transform [J]. Signal Processing Magazine, IEEE,2005,22(6):123-151.
[60]Coifman R, Donoho D. Translation-invariant De-noising [J]. LECTURE NOTES IN STATISTICS-NEW YORK-SPRINGER VERLAG, 1995:125-125.
[61]Lang M, Guo H, Odegard J. Noise Reduction Using an Undecimated Discrete Wavelet Transform [J]. Signal Processing Letters, IEEE,2002,3(1):10-12.
[62]Donoho D, JOHNSTONE J. Ideal Spatial Adaptation by Wavelet Shrinkage [J]. Biometrika,1994,81(3):425.
[63]Sendur L, Selesnick I. Bivariate Shrinkage Functions for Wavelet-based Denoising Exploiting Interscale Dependency [J]. Signal Processing, IEEE Transactions on,2002,50(11):2744-2756.
[64]刘中田,邱宽民,赵瑞珍.基于谱线特征匹配的恒星光谱自动识别方法[J].光谱学与光谱分析.2008年28卷6期：1435-1438
[65]朱光华,罗阿理,赵永恒LAMOST星系光谱的红移自动测量[J].光谱学与光谱分析,2005,25(006)：1002-1005.
[66]李磊,平西建,童莉.基于高斯拟合的自适应多阂值分割算法[J].计算机应用研究,2006,23(008)：162-163.
[67]罗阿理.光谱自动分析技术中的模式识别方法研究[D].北京：中国科学院国家天文台,2001.
[68]孔兵,王昭.激光光斑的高斯拟合[J].激光技术,2002,26(004)：277-278.
[69]Starck J, Murtagh F. Astronomical Image and Data Analysis[M].2006.
[70]Niu Y, Shen L. A Novel Approach to Image Denoising Using the Pareto Optimal Curvelet Thresholds:Proceedings of the 2007 International Conference on Wavelet Analysis and Pattern Recognition, Beijing,2007[C]. IEEE,2008:630-635.
[71]Velde K. Multi-scale Color Image Enhancement:Proceedings of the International Conference on Image Processing,1999[C]. IEEE,2002:584-587.
[72]Colonna GREaF. Generalized Discrete Random Transform and Application to Image Processing [J]. Advances in Imaging and Electron Physics,2008,151: 169-239.
[73]Jingchang Pan, Caiming Zhang and Qiang Guo, Image Enhancement Based On Shearlet Transform[J]. ICIC Express Letters,2009.9,v3,n3,621-626.
[74]Guo Q, Yu S, Chen X. Shearlet-Based Image Denoising Using Bivariate Shrinkage with Intra-band and Opposite Orientation Dependencies: Proceedings of, the 2nd International Joint Conference on Computational Sciences and Optimization,2009[C]. IEEE,2009:863-866.
[75]Xiangqun Cui. [J]SPIE,2009,41:473.
[76]Jacoby GH., D.A. Hunter, C.A. Christian. The Astrophysical Journal Supplement Series[J].1984,56:257-281.
[77]刘中田,邱宽民,杨金福(Liu Zhongtian. Oiu Kuanmin.Yang Jinfu) [J]光学学报(ACTA OPTICA SINICA),2008,28(006):1101-1105.
[78]罗阿理,赵永恒(Luo Ali,Zhao Yongheng) [J]天体物理学报(Acta Astrophysica Sinica),2000:04.
[79]Szkody P., S.F. Anderson, M. Agueros, et al. [J]. The Astronomical Journal, 2002,123:430.
[80]Szkody P., S.F. Anderson, M. Hayden, et al. [J]. The Astronomical Journal, 2009,137:4011.
[81]Szkody P., O. Fraser, N. Silvestri, et al. [J]. The Astronomical Journal,2003, 126:1499.
[82]Szkody P., A. Henden, O. Fraser, et al. [J] The Astronomical Journal,2004,128: 1882.
[83]Szkody P., A. Henden, O.J. Fraser, et al. [J]. The Astronomical Journal,2005, 129:2386.
[84]Szkody P., A. Henden, L. Mannikko, et al. [J]. The Astronomical Journal,2007, 134:185.
[85]Wils P., B.T. G nsicke, A.J. Drake, et al. [J]. Monthly Notices of the Royal Astronomical Society,2010,402(1):436-446.
[86]Starck J.L., R. Siebenmorgen, R. Gredel. [J]. The astrophysical journal,1997, 482:1011.
[87]Eisenstein D.J., D.H. Weinberg, E. Agol, et al. [J]. The Astronomical Journal, 2011,142:72.
[88]Aihara H., C. Allende Prieto, D. An, et al. [J]. The Astrophysical Journal Supplement Series,2011,193:29.
[89]Naik S, Murthy C. Distinct Multicolored Region Descriptors for Object Recognition [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2007,29(7):1291-1296.
[90]Serre T, Wolf L, Bileschi S. Robust Object Recognition with Cortex-like Mechanisms [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2007,29(3):411-426.
[91]Pham T, Smeulders A. Sparse Representation for Coarse and Fine Object Recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2006:555-567.
[92]王志衡,吴福朝.伪球滤波和边缘检测[J].软件学报,2008,19(4)：803-816.
[93]Pan H, Xia L. Efficient Object Recognition Using Boundary Representation and Wavelet Neural Network [J]. Neural Networks, IEEE Transactions,2008, 19(12):2132-2149.
[94]Vicente M, Hoyer P, Hyvarinen A. Equivalence of Some Common Linear Feature Extraction Techniques for Appearance-based Object Recognition Tasks [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions,2007,29(5): 896-900.
[95]Shotton J, Blake A, Cipolla R. Multiscale Categorical Object Recognition Using Contour Fragments [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2007:1270-1281.
[96]Definition of the Flexible Image Transport System (FITS) http://fits. gsfc. nasa. gov
[97]Detecting and Measuring Faint Point Sources with a CCD http://www.astrometrica.at
[98]Rafael C. Gonzalez RE. Woods, Digital Image Processing [M]. Beijing: Publishing House of Electronics Industry,2004.
[99]UCAC2 Documentation,http://ad.usno.navy.mil/ucac/
[100]WCSTools Telescope Data Center, http://tdc-www.harvard.edu/software/ wcstools
[101]Rafael C, Richard E, Steven L. Digital Image Processing Using MATLAB[M]. Beijing:Publishing House of Electronics Industry,2006.
[102]Hanselman D, Littlefield B. Mastering Matlab 7[M]. Pearson Education India.
[103]Yi S. New Outline of Astronomy (3rd edition)[M]. Publishing House of Huazhong University of Science and Technology,2005.
[104]Yan L. Popular Astronomy [M]. Publishing House of Guangxi Normal School, 2003.
[105]李金增,胡景耀.晚型星计算机自动光谱分类[J].天体物理学报, 1999,19(No.3):297-302
[106]Jingchang Pan, Peng Wei, Caiming Zhang, and Ali Luo, Outlier Detection Of Celestial Spectra Based On Modified GA[J]. ICIC Express Letters,2010.9, v3,n3,35-40.
[107]Random Forests:http://stat-www.berkeley.edu/users/breiman/RandomForests/
[108]Friedman N, Geiger D, Goldszmidt M. Bayesian Network Classifiers [J]. Machine Learning,1997,29(2):131-163.
[109]Liaw A, Wiener M. Classification and Regression by Random Forest [J]. R news,2002,2(3):18C22.
[110]Ho T. A Data Complexity Analysis of Comparative Advantages of Decision Forest Constructors [J]. Pattern Analysis & Applications,2002,5(2):102-112.
[111]Prinzie A, Van den Poel D. Random Multiclass Classification:Generalizing Random Forests to Random mnl and Random nb [J]. Lecture Notes in Computer Science,2007,4653:349-358.
[112]Prinzie A, Van den Poel D. Random Forests for Multiclass Classification: Random Multinomial Logit [J]. Expert Systems with Applications,2008,34(3): 1721-1732.
[113]The Sloan Digital Sky Survey http://www.sdss.org/
[114]Madgwick D, Hewett P, Mortlock D. Spectroscopic Detection of Type la Supernovae in the Sloan Digital Sky Survey [J]. The Astrophysical Journal Letters,2003,599:L33.
[115]Tu L, Luo A. New Supernova Candidates from the SDSS-DR7 Spectral Survey [J]. Research in Astronomy and Astrophysics,2009,9:635.
[116]http://simbad.u-strasbg.fr/simbad/
[117]Szkody P, Anderson S, Agleros M. Cataclysmic Variables from The Sloan Digital Sky Survey. Ⅰ. The First Results [J]. The Astronomical Journal,2002, 123:430.
[118]Szkody P, Fraser O, Silvestri N. Cataclysmic Variables from the Sloan Digital Sky Survey. Ⅱ. The Second Year [J]. The Astronomical Journal,2003,126: 1499.
[119]Szkody P, Henden A, Fraser O. Cataclysmic Variables from the Sloan Digital Sky Survey.Ⅲ. The Third Year [J]. The Astronomical Journal,2004,128:1882.
[120]Szkody P, Henden A, Fraser O. Cataclysmic Variables from Sloan Digital Sky Survey. Ⅳ The Fourth Year (2003)[J]. The Astronomical Journal,2005,129: 2386.
[121]Szkody P, Henden A, Agleros M. Cataclysmic Variables from Sloan Digital Sky Survey. Ⅴ. The Fifth Year (2004)[J]. The Astronomical Journal,2006,131: 973.
[122]Szkody P, Henden A, Mannikko L. Cataclysmic Variables from Sloan Digital Sky Survey. Ⅵ. The Sixth Year (2005)[J]. The Astronomical Journal,2007, 134:185.
[123]李宗云,刘武.20个激变变星或相关天体的分光证认[J].天文学报,1999,40(001)：1-15.
[124]姜斌,潘景昌,郭强,等.PCA和相融性度量在聚类算法中的应用[J].电子科技大学学报,2007,36(006)：1292-1295.
[125]覃冬梅,赵永恒.一种基于主分量分析的恒星光谱快速分类法[J].光谱学与光谱分析,2003,23(001)：182-186.
[2]Donoho D. De-noising by Soft-thresholding [J]. Information Theory, IEEE Transactions on,2002,41(3):613-627.
[3]Fligge M, Solanki S. Noise Reduction in Astronomical Spectra Using Wavelet Packets [J]. Astronomy and Astrophysics Supplement Series,1997,124(3): 579-587.
[4]赵瑞珍,胡占义,胡绍海.天体光谱信号去噪的小波域复合阈值新算法[J].光谱学与光谱分析,2007,27(008)：1644-1647.
[5]Starck J, Murtagh F. Astronomical Image and Signal Processing [J]. IEEE Signal Processing Magazine,2001,18(2):30-40.
[6]罗林,王黎,程卫东,等天文图像多帧盲反卷积收敛性的增强方法[J].物理学报,2006,55(012)：6708-6714.
[7]Liu H, Guo Y, Zheng G Image Denoising Based on Least Squares Support Vector Machines:Proceedings of the 6th World Congress on Intelligent Control and Automation, Dalian, China,2006[C]. IEEE,2007:4180-4184.
[8]毛志红,马利庄,赵明喜.鲁棒估计器在3D网格降噪中的应用[J].软件学报,2007,18(2)：453-460.
[9]Niu Y, Shen L. A Novel Approach to Image Denoising Using the Pareto Optimal Curvelet Thresholds:Proceedings of the 2007 International Conference on Wavelet Analysis and Pattern Recognition, Beijing, China, 2007[C]. IEEE,2008:630-635.
[10]Ashamol V, Sreelekha Q Sathidevi P. Diffusion-based Image Denoising Combining Curvelet and Wavelet:Proceedings of the 15th International Conference on Systems, Signals and Image Processing, Bratislava 2008[C]. IEEE,2008:169-172.
[11]Wu J, Ruan Q. An Adaptive Edge Enhancing Image Denoising Model Based on Fuzzy Theory:Proceedings of the International Symposium on Intelligent Signal Processing and Communication Systems, Xiamen,2008[C]. IEEE: 216-219.
[12]Rabbani H, Vafadust M, Gazor S. Image Denoising Based on a Mixture of Laplace Distributions with Local Parameters in Complex Wavelet Domain: Proceedings of the 2006 IEEE International Conference on Image Processing, Atlanta, GA 2006[C].2007:IEEE:2597-2600.
[13]Luisier Florian, Blu, Thierry, Unser, Michael. Image denoising in mixed poissongaussian noise. IEEE Transactions on Image Processing[J], v 20, n 3, p 696-708, March 2011
[14]Tammana Q Zheng Y Image Denoising Using Multi-Resolution Coefficient Support Based Empirical Wiener Filtering:proceedings of the 2006 IEEE International Conference on Digital Object Identifier, Atlanta, GA,2006[C]. IEEE,2007:2613-2616.
[15]Ranganathan V, von Borries R. Sliced Ridgelet Transform for Image Denoising: proceedings of the 4th Digital Signal Processing Workshop and 12th Signal Processing Education Workshop, Teton National Park, WY 2006[C]. IEEE, 2006:209-213.
[16]Pan JC, Zhang C, Guo Q. Image Enhancement Based On Shearlet Transform [J]. ICIC Express Letters,2009,3(3):621-626.
[17]Pan JC, Zhang C, Guo Q. Spectra Denoising Based on the Dual-Tree Complex Wavelet Transform:Proceedings of the International Conference on Audio, Language and Image Processing, Shanghai,2008[C].IEEE,2008:1121-1125
[18]Li D, Simske S, Mersereau RM. Image Denoising Through Support Vector Regression:Proceedings of the IEEE International Conference on Image Processing, San Antonio, TX 2007[C]. IEEE,2007:1522-4880
[19]Chen B, Geng Z, Yang Y,. Dual-tree Complex Wavelets Transforms for Image Denoising:proceedings of the Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing, Qingdao 2007[C]. IEEE,2007:70-74.
[20]Huang Z-H, He X-P, Fang B. Image Denoising and Comparison by Improving Threshold Based on the Dyadic Wavelet Transform:Proceedings of the 07 International Conferences on Wavelet Analysis and Pattern Recognition, Beijing 2007[C]. IEEE,2007:35-539.
[21]Zhang W, Sui Q, Liu W. Image Denoising Based on Multiple Wavelet Representations and Universal Hidden Markov Tree:Proceedings of the IEEE International Conference on Automation and Logistics, Jinan 2007[C]. IEEE, 2007:2276-2280.
[22]Liu C, Wang H, Wang Y. Image Denoising Based on Wavelet Edge Detection by Scale Multiplication:Proceedings of the 07 IEEE International Conference on Integration Technology, Shenzhen 2007[C]. IEEE,2007:701-705.
[23]Bao Z-C, You X-Q Xing C-F. Image Denoising by Using Non-Tensor Product Wavelets Filter Banks:Proceedings of the 2007 International Conference on Machine Learning and Cybernetics, Hong Kong,2007[C]. IEEE,2007:1734-1738.
[24]Rabbani H, Vafadust M, Gazor S. Image Denoising Employing a Bivariate Cauchy Distribution with Local Variance in Complex Wavelet Domain: Proceedings of the 4th Digital Signal Processing Workshop and 12th-Signal Processing Education Workshop, Teton National Park, WY 2006[C]. IEEE, 2006:203-208.
[25]Zhang W, Wei K, Liu X. Image Denoising Using Multiple Wavelet Representations and Local Contextual Hidden Markov Model:Proceedings of the 2007 IEEE International Conference on Robotics and Biomimetics, Sanya, 2008[C]. IEEE,2008:156-161.
[26]Minasyan S, Astola J, Egiazarian K. Parametric Haar-Like Transforms in Image Denoising:Proceedings of the 2006 IEEE International Conference on Image Processing,2006[C]. IEEE,2007:2629-2632.
[27]Rabbani H, Vafadoost M, Selesnick I. Wavelet Based Image Denoising with A Mixture of Gaussian Distributions with Local Parameters:proceedings of,48th International Symposium ELMAR-2006 focused on Multimedia Signal Processing and Communications,2006[C]. IEEE,2007:85-88.
[28]Yuanyuan B, Wenbo W. Image Noise Reduction Based on Wavelet Packet and Realization with Matlab [J]. Journal of Liaoning Technical University (Natural Science),2008,27:224-226.
[29]ZHOU Y, ZHAO J, KONG M. Image Denoising Based on Wavelet [J]. Journal of West Anhui University,2007,23(5):51-53.
[30]ZHAO T, ZHANG X, ZHOU K. Wavelet Tansform in the Application of Remote Sensing Image Denoising [J]. CHINA SCIENCE AND TECHNOLOGY INFORMATION,2007,1:248-252.
[31]Li X-c, Zhu S-a. Survey of Wavelet Domain Image Denoising [J]. Journal of Image and Graphics,2006,11(9):1201-1209.
[32]Zhu J. The Image Denoising Algorithm of Principal Direction Anisotropic Difusion Wavelet Shrinkage [J]. Journal of Heilongjiang August First Land Reclamation University,2008,20(2):75-79.
[33]PENG J-x, ZHOU W-l. Infrared Background Suppression for Segmenting and Detecting Small target[J], Acta Electronica Sinica,1999,27(12):47-51.
[34]Jian-tao H, ZHANG Y, Zeng-ping C. Real Time Detection Algorithm of Weak Targets in Astronomical Images [J]. Opto-electronic Engineering,2005,12.
[35]尤育赛.关于数字图像处理在运动目标检测和医学检验中若干应用的研究[D].杭州：浙江大学,2005.
[36]雍杨.小目标检测与识别技术研究[D].北京：中国科学院光电技术研究所,2006.
[37]张海英,温玄,张田文.低信噪比多目标检测的贪心算法[J].计算机学报,2008,Vol.31 No.1 142-150.
[38]彭嘉雄,彭铁.弱目标检测的图像流法[J].红外与激光工程,1996,25(4)：34-40.
[39]周卫祥,彭嘉雄.红外图像序列运动小目标检测的预处理算法研究[J].国防科技大学学报,1999,21(005)：57-60.
[40]张兵,卢焕章.动态规划算法在运动点目标检测的应用研究[J].电子与信息学报,2004,Vol.26 No.12,1895-1900.
[41]Zhu Z, Li Z, Liang H,等Gray-scale Morphological Filter for Small-target Detection:Proceedings of the SPIE,2000[C].28-34.
[42]李国宽,彭嘉雄.基于向量小波变换的小目标检测方法[J].华中理工大学学报,2000,28(001)：73-75.
[43]周杰,彭嘉雄,丁明跃,等.基于小波变换的运动点目标检测方法[J].宇航学报,1996,17(003)：20-24.
[44]冯毅.基于独立分量分析的运动目标检测与跟踪[D].大连：大连理工大学,2008.
[45]Fernandez-Caballero A, Mira J, Fernandez M,等On Motion Detection Through a Multi-layer Neural Network Architecture [J]. Neural Networks, 2003,16(2)：205-222.
[46]余农,吴常泳,李范鸣,等.自动目标检测的形态学神经网络与模拟退火学习算法[J].中国科学：E辑,2003,33(006)：505-521.
[47]查宇飞,楚瀛,王勋,马时平,毕笃彦.一种基于Boosting判别模型的运动阴影检测方法[J].计算机学报,2007,Vol.30 No.8 1295-1301.
[48]陶卿,曹进德,孙德敏.基于支持向量机分类的回归方法[J].软件学报,2002,13(5)：1024-1028.
[49]Breiman L. Random forests [J]. Machine Learning,2001,45(1):5-32.
[50]M KE, RT N. Algorithm Forming Distance-based Outliers in Large Datasets: Proceedings of the the 24th International Conference on Very Large Data Bases, San Francisco,1988[C]. Morgan Kaufmann Publishers:392-403.
[51]Barnett V, Lewis T, Abeles F. Outliers in Statistical Data [J]. Physics Today, 1979,32:73.
[52]Arning A, Agrawal R, Raghavan P. A Linear Method for Deviation Detection in Large Databases:Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining,1996[C].164-169.
[53]Breunig M, Kriegel H, Ng R. LOF:Identifying Density-based Local Outliers [J]. Sigmod Record,2000,29(2):93-104.
[54]Jifu Z, Yi-Yong J, Li-Hua H. A Concept Lattice Based Recognition Method of Celestial Spectra Outliers [J]. Acta Automatica Sinica,2008,34(9):1060-1066.
[55]魏藜,宫学庆,钱卫宁,等.高维空间中的离群点发现[J].软件学报,2002,13(002)：280-290.
[56]Aggarwal C, Yu S. An Effective and Efficient Algorithm for High-dimensional Outlier Detection [J]. The VLDB Journalia The International Journal on Very Large Data Bases,2005,14(2):211-221.
[57]郭强.基于剪切波变换的图像统计模型及其应用研究[D].上海：上海大学,2010.
[58]Kingsbury N. Image Processing with Complex Wavelets [J]. Philosophical Transactions of the Royal Society of London Series A:Mathematical, Physical and Engineering Sciences,1999,357(1760):2543.
[59]Selesnick I, Baraniuk R, Kingsbury N. The Dual-tree Complex Wavelet Transform [J]. Signal Processing Magazine, IEEE,2005,22(6):123-151.
[60]Coifman R, Donoho D. Translation-invariant De-noising [J]. LECTURE NOTES IN STATISTICS-NEW YORK-SPRINGER VERLAG, 1995:125-125.
[61]Lang M, Guo H, Odegard J. Noise Reduction Using an Undecimated Discrete Wavelet Transform [J]. Signal Processing Letters, IEEE,2002,3(1):10-12.
[62]Donoho D, JOHNSTONE J. Ideal Spatial Adaptation by Wavelet Shrinkage [J]. Biometrika,1994,81(3):425.
[63]Sendur L, Selesnick I. Bivariate Shrinkage Functions for Wavelet-based Denoising Exploiting Interscale Dependency [J]. Signal Processing, IEEE Transactions on,2002,50(11):2744-2756.
[64]刘中田,邱宽民,赵瑞珍.基于谱线特征匹配的恒星光谱自动识别方法[J].光谱学与光谱分析.2008年28卷6期：1435-1438
[65]朱光华,罗阿理,赵永恒LAMOST星系光谱的红移自动测量[J].光谱学与光谱分析,2005,25(006)：1002-1005.
[66]李磊,平西建,童莉.基于高斯拟合的自适应多阂值分割算法[J].计算机应用研究,2006,23(008)：162-163.
[67]罗阿理.光谱自动分析技术中的模式识别方法研究[D].北京：中国科学院国家天文台,2001.
[68]孔兵,王昭.激光光斑的高斯拟合[J].激光技术,2002,26(004)：277-278.
[69]Starck J, Murtagh F. Astronomical Image and Data Analysis[M].2006.
[70]Niu Y, Shen L. A Novel Approach to Image Denoising Using the Pareto Optimal Curvelet Thresholds:Proceedings of the 2007 International Conference on Wavelet Analysis and Pattern Recognition, Beijing,2007[C]. IEEE,2008:630-635.
[71]Velde K. Multi-scale Color Image Enhancement:Proceedings of the International Conference on Image Processing,1999[C]. IEEE,2002:584-587.
[72]Colonna GREaF. Generalized Discrete Random Transform and Application to Image Processing [J]. Advances in Imaging and Electron Physics,2008,151: 169-239.
[73]Jingchang Pan, Caiming Zhang and Qiang Guo, Image Enhancement Based On Shearlet Transform[J]. ICIC Express Letters,2009.9,v3,n3,621-626.
[74]Guo Q, Yu S, Chen X. Shearlet-Based Image Denoising Using Bivariate Shrinkage with Intra-band and Opposite Orientation Dependencies: Proceedings of, the 2nd International Joint Conference on Computational Sciences and Optimization,2009[C]. IEEE,2009:863-866.
[75]Xiangqun Cui. [J]SPIE,2009,41:473.
[76]Jacoby GH., D.A. Hunter, C.A. Christian. The Astrophysical Journal Supplement Series[J].1984,56:257-281.
[77]刘中田,邱宽民,杨金福(Liu Zhongtian. Oiu Kuanmin.Yang Jinfu) [J]光学学报(ACTA OPTICA SINICA),2008,28(006):1101-1105.
[78]罗阿理,赵永恒(Luo Ali,Zhao Yongheng) [J]天体物理学报(Acta Astrophysica Sinica),2000:04.
[79]Szkody P., S.F. Anderson, M. Agueros, et al. [J]. The Astronomical Journal, 2002,123:430.
[80]Szkody P., S.F. Anderson, M. Hayden, et al. [J]. The Astronomical Journal, 2009,137:4011.
[81]Szkody P., O. Fraser, N. Silvestri, et al. [J]. The Astronomical Journal,2003, 126:1499.
[82]Szkody P., A. Henden, O. Fraser, et al. [J] The Astronomical Journal,2004,128: 1882.
[83]Szkody P., A. Henden, O.J. Fraser, et al. [J]. The Astronomical Journal,2005, 129:2386.
[84]Szkody P., A. Henden, L. Mannikko, et al. [J]. The Astronomical Journal,2007, 134:185.
[85]Wils P., B.T. G nsicke, A.J. Drake, et al. [J]. Monthly Notices of the Royal Astronomical Society,2010,402(1):436-446.
[86]Starck J.L., R. Siebenmorgen, R. Gredel. [J]. The astrophysical journal,1997, 482:1011.
[87]Eisenstein D.J., D.H. Weinberg, E. Agol, et al. [J]. The Astronomical Journal, 2011,142:72.
[88]Aihara H., C. Allende Prieto, D. An, et al. [J]. The Astrophysical Journal Supplement Series,2011,193:29.
[89]Naik S, Murthy C. Distinct Multicolored Region Descriptors for Object Recognition [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2007,29(7):1291-1296.
[90]Serre T, Wolf L, Bileschi S. Robust Object Recognition with Cortex-like Mechanisms [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2007,29(3):411-426.
[91]Pham T, Smeulders A. Sparse Representation for Coarse and Fine Object Recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2006:555-567.
[92]王志衡,吴福朝.伪球滤波和边缘检测[J].软件学报,2008,19(4)：803-816.
[93]Pan H, Xia L. Efficient Object Recognition Using Boundary Representation and Wavelet Neural Network [J]. Neural Networks, IEEE Transactions,2008, 19(12):2132-2149.
[94]Vicente M, Hoyer P, Hyvarinen A. Equivalence of Some Common Linear Feature Extraction Techniques for Appearance-based Object Recognition Tasks [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions,2007,29(5): 896-900.
[95]Shotton J, Blake A, Cipolla R. Multiscale Categorical Object Recognition Using Contour Fragments [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2007:1270-1281.
[96]Definition of the Flexible Image Transport System (FITS) http://fits. gsfc. nasa. gov
[97]Detecting and Measuring Faint Point Sources with a CCD http://www.astrometrica.at
[98]Rafael C. Gonzalez RE. Woods, Digital Image Processing [M]. Beijing: Publishing House of Electronics Industry,2004.
[99]UCAC2 Documentation,http://ad.usno.navy.mil/ucac/
[100]WCSTools Telescope Data Center, http://tdc-www.harvard.edu/software/ wcstools
[101]Rafael C, Richard E, Steven L. Digital Image Processing Using MATLAB[M]. Beijing:Publishing House of Electronics Industry,2006.
[102]Hanselman D, Littlefield B. Mastering Matlab 7[M]. Pearson Education India.
[103]Yi S. New Outline of Astronomy (3rd edition)[M]. Publishing House of Huazhong University of Science and Technology,2005.
[104]Yan L. Popular Astronomy [M]. Publishing House of Guangxi Normal School, 2003.
[105]李金增,胡景耀.晚型星计算机自动光谱分类[J].天体物理学报, 1999,19(No.3):297-302
[106]Jingchang Pan, Peng Wei, Caiming Zhang, and Ali Luo, Outlier Detection Of Celestial Spectra Based On Modified GA[J]. ICIC Express Letters,2010.9, v3,n3,35-40.
[107]Random Forests:http://stat-www.berkeley.edu/users/breiman/RandomForests/
[108]Friedman N, Geiger D, Goldszmidt M. Bayesian Network Classifiers [J]. Machine Learning,1997,29(2):131-163.
[109]Liaw A, Wiener M. Classification and Regression by Random Forest [J]. R news,2002,2(3):18C22.
[110]Ho T. A Data Complexity Analysis of Comparative Advantages of Decision Forest Constructors [J]. Pattern Analysis & Applications,2002,5(2):102-112.
[111]Prinzie A, Van den Poel D. Random Multiclass Classification:Generalizing Random Forests to Random mnl and Random nb [J]. Lecture Notes in Computer Science,2007,4653:349-358.
[112]Prinzie A, Van den Poel D. Random Forests for Multiclass Classification: Random Multinomial Logit [J]. Expert Systems with Applications,2008,34(3): 1721-1732.
[113]The Sloan Digital Sky Survey http://www.sdss.org/
[114]Madgwick D, Hewett P, Mortlock D. Spectroscopic Detection of Type la Supernovae in the Sloan Digital Sky Survey [J]. The Astrophysical Journal Letters,2003,599:L33.
[115]Tu L, Luo A. New Supernova Candidates from the SDSS-DR7 Spectral Survey [J]. Research in Astronomy and Astrophysics,2009,9:635.
[116]http://simbad.u-strasbg.fr/simbad/
[117]Szkody P, Anderson S, Agleros M. Cataclysmic Variables from The Sloan Digital Sky Survey. Ⅰ. The First Results [J]. The Astronomical Journal,2002, 123:430.
[118]Szkody P, Fraser O, Silvestri N. Cataclysmic Variables from the Sloan Digital Sky Survey. Ⅱ. The Second Year [J]. The Astronomical Journal,2003,126: 1499.
[119]Szkody P, Henden A, Fraser O. Cataclysmic Variables from the Sloan Digital Sky Survey.Ⅲ. The Third Year [J]. The Astronomical Journal,2004,128:1882.
[120]Szkody P, Henden A, Fraser O. Cataclysmic Variables from Sloan Digital Sky Survey. Ⅳ The Fourth Year (2003)[J]. The Astronomical Journal,2005,129: 2386.
[121]Szkody P, Henden A, Agleros M. Cataclysmic Variables from Sloan Digital Sky Survey. Ⅴ. The Fifth Year (2004)[J]. The Astronomical Journal,2006,131: 973.
[122]Szkody P, Henden A, Mannikko L. Cataclysmic Variables from Sloan Digital Sky Survey. Ⅵ. The Sixth Year (2005)[J]. The Astronomical Journal,2007, 134:185.
[123]李宗云,刘武.20个激变变星或相关天体的分光证认[J].天文学报,1999,40(001)：1-15.
[124]姜斌,潘景昌,郭强,等.PCA和相融性度量在聚类算法中的应用[J].电子科技大学学报,2007,36(006)：1292-1295.
[125]覃冬梅,赵永恒.一种基于主分量分析的恒星光谱快速分类法[J].光谱学与光谱分析,2003,23(001)：182-186.