摘要
本文的研究目的是应用计算机对田间青椒进行自动识别,为将来实现田间青椒自动采摘机器人打下基础。本文的主要研究内容如下:
1.提出了颜色因子与直方图阈值相结合对田间青椒与叶子(枝干)进行分割的方法。根据田间拍摄的青椒图像中的青椒、叶子(枝干)等颜色特征,进行了仔细地统计和分析,提出了颜色因子与直方图阈值相结合对田间青椒与叶子(枝干)进行分割的方法。
2.为了准确提取青椒图像的形状特征,本文提出了对图像进行去噪、二值形态学、边缘检测等一系列的前期处理过程。由于图像在输入和处理过程中会产生干扰,形成噪声,降低图像质量,本文采用中值滤波对图像进行了去噪处理;对图像实行开启和闭合运算进行误判区域处理;通过Canny算子对图像进行了边缘检测处理,对目标图像的轮廓进行特征提取。
3.计算并提取了青椒的五个形状特征,作为BP神经网络的输入。如果直接把预处理后的青椒图像作为神经网络的输入,会导致数据量大,识别速率比较慢,因此,本文提取了青椒的形状系数、伸长度、紧密度、长宽比、主轴周长比等五个归一化形状特征,作为神经网络的输入。
4.构造BP神经网络图像识别系统。本文在实验的基础上确定了改进的BP神经网络模型及其对应参数,包括神经网络层数、各层结点数、激活函数、学习速率、动量因子等,并通过稳定的BP神经网络实现样本的识别测试,最终对识别结果进行统计、分析。
5.本文利用最小二乘法进行圆的拟合以提取青椒的质心,从而实现青椒的准确定位。
The purpose of this research is to apply computer to automatically identify green peppers in the fields, and for realization of research about the fields picking green peppers robot in the future to lay the foundation. The main research content of this article as follows:
1. Proposed segmentation method for the field peppers and leaves (branches) to using of the combination of color factors and histogram threshold.Through carefully statistics and analysis to color features of green peppers, leaves (branches) and so on among the peppers images taken in the field, proposed segmentation method about the combination color factor and histogram threshold of the peppers and leaves (branches) in the field.
2. In order to accurately extract the shape characteristics of peppers image, in the paper, image pre-processing, such as image de-noising, binary morphology, edge detection and so on, are proposed. In the paper, use of median filtering to remove the image noise, because they will interfere to form a noise, reduce the image quality, when the image input or processing; The use of open and closed operations to process misjudge the regional in the image; Use Canny operator to process the image edge detection and to extraction feature of the target image contours.
3. As a BP neural networks input, calculated and extracted green pepper characteristics of the five shapes, If the pretreatment peppers image directly as a neural network input then that will increase the amount of data, and slow identification rate. Therefore, extracted five normalized shape feature of pepper as a neural network input, including the form factor, stretch length, close degrees, aspect ratio, spindle circumference ratio.
4. Construction BP neural network image recognition system. Through experiments, this paper identified the improved BP neural network model and the corresponding parameters. Including neural network layers, layers of nodes, activation function, learning rate, momentum factor and so on, and use a stable BP neural network to realize sample identification test. Finally, statistic and analysis recognition results.
5. In this paper, using Least-squares method to fit the circle for extract the pepper centroid, and accurately locate pepper.
引文
安雪梅.2007.Photoshop图像处理与创意设计案例教程[M].清华大学出版社.
暴风雪科技.2004. Photoshop图像处理基础与实例培训教程[M].上海科学普及出版社.
陈兵旗,孙明.2007.实用数字图像处理与分析[M].中国农业大学出版社.清华大学出版社.
陈强.2007.基于组合矩和神经网络的图像识别技术研究[J].南京理工大学硕士学位论文.
蔡健荣,李玉良,范军等.2007.成熟柑橘的图像识别及空间定位研究[J].微计算机信息.23(12~1)
董长虹.2005.Matlab神经网络与应用[M].国防工业出版社.1:65~67
董长虹,赖志国,余啸海.2004.Matlab图像处理与应用[M].国防工业出版社.1:150~156
范立南,韩晓微,张广渊.2007.图像处理与模式识别[M].科学出版社.
郭小刚,金星.2003.C/C++程序设计教程[M].人民邮电出版社.
陆宗骐.2005.C/C++图像处理编程[M].清华大学出版.
李弼程,彭天强,彭波.2004.智能图像处理技术[M].电子工业出版社.3:220~242
李印清,郑小东,王晓洁.2008.基于区域特征的果实识别技术[J].河南科学.3(26)
钮毅.2007.部分遮挡条件下椭圆目标识别[J].上海交通大学硕士学位论文.
孙即祥.2004.图像分析[M].科学出版社.7:96~99
孙即祥.2004.图像处理[M].科学出版社.
孙兵旗,孙明.2004.Visual C++实用图像处理[M].清华大学出版社.
孙印杰,沈宾,王艺菲.2004.图像处理Photoshop CS[M].电子工业出版社.
王家文,曹宇.2003.Matlab6.5图形图像处理[M].国防工业出版社.
吴晏,丁明跃,彭嘉雄.1996.基于图像直方图的一维不变矩研究[J].华中理工大学学报.24(2):66~68
王勇,沈明霞,姬长英.2007.基于BP神经网络的成熟棉桃识别研究[J].浙江农业科学.
徐惠荣.2004.基于机器视觉的树上柑桔识别方法研究[J].浙江大学硕士学位论文.
阮沈勇,王永利,桑群芳.2003.Matlab程序设计[M].电子工业出版社.
余成波.2003.数字图像处理及Matlab实现[M].重庆大学出版社.
杨淑莹.2008.模式识别与智能计算——Matlab技术实现[M].电子工业出版社.
章毓晋.2005.图像工程[M].清华大学出版社.
郑文.2008.曲线拟合[J].西南大学硕士学位论文.28
周云山,力强,李红英等.1995.计算机视觉在蘑菇采摘机器上的应用[J].农业工程学报.11(4):27~32
Baiqing Sun.2006.Research on Rejection Capabilities of Paper Currency Recognition System with the Neural Network Employing Gaussian Function.Department of EngineeringGraduate School of EngineeringKochi University of Technology Kochi,Japan.11~14
Bajwa S.G,Tian L.F.2001.Acrial CIR remote sensing for weed density mapping in a soybean field.Trans of the ASAE.44(6):1965~1974
Chandramouli,K.Izquierdo, E..2006. Image Classification using Chaotic Particle Swarm Optimization . In Proceedings of Image Processing.IEEE.
D.M.Bulanon.T.Katanka.Y.Ota,T.Hiroma.2002.Automatic recognition of Fujiap Plesat harvest.BiosystemsEngineering.83(4):405~412
Dr.R.Tsheko.2002.Discrimination of plant species using co occurrence matrix of leaves[J].The DIGR journal of scientific research and development.136(4):11~14
Fito P.J.,Ortola M.D.,De los Reyes R.et al.2004.Control of citrus surface drying by image analysis of infrared thermography.Journal of Food Engineering.61:287~290
Joyce Van de Vegte,侯正信,王安国.2004.数字信号处理基础.电子工业出版社.
Jo-ao Camargo Neto,George.E.Meyer,David.D.Jones,et al.2006.Plant species identification using Elliptic Fourier leaf shape analysis[J].Computers and electronics in agriculture.50(2):121~34
Kim Y.Ling P.P.2001.Machine vision guided sensor positioning system for leaf temperature assessment.Trans of the ASAE.44(6):1941~1947
Li bicheng,Peng Tianqiang,Su Huan.2002.Lossless Compression of Images Based on DPCM and S+P Transform.Proc.Of SPIE.4875:340~346
P.K.Goel,S.O.Prasher,R.M.Patel,et al.2002.Use of airborne multi-spectral imagery for weed detection in field crops[J].Transactions of the ASAE.45(2):443~449
Simon Haykin,叶世伟,史忠植.2004.神经网络原理.机械工业出版社.
Stajnko D.,Lakota M.,Hocevar M.2004.Estimation of number and diameter of apple fruits in an orchard during the growing season by thermal imaging.Computers and electronics in agriculture.42:31~42
Victor.Alchanatis,Leonid.Ridel,Amots.Hetzroni,et al.2005.Weed detection in multi-spectral images of cotton fields[J].Computers and electronics in agriculture.47(3):243~260
Wang Lei,Shen Ting-zhi.2002.Two-Dimensional Entropy Method Based on Genetic Algorithm. Journal of Beijing Institute of Technology.11(2)
YKarimi,S.O.Prasher,R.M.Patel,et al.2006.Application of support vector machine technology for weed and nitrogen stress detection in corn[J].Computers and electronics in agriculture.51(2):99~109