基于角点检测的图像局部特征识别
|
摘要
运用传统方法对超分辨图像的局部特征进行识别时,存在识别准确率较低和识别时间较长的问题,为此给出一种基于角点检测的图像局部特征识别方法。运用细节特征定位方法对图像的局部信息进行采样,采用灰度直方图重构方法对图像进行三维重建,将重建结果与边缘轮廓特点融合方法相结合,对图像的局部边缘信息特征进行提取。根据Harris角点检测方法提取图像的局部信息特征量,并依据卷积神经网络对提取结果进行分类,最终实现对超分辨图像局部特征的识别。分析实验结果可知,与传统方法相比,此方法的识别准确率较高,并且识别时间远低于传统方法。
Traditional methods of recognizing local features of super-resolution images have such problems as low recognition accuracy and more recognition time. Therefore, a method of image local feature recognition based on corner detection is proposed. The local information of the image is sampled by the method of locating minutiae features, and the image is reconstructed by the method of gray histogram reconstruction. The local edge information features of the image are extracted by combining the reconstructed results with the fusion method of edge contour features. According to Harris corner detection method, the local information feature of the image is extracted, and the extracted results are classified according to convolution neural network. Finally, the local feature of super-resolution image is recognized. The experimental results show that, compared with the traditional method, the recognition accuracy of this method is higher and the recognition time is much less than that of the traditional method.
Traditional methods of recognizing local features of super-resolution images have such problems as low recognition accuracy and more recognition time. Therefore, a method of image local feature recognition based on corner detection is proposed. The local information of the image is sampled by the method of locating minutiae features, and the image is reconstructed by the method of gray histogram reconstruction. The local edge information features of the image are extracted by combining the reconstructed results with the fusion method of edge contour features. According to Harris corner detection method, the local information feature of the image is extracted, and the extracted results are classified according to convolution neural network. Finally, the local feature of super-resolution image is recognized. The experimental results show that, compared with the traditional method, the recognition accuracy of this method is higher and the recognition time is much less than that of the traditional method.
引文
[1] 苏泽斌,黄梦莹,景军锋.基于参数核图割的纱线毛羽图像处理方法[J].西安工程大学学报,2017,31(4):486-494. SU Z B,HUANG M Y,JING J F.Image processing of yarn hairiness based on parametric kernel graph cut method[J].Journal of Xi′an Polytechnic University,2017,31(4):486-494.(in Chinese)
[2] 孙毅堂,宋慧慧,张开华,等.基于极深卷积神经网络的人脸超分辨率重建算法[J].计算机应用,2018,38(4):1141-1145. SUN Y T,SONG H H,ZHANG K H,et al.Face super-resolution via very deep convolutional neural network[J].Journal of Computer Applications,2018,38(4):1141-1145.(in Chinese)
[3] 王松山,傅新镇,李强.PACS系统中的图像可识别特征分割方法研究与分析[J].微型电脑应用,2017,33(4):35-38. WANG S S,FU X Z,LI Q.Research and analysis of image recognition feature segmentation method in PACS system[J].Microcomputer Applications,2017,33(4):35-38.(in Chinese)
[4] 汪立,蒋念平.基于改进Harris角点检测的视网膜图像配准[J].电子科技,2017,30(2):119-122. WANG L,JIANG N P.Retinal image registration based on improved Harris corner detection[J].Electronic Science and Technology,2017,30(2):119-122.(in Chinese)
[5] 牛耕.基于激光扫描的残缺指纹图像特征提取技术研究[J].激光杂志,2017,38(11):109-112. NIU G.Research on feature extraction of incomplete fingerprint image based on laser scanning[J].Laser Journal,2017,38(11):109-112.(in Chinese)
[6] 曹艳玲,袁义宏.岭南古建筑图像特征优化提取仿真研究[J].计算机仿真,2017,34(9):354-357. CAO Y L,YUAN Y H.Simulation research on image feature extraction of South of the Five Ridges ancient architecture[J].Computer Simulation,2017,34(9):354-357.(in Chinese)
[7] 王薇,王展青.多尺度特征点聚类的图像配准算法[J].小型微型计算机系统,2017,38(11):2597-2603. WANG W,WANG Z Q.Image registration of multi-scale feature points clustering[J].Journal of Chinese Computer Systems,2017,38(11):2597-2603.(in Chinese)
[8] 侯小红,郭敏.一种基于Harris-SIFT特征点检测的LBP人脸表情识别算法[J].西北大学学报(自然科学版),2017,47(2):209-214. HOU X H,GUO M.LBP algorithm for facial expression recognition based on Harris-SIFT feature point detection[J].Journal of Northwest University(Natural Science Edition),2017,47(2):209-214.(in Chinese)
[9] 金亦挺,王万良,赵燕伟,等.基于角度累加的鲁棒角点检测算法[J].计算机辅助设计与图形学学报,2017,29(11):2005-2014. JIN Y T,WANG W L,ZHAO Y W,et al.Robust corner detection algorithm based on angle accumulation[J].Journal of Computer-Aided Design & Computer Graphics,2017,29(11):2005-2014.(in Chinese)
[10] 于立洋,韩琦,牛夏牧.基于MROGH特征描述子的图像局部拷贝-旋转-移动行为取证[J].智能计算机与应用,2017,7(4):124-127. YU L Y,HAN Q,NIU X M.Copy-rotation-move forgery detection using the MROGH descriptor[J].Intelligent Computer and Applications,2017,7(4):124-127.(in Chinese)
[11] 欧阳帅,安博文,周凡,等.海事监管中无人机航拍图像快速拼接算法[J].传感器与微系统,2017,36(9):113-116. OUYANG S,AN B W,ZHOU F,et al.UAV aerial image fast mosaic algorithm in maritime supervision[J].Transducer and Microsystem Technologies,2017,36(9):113-116.(in Chinese)
[12] 王庆,唐涛,项德良,等.基于梯度比率的SAR图像局部特征提取方法研究[J].智能系统学报,2017,12(3):286-292. WANG Q,TANG T,XIANG D L,et al.Research on local feature extraction of SAR images based on gradient ratio[J].CAAI Transactions on Intelligent Systems,2017,12(3):286-292.(in Chinese)
[13] 吴喆,曾接贤,高琪琪.显著图和多特征结合的遥感图像飞机目标识别[J].中国图象图形学报,2017,22(4):532-541. WU Z,ZENG J X,GAO Q Q.Aircraft target recognition in remote sensing images based on saliency images and multi-feature combination[J].Journal of Image and Graphics,2017,22(4):532-541.(in Chinese)
[14] 张泊平.可变光照下彩色多维人脸图像自动识别方法研究[J].微电子学与计算机,2017,34(5):128-131. ZHANG B P.Research on automatic recognition of color multi-dimensional face images under variable illumination[J].Microelectronics & Computer,2017,34(5):128-131.(in Chinese)
[15] 李隽,王伟.遗传算法优化神经网络在图像目标识别中的应用研究[J].现代电子技术,2017,40(20):111-113. LI J,WANG W.Application of genetic algorithm optimizing neural network in image target recognition[J].Modern Electronics Technique,2017,40(20):111-113.(in Chinese)
[16] 杨念聪,任琼,张成喆,等.基于卷积神经网络的图像特征识别研究[J].信息与电脑(理论版),2017(14):62-64. YANG N C,REN Q,ZHANG C Z,et al.Research on image feature recognition based on convolution neural network[J].China Computer & Communication,2017(14):62-64.(in Chinese)
[17] 樊颖军.傅里叶变换下的直方图均衡化图像特征识别算法的研究[J].计算机与数字工程,2017,45(9):1848-1852. FAN Y J.Research on image feature recognition algorithm based on Fourier transform coupling histogram equalization[J].Computer and Digital Engineering,2017,45(9):1848-1852.(in Chinese)
[18] 肖志云,刘洪.小波域马铃薯典型虫害图像特征选择与识别[J].农业机械学报,2017,48(9):24-31. XIAO Z Y,LIU H.Features selection and recognition of potato typical insect pest images in wavelet domain[J].Transactions of the Chinese Society for Agricultural Machinery,2017,48(9):24-31.(in Chinese)
[19] 孙继平,杨坤.一种燥岩图像特征提取与识别方法[J].工矿自动化,2017,43(5):1-5. SUN J P,YANG K.A coal-rock image feature extraction and recognition method[J].Industry and Mine Automation,2017,43(5):1-5.(in Chinese)
[20] 刘欢,肖根福,罗文浪,等.Contourlet变换和分形维的图像特征提取与识别[J].小型微型计算机系统,2017,38(10):2401-2405. LIU H,XIAO G F,LUO W L,et al.Image feature extraction and recognition with Contourlet transform and fractal dimension[J].Journal of Chinese Computer Systems,2017,38(10):2401-2405.(in Chinese)
[2] 孙毅堂,宋慧慧,张开华,等.基于极深卷积神经网络的人脸超分辨率重建算法[J].计算机应用,2018,38(4):1141-1145. SUN Y T,SONG H H,ZHANG K H,et al.Face super-resolution via very deep convolutional neural network[J].Journal of Computer Applications,2018,38(4):1141-1145.(in Chinese)
[3] 王松山,傅新镇,李强.PACS系统中的图像可识别特征分割方法研究与分析[J].微型电脑应用,2017,33(4):35-38. WANG S S,FU X Z,LI Q.Research and analysis of image recognition feature segmentation method in PACS system[J].Microcomputer Applications,2017,33(4):35-38.(in Chinese)
[4] 汪立,蒋念平.基于改进Harris角点检测的视网膜图像配准[J].电子科技,2017,30(2):119-122. WANG L,JIANG N P.Retinal image registration based on improved Harris corner detection[J].Electronic Science and Technology,2017,30(2):119-122.(in Chinese)
[5] 牛耕.基于激光扫描的残缺指纹图像特征提取技术研究[J].激光杂志,2017,38(11):109-112. NIU G.Research on feature extraction of incomplete fingerprint image based on laser scanning[J].Laser Journal,2017,38(11):109-112.(in Chinese)
[6] 曹艳玲,袁义宏.岭南古建筑图像特征优化提取仿真研究[J].计算机仿真,2017,34(9):354-357. CAO Y L,YUAN Y H.Simulation research on image feature extraction of South of the Five Ridges ancient architecture[J].Computer Simulation,2017,34(9):354-357.(in Chinese)
[7] 王薇,王展青.多尺度特征点聚类的图像配准算法[J].小型微型计算机系统,2017,38(11):2597-2603. WANG W,WANG Z Q.Image registration of multi-scale feature points clustering[J].Journal of Chinese Computer Systems,2017,38(11):2597-2603.(in Chinese)
[8] 侯小红,郭敏.一种基于Harris-SIFT特征点检测的LBP人脸表情识别算法[J].西北大学学报(自然科学版),2017,47(2):209-214. HOU X H,GUO M.LBP algorithm for facial expression recognition based on Harris-SIFT feature point detection[J].Journal of Northwest University(Natural Science Edition),2017,47(2):209-214.(in Chinese)
[9] 金亦挺,王万良,赵燕伟,等.基于角度累加的鲁棒角点检测算法[J].计算机辅助设计与图形学学报,2017,29(11):2005-2014. JIN Y T,WANG W L,ZHAO Y W,et al.Robust corner detection algorithm based on angle accumulation[J].Journal of Computer-Aided Design & Computer Graphics,2017,29(11):2005-2014.(in Chinese)
[10] 于立洋,韩琦,牛夏牧.基于MROGH特征描述子的图像局部拷贝-旋转-移动行为取证[J].智能计算机与应用,2017,7(4):124-127. YU L Y,HAN Q,NIU X M.Copy-rotation-move forgery detection using the MROGH descriptor[J].Intelligent Computer and Applications,2017,7(4):124-127.(in Chinese)
[11] 欧阳帅,安博文,周凡,等.海事监管中无人机航拍图像快速拼接算法[J].传感器与微系统,2017,36(9):113-116. OUYANG S,AN B W,ZHOU F,et al.UAV aerial image fast mosaic algorithm in maritime supervision[J].Transducer and Microsystem Technologies,2017,36(9):113-116.(in Chinese)
[12] 王庆,唐涛,项德良,等.基于梯度比率的SAR图像局部特征提取方法研究[J].智能系统学报,2017,12(3):286-292. WANG Q,TANG T,XIANG D L,et al.Research on local feature extraction of SAR images based on gradient ratio[J].CAAI Transactions on Intelligent Systems,2017,12(3):286-292.(in Chinese)
[13] 吴喆,曾接贤,高琪琪.显著图和多特征结合的遥感图像飞机目标识别[J].中国图象图形学报,2017,22(4):532-541. WU Z,ZENG J X,GAO Q Q.Aircraft target recognition in remote sensing images based on saliency images and multi-feature combination[J].Journal of Image and Graphics,2017,22(4):532-541.(in Chinese)
[14] 张泊平.可变光照下彩色多维人脸图像自动识别方法研究[J].微电子学与计算机,2017,34(5):128-131. ZHANG B P.Research on automatic recognition of color multi-dimensional face images under variable illumination[J].Microelectronics & Computer,2017,34(5):128-131.(in Chinese)
[15] 李隽,王伟.遗传算法优化神经网络在图像目标识别中的应用研究[J].现代电子技术,2017,40(20):111-113. LI J,WANG W.Application of genetic algorithm optimizing neural network in image target recognition[J].Modern Electronics Technique,2017,40(20):111-113.(in Chinese)
[16] 杨念聪,任琼,张成喆,等.基于卷积神经网络的图像特征识别研究[J].信息与电脑(理论版),2017(14):62-64. YANG N C,REN Q,ZHANG C Z,et al.Research on image feature recognition based on convolution neural network[J].China Computer & Communication,2017(14):62-64.(in Chinese)
[17] 樊颖军.傅里叶变换下的直方图均衡化图像特征识别算法的研究[J].计算机与数字工程,2017,45(9):1848-1852. FAN Y J.Research on image feature recognition algorithm based on Fourier transform coupling histogram equalization[J].Computer and Digital Engineering,2017,45(9):1848-1852.(in Chinese)
[18] 肖志云,刘洪.小波域马铃薯典型虫害图像特征选择与识别[J].农业机械学报,2017,48(9):24-31. XIAO Z Y,LIU H.Features selection and recognition of potato typical insect pest images in wavelet domain[J].Transactions of the Chinese Society for Agricultural Machinery,2017,48(9):24-31.(in Chinese)
[19] 孙继平,杨坤.一种燥岩图像特征提取与识别方法[J].工矿自动化,2017,43(5):1-5. SUN J P,YANG K.A coal-rock image feature extraction and recognition method[J].Industry and Mine Automation,2017,43(5):1-5.(in Chinese)
[20] 刘欢,肖根福,罗文浪,等.Contourlet变换和分形维的图像特征提取与识别[J].小型微型计算机系统,2017,38(10):2401-2405. LIU H,XIAO G F,LUO W L,et al.Image feature extraction and recognition with Contourlet transform and fractal dimension[J].Journal of Chinese Computer Systems,2017,38(10):2401-2405.(in Chinese)