乳腺肿瘤图像的融合纹理特征提取方法
|
摘要
为了准确地识别乳腺肿瘤图像特征,提出一种改进的灰度共生矩阵(GLCM)与Tamura相结合的纹理特征提取算法。首先对乳腺肿瘤图像进行预处理,滤除图像噪声部分并提高图像的对比度;通过对传统的灰度共生矩阵进行改进,减少大量的冗余信息,增强图像的识别率;最后将改进的灰度共生矩阵与Tamura相结合,提取图像纹理特征,并进行图像特征识别。实验结果表明,乳腺肿瘤图像特征识别率可达到96.67%,平均计算时间为14.6s,具有较高的识别准确率和计算效率。
In order to accurately identify breast tumor image features,an improved textural feature extraction algorithm based on improved gray level co-occurrence matrix(GLCM)and Tamura is proposed. First,the images are preprocessed by eliminating image noise and enhancing image contrast. Then,the traditional gray level co-occurrence matrix is improved,and redundant information is reduced,improving the recognition rate of the image and the running speed of the program. Finally,The symbiotic matrix is combined with Tamura to obtain the image texture features,and the extracted features are identified. The experimental results show that the recognition rate of fusion features can reach 96.67% with 14.6 s average calculation rate,which has high recognition accuracy and omputational efficiency.
In order to accurately identify breast tumor image features,an improved textural feature extraction algorithm based on improved gray level co-occurrence matrix(GLCM)and Tamura is proposed. First,the images are preprocessed by eliminating image noise and enhancing image contrast. Then,the traditional gray level co-occurrence matrix is improved,and redundant information is reduced,improving the recognition rate of the image and the running speed of the program. Finally,The symbiotic matrix is combined with Tamura to obtain the image texture features,and the extracted features are identified. The experimental results show that the recognition rate of fusion features can reach 96.67% with 14.6 s average calculation rate,which has high recognition accuracy and omputational efficiency.
引文
[1]战扬.融合纹理特征和形状特征的医学图像分类方法[J].信息技术,2013(6):44-46.ZHAN Yang. Medical Image Classification Based on Texture Features and Shape Features[J]. Information Technology,2013(6):44-46.
[2]张峰,罗立民,鲍旭东.常用影像方法在乳腺癌辅助诊断中的性能对比[J].中国生物医学工程学报,2012,31(2):276-284.ZHANG Feng,LUO Limin,BAO Xudong. Comparative study of common imaging methods in the diagnosis of breast cancer[J]. Chinese Journal of Biomedical Engineering,2012,31(2):276-284.
[3]Zulpe N S,Pawar V P.GLCM textural features for Brain Tumor Classification[J]. International Journal of Computer Science Issues,2012,9(3).
[4]Liao S Y,Huang T Q.Video copy-move forgery detection and localization based on Tamura texture features[C]//International Congress on Image and Signal Processing.IEEE,2014:864-868.
[5]Sharif M,Khalid A,Raza M,et al. Face Recognition using Gabor Filters[J]. Journal of Applied Computer Science&Mathematics,2011,5(11):510-515.
[6]马箐,谢娟英.基于粒计算的K-medoids聚类算法[J].计算机应用,2012,32(7):1973-1977.MA Jing,XIE Juanying. K-medoids clustering algorithm based on kernel computing[J]. Journal of Computer Applications,2012,32(7):1973-1977.
[7]Song M,Civco D. Road Extraction Using SVM and Image Segmentation[J]. Photogrammetric Engineering&Remote Sensing,2015,70(12):1365-1371.
[8]Zheng Y,Byeungwoo J,Xu D,et al. Image segmentation by generalized hierarchical fuzzy C-means algorithm[J].Journal of Intelligent&Fuzzy Systems,2015,28(2):4024-4028.
[9]焦蓬蓬,郭依正,刘丽娟,等.灰度共生矩阵纹理特征提取的Matlab实现[J].计算机技术与发展,2012(11):169-171.JIAO Pengpeng,GUO Yizheng,LIU Lijuan,et al. A Matlab implementation of texture feature extraction of grayscale co-occurrence matrix[J]. Computer Technology&Development,2012(11):169-171.
[10]黄媛媛,张尤赛.双树复小波域共生矩阵的纹理特征提取方法[J].计算机应用与软件,2012,29(7):216-219.HUANG Yuanyuan,ZHANG Yousai.A method for texture feature extraction of co-occurrence matrix in double-tree complex wavelet domain[J]. Computer Applications and Software,2012,29(7):216-219.
[11]吕晓琪,郭金鸽,赵宇红,等.基于图像分割的Tamura纹理特征算法的研究与实现[J].中国组织工程研究,2012,16(17):3160-3163.LV Xiaoqi,GUO Jinge,ZHAO Yuhong,et al. Study and implementation of Tamura texture feature algorithm based on image segmentation[J]. Chinese Journal of Tissue Engineering Research,2012,16(17):3160-3163.
[12]黄飞,周军,卢晓东.基于马氏距离的一维距离像识别算法仿真[J].计算机仿真,2010,27(3):31-34.HUANG Fei,ZHOU Jun,LU Xiaodong.A Simulation Algorithm of One-Dimensional Range Image Recognition Based on Mahalanobis Distance[J]. Computer Simulation,2010,27(3):31-34.
[13]周先春,汪美玲,石兰芳.阈值寻优的高保真各向异性滤波模型[J].计算机辅助设计与图形学学报,2016,28(9):1550-1559.ZHOU Xianchun,WANG Meiling,SHI Lanfang. High Fidelity Anisotropic Filtering Model for Threshold Optimization[J]. Journal of Computer-Aided Design and Graphics,2016,28(9):1550-1559.
[14] Kurt B,Nabiyev V V,Turhan K. Medical images enhancement by using anisotropic filter and CLAHE[C]//International Symposium on Innovations in Intelligent Systems and Applications. IEEE,2012:1-4.
[15]Cheng X,Zeng M,Liu X. Feature-preserving filtering with L 0,gradient minimization[J]. Computers&Graphics,2014,38(1):150-157.
[16]张伟伟.图像纹理特征提取及分类方法研究[D].天津:天津大学,2012.ZHANG Weiwei. Image texture feature extraction and classification methods[D]. Tianjin:Tianjin University,2012.
[17]杨国城,卢凤梅,李美玲.基于灰度共生矩阵的肝脏纹理特征提取[J].医药前沿,2012,02(17):105-106.YANG Guocheng,LU Fengmei,LI Meiling. Liver Texture Feature Extraction Based on Grayscale Co-occurrence Matrix[J]. Medicine Frontier,2012,02(17):105-106.
[18]景军锋,邓淇英,李鹏飞,等. LBP和GLCM融合的织物组织结构分类[J].电子测量与仪器学报,2015,29(9):1406-1413.JING Junfeng,DENG Qiying,LI Pengfei,et al. Classification of fabric structure by LBP and GLCM[J]. Journal of Electronics&Measurements,2015,29(9):1406-1413.
[19]高源,宋辉,张志佳.基于Tamura特征的虹膜结构密度计算方法[J].计算机技术与发展,2016,26(3):36-39.GAO Yuan,SONG Hui,ZHANG Zhijia. A Method to Calculate the Density of Iris Structures Based on Tamura Feature[J]. Computer Technology&Development,2016,26(3):36-39.
[20]姜芳芳,何明一,王欣欣.基于自编码特征提取及弹性学习的手写数字识别[J].现代电子技术,2014(10):31-34.JIANG Fangfang,HE Mingyi,WANG Xinxin. Handwritten Digital Recognition Based on Self-coding Feature Extraction and Elasticity Learning[J]. Modern Electronics,2014(10):31-34.
[2]张峰,罗立民,鲍旭东.常用影像方法在乳腺癌辅助诊断中的性能对比[J].中国生物医学工程学报,2012,31(2):276-284.ZHANG Feng,LUO Limin,BAO Xudong. Comparative study of common imaging methods in the diagnosis of breast cancer[J]. Chinese Journal of Biomedical Engineering,2012,31(2):276-284.
[3]Zulpe N S,Pawar V P.GLCM textural features for Brain Tumor Classification[J]. International Journal of Computer Science Issues,2012,9(3).
[4]Liao S Y,Huang T Q.Video copy-move forgery detection and localization based on Tamura texture features[C]//International Congress on Image and Signal Processing.IEEE,2014:864-868.
[5]Sharif M,Khalid A,Raza M,et al. Face Recognition using Gabor Filters[J]. Journal of Applied Computer Science&Mathematics,2011,5(11):510-515.
[6]马箐,谢娟英.基于粒计算的K-medoids聚类算法[J].计算机应用,2012,32(7):1973-1977.MA Jing,XIE Juanying. K-medoids clustering algorithm based on kernel computing[J]. Journal of Computer Applications,2012,32(7):1973-1977.
[7]Song M,Civco D. Road Extraction Using SVM and Image Segmentation[J]. Photogrammetric Engineering&Remote Sensing,2015,70(12):1365-1371.
[8]Zheng Y,Byeungwoo J,Xu D,et al. Image segmentation by generalized hierarchical fuzzy C-means algorithm[J].Journal of Intelligent&Fuzzy Systems,2015,28(2):4024-4028.
[9]焦蓬蓬,郭依正,刘丽娟,等.灰度共生矩阵纹理特征提取的Matlab实现[J].计算机技术与发展,2012(11):169-171.JIAO Pengpeng,GUO Yizheng,LIU Lijuan,et al. A Matlab implementation of texture feature extraction of grayscale co-occurrence matrix[J]. Computer Technology&Development,2012(11):169-171.
[10]黄媛媛,张尤赛.双树复小波域共生矩阵的纹理特征提取方法[J].计算机应用与软件,2012,29(7):216-219.HUANG Yuanyuan,ZHANG Yousai.A method for texture feature extraction of co-occurrence matrix in double-tree complex wavelet domain[J]. Computer Applications and Software,2012,29(7):216-219.
[11]吕晓琪,郭金鸽,赵宇红,等.基于图像分割的Tamura纹理特征算法的研究与实现[J].中国组织工程研究,2012,16(17):3160-3163.LV Xiaoqi,GUO Jinge,ZHAO Yuhong,et al. Study and implementation of Tamura texture feature algorithm based on image segmentation[J]. Chinese Journal of Tissue Engineering Research,2012,16(17):3160-3163.
[12]黄飞,周军,卢晓东.基于马氏距离的一维距离像识别算法仿真[J].计算机仿真,2010,27(3):31-34.HUANG Fei,ZHOU Jun,LU Xiaodong.A Simulation Algorithm of One-Dimensional Range Image Recognition Based on Mahalanobis Distance[J]. Computer Simulation,2010,27(3):31-34.
[13]周先春,汪美玲,石兰芳.阈值寻优的高保真各向异性滤波模型[J].计算机辅助设计与图形学学报,2016,28(9):1550-1559.ZHOU Xianchun,WANG Meiling,SHI Lanfang. High Fidelity Anisotropic Filtering Model for Threshold Optimization[J]. Journal of Computer-Aided Design and Graphics,2016,28(9):1550-1559.
[14] Kurt B,Nabiyev V V,Turhan K. Medical images enhancement by using anisotropic filter and CLAHE[C]//International Symposium on Innovations in Intelligent Systems and Applications. IEEE,2012:1-4.
[15]Cheng X,Zeng M,Liu X. Feature-preserving filtering with L 0,gradient minimization[J]. Computers&Graphics,2014,38(1):150-157.
[16]张伟伟.图像纹理特征提取及分类方法研究[D].天津:天津大学,2012.ZHANG Weiwei. Image texture feature extraction and classification methods[D]. Tianjin:Tianjin University,2012.
[17]杨国城,卢凤梅,李美玲.基于灰度共生矩阵的肝脏纹理特征提取[J].医药前沿,2012,02(17):105-106.YANG Guocheng,LU Fengmei,LI Meiling. Liver Texture Feature Extraction Based on Grayscale Co-occurrence Matrix[J]. Medicine Frontier,2012,02(17):105-106.
[18]景军锋,邓淇英,李鹏飞,等. LBP和GLCM融合的织物组织结构分类[J].电子测量与仪器学报,2015,29(9):1406-1413.JING Junfeng,DENG Qiying,LI Pengfei,et al. Classification of fabric structure by LBP and GLCM[J]. Journal of Electronics&Measurements,2015,29(9):1406-1413.
[19]高源,宋辉,张志佳.基于Tamura特征的虹膜结构密度计算方法[J].计算机技术与发展,2016,26(3):36-39.GAO Yuan,SONG Hui,ZHANG Zhijia. A Method to Calculate the Density of Iris Structures Based on Tamura Feature[J]. Computer Technology&Development,2016,26(3):36-39.
[20]姜芳芳,何明一,王欣欣.基于自编码特征提取及弹性学习的手写数字识别[J].现代电子技术,2014(10):31-34.JIANG Fangfang,HE Mingyi,WANG Xinxin. Handwritten Digital Recognition Based on Self-coding Feature Extraction and Elasticity Learning[J]. Modern Electronics,2014(10):31-34.