RESEARCH ON IMAGE SEGMENTATION BASED ON SUPPORT VECTOR MACHINE

被引:0
作者
Tan, Chong [1 ]
Sun, Ying [1 ,2 ]
Li, Gong-Fa [1 ,3 ]
Jiang, Guo-Zhang [2 ,4 ]
Kong, Jian-Yi [1 ,2 ,3 ]
Tao, Bo [1 ,2 ]
机构
[1] Wuhan Univ Sci & Technol, Minist Educ, Key Lab Met Equipment & Control Technol, Wuhan 430081, Peoples R China
[2] Wuhan Univ Sci & Technol, Hubei Key Lab Mech Transmiss & Mfg Engn, Wuhan 430081, Peoples R China
[3] Wuhan Univ Sci & Technol, Res Ctr Biol Manipulator & Intelligent Measuremen, Wuhan 43008, Peoples R China
[4] Wuhan Univ Sci & Technol, 3D Printing & Intelligent Mfg Engn Inst, Wuhan 430081, Peoples R China
来源
PROCEEDINGS OF 2018 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS (ICMLC), VOL 2 | 2018年
基金
中国国家自然科学基金;
关键词
Support vector machines; Image segmentation; Kernel functions; Statistical learning; Target classification; SVM;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Image segmentation technology is one of the important topics in the field of digital image processing. However, the existing image segmentation technology does not have a uniform standard, and the traditional image segmentation technology is only suitable for some fixed situations. Therefore, the image segmentation technology on new theories and new methods deserves further research and development. The SVM algorithm for image segmentation, a variety of image features can be used to get a better segmentation results. So, this paper based on the theory of support vector machines, introduces the basic idea of SVM in detail, and the current state of image segmentation and the development trend of image segmentation are described in detail. Finally, the necessity of introducing statistical learning into image segmentation and the possibility of introducing SVM into image segmentation are studied and analyzed in depth. The results show that support vector machine can well segment the image target.
引用
收藏
页码:650 / 655
页数:6
相关论文
共 20 条
[1]   Principal pixel analysis and SVM for automatic image segmentation [J].
Bai, Xuefei ;
Wang, Wenjian .
NEURAL COMPUTING & APPLICATIONS, 2016, 27 (01) :45-58
[2]   Saliency-SVM: An automatic approach for image segmentation [J].
Bai, Xuefei ;
Wang, Wenjian .
NEUROCOMPUTING, 2014, 136 :243-255
[3]  
Chen D, 2017, SENSORS, V17, P539
[4]  
Disi Chen, 2017, International Journal of Wireless and Mobile Computing, V12, P305
[5]   Integrated inference and learning of neural factors in structural support vector machines [J].
Houthooft, Rein ;
De Turck, Filip .
PATTERN RECOGNITION, 2016, 59 :292-301
[6]  
[焦卫东 Jiao Weidong], 2015, [仪器仪表学报, Chinese Journal of Scientific Instrument], V36, P1861
[7]   Insecurity of Voice Solution VoLTE in LTE Mobile Networks [J].
Li, Chi-Yu ;
Tu, Guan-Hua ;
Peng, Chunyi ;
Yuan, Zengwen ;
Li, Yuanjie ;
Lu, Songwu ;
Wang, Xinbing .
CCS'15: PROCEEDINGS OF THE 22ND ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, 2015, :316-327
[8]   Recognition and evaluation of bridge cracks with modified active contour model and greedy search-based support vector machine [J].
Li, Gang ;
Zhao, Xiaoxing ;
Du, Kai ;
Ru, Feng ;
Zhang, Yubo .
AUTOMATION IN CONSTRUCTION, 2017, 78 :51-61
[9]   ROSA: Resource-Oriented Service Management Schemes for Web of Things in a Smart Home [J].
Liao, Chun-Feng ;
Chen, Peng-Yu .
SENSORS, 2017, 17 (10)
[10]  
Lu Zhaogang, 2015, INT J INFORM COMMUNI, V7, P508