Abstract：A novel Support Vector Machine (SVM)-based unified segmentation model was proposed for segmenting a continuous ultrasound image set, because the traditional SVM-based segmenting method needed to extract sample points for each image to create a segmentation model. Firstly, the gray feature was extracted from the gray histogram of the image as the characteristic representing the continuity of the image in the image set. Secondly, part images were selected as the samples and the gray feature of each pixel was extracted. Finally, the gray feature of the pixel was combined with the feature of image sequence continuity in the image where each pixel was located. The SVM was used to train the segmentation model to segment the whole image set. The experimental results show that compared with the traditional SVM-based segmentation method, the new model can greatly reduce the workload of manually selecting the sample points when segmenting the image set with large quantity and continuous variation and guarantees the segmentation accuracy simultaneously.
刘俊, 李鹏飞. 基于支持向量机的连续超声图像集分割算法[J]. 计算机应用, 2017, 37(7): 2089-2094.
LIU Jun, LI Pengfei. Continuous ultrasound image set segmentation method based on support vector machine. Journal of Computer Applications, 2017, 37(7): 2089-2094.
[1] REYNA R A, HERNANDEZ N, ESTEVE D, et al. Segmenting images with support vector machines[C]//Proceedings of the 2000 International Conference on Image Processing. Piscataway, NJ:IEEE, 2000, 1:820-823. [2] YANG H Y, WANG X Y, WANG Q Y, et al. LS-SVM based image segmentation using color and texture information[J]. Journal of Visual Communication & Image Representation, 2012, 23(7):1095-1112. [3] MITERAN J, BOUILLANT S, BOURENNANE E. SVM approximation for real-time image segmentation by using an improved hyperrectangles-based method[J]. Real-Time Imaging, 2003, 9(3):179-188. [4] CHEN X, TIAN J. Segmentation of fingerprint images using linear classifier[J]. EURASIP Journal on Advances in Signal Processing, 2004, 2004(4):1-15. [5] 邓晓飞,徐蔚鸿.一种结合多特征的SVM图像分割方法[J].计算机工程与科学,2013,35(2):154-158.(DENG X F,XU W H.An SVM image segmentation method using multi-features[J]. Computer Engineering & Science, 2013, 35(2):154-158.) [6] 薛志东,隋卫平,李利军.一种SVM与区域增长相结合的图像分割方法[J].计算机应用,2007,27(2):463-465.(XUE Z D, SUI W P, LI L J. Interactive segmentation method with SVM and region growing[J]. Journal of Computer Applications, 2007, 27(2):463-465.) [7] MICHAILOVICH O V, TANNENBAUM A. Despeckling of medical ultrasound images[J]. IEEE Transactions on Ultrasonics Ferroelectrics & Frequency Control, 2006, 53(1):64-78. [8] 薛志东,王燕,李利军.SVM图像分割方法的研究[J].微计算机信息,2007,23(24):306-308.(XUE Z D, WANG Y, LI L J. The research on SVM segmentation method[J]. Microcomputer Information, 2007, 23(24):306-308.) [9] MITRA P, SHANKAR B U, PAL S K. Segmentation of multispectral remote sensing images using active support vector machines[J]. Pattern Recognition Letters, 2004, 25(9):1067-1074. [10] 曹健,李海生,蔡强,等.图像目标的特征提取技术研究[J].计算机仿真,2013,30(1):409-414.(CAO J, LI H S, CAI Q, et al. Research on feature extraction of image target[J]. Computer Simulation, 2013, 30(1):409-414.) [11] 郝衍,朱信忠,赵建民,等.基于图像颜色直方图及纹理特征提取的兴趣点凸包检索方法[J].微型电脑应用,2011,27(6):42-45.(HAO Y, ZHU X Z, ZHAO J M, et al. Home point retrieval method based on color histogram and texture feature extraction[J].Microcomputer Applications, 2011, 27(6):42-45.) [12] PATRICIO M A, MARAVALL D. Segmentation of text and graphics/images using the gray-level histogram Fourier transform[C]//Proceedings of the 2000 Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR). Berlin:Springer, 2000:757-766. [13] BAI X, WANG W. Saliency-SVM:an automatic approach for image segmentation[J]. Neurocomputing, 2014, 136(8):243-255. [14] HUTCHINSON M F, HOOG F R D. Smoothing noisy data with spline functions[J]. Numerische Mathematik, 1985, 47(1):99-106. [15] 芮杰,吴冰,秦志远,等.一种稳健的自适应图像平滑算法[J].中国图象图形学报,2005,10(1):54-58.(RUI J, WU B, QIN Z Y, et al. A robust adaptive image smoothing algorithm[J]. Journal of Image and Graphics, 2005, 10(1):54-58.) [16] 彭新俊,王翼飞.间隔v-支持向量机及其几何问题[J].模式识别与人工智能,2009,22(1):8-16.(PENG X J, WANG Y F. Total margin v-support vector machine and its geometric problem[J]. Pattern Recognition & Artificial Intelligence, 2009, 22(1):8-16.) [17] 奉国和.SVM分类核函数及参数选择比较[J].计算机工程与应用,2011,47(3):123-124.(FENG G H. Parameter optimizing for support vector machines classification[J]. Computer Engineering and Applications, 2011, 47(3):123-124.) [18] 卢照敢,许春梅,孙楠,等.采用改进高斯核的MLS-SVM人脸表情识别算法[J].计算机科学,2014,41(s1):132-134.(LU Z G, XU C M, SUN N, et al. Improved face emotion identification algorithm by MLS-SVM with modified Gauss kernel function[J]. Computer Science, 2014, 41(s1):132-134.) [19] MCFEETERS S K. The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features[J]. International Journal of Remote Sensing, 1996, 17(7):1425-1432. [20] LI J, WANG H, LI S. Microscopic image segmentation method based on SVM[J]. International Journal of Signal Processing, Image Processing and Pattern Recognition, 2016, 9(2):179-188. [21] TIAN X, HU T. A method of debris image segmentation based on SVM[C]//IMSCCS'06:Proceedings of the First International Multi-Symposiums on Computer and Computational Sciences. Piscataway, NJ:IEEE, 2006:307-311. [22] 王行甫,陈家伟.基于高斯核的SVM的参数选择[J].计算机系统应用,2014,23(7):242-245.(WANG X F, CHEN J W. Parameter selection of SVM with Gaussian kernel[J]. Computer Systems & Applications, 2014, 23(7):242-245.) [23] MIZUSHIMA A, LU R. An image segmentation method for apple sorting and grading using support vector machine and Otsu's method[J]. Computers & Electronics in Agriculture, 2013, 94:29-37.
2017, Vol. 37 
