Curvature Scale Space application to distorted object recognition and classification

被引：0
|
作者：
Jacobson, Natan [1 ]
Nguyen, Truong [1 ]
Crosby, Frank [2 ]
机构：
[1] Univ Calif San Diego, San Diego, CA 92103 USA
[2] Naval Surface Warfare ctr, Panama City, FL USA
来源：
CONFERENCE RECORD OF THE FORTY-FIRST ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, VOLS 1-5 | 2007年
关键词：
D O I：
暂无
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
Contour classification methods which operate directly on an image are greatly affected by small magnitude transformations to the image. In this paper, a contour classification method is developed which takes advantage of Curvature Scale Space (CS2) and a linear Support Vector Machine (SVM) classifier. The CS2 representation boasts invariance to transformations including: scaling, rotation, translation and noise. In addition, the linear SVM is a robust tool for classification problems involving multiple labels. The combination of these tools produces a classifier well suited for object recognition in photographs where distortion is present.
引用
收藏
页码：2110 / +
页数：2
相关论文
共 50 条
  • [11] Comparison of HK and SC Curvature Descriptions in a Scale-Space for the Purpose of 3D Object Recognition
    Akagunduz, Erdem
    Ulusoy, Ilkay
    2009 IEEE 17TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE, VOLS 1 AND 2, 2009, : 218 - 221
  • [12] Reliable classification of chrysanthemum leaves through curvature scale space
    Abbasi, S
    Mokhtarian, F
    Kittler, J
    SCALE-SPACE THEORY IN COMPUTER VISION, 1997, 1252 : 284 - 295
  • [13] Shape classification based on histogram representation in curvature scale space
    Peng, Jinye
    Yang, Wanhai
    Li, Yan
    2006 INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND SECURITY, PTS 1 AND 2, PROCEEDINGS, 2006, : 1722 - 1725
  • [14] Enhancing curvature scale space features for robust shape classification
    Kopf, S
    Haenselmann, T
    Effelsberg, W
    2005 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), VOLS 1 AND 2, 2005, : 478 - 481
  • [15] Fuzzy pyramid scheme for distorted object recognition
    Liu, XF
    Tan, SH
    Ong, SH
    PATTERN RECOGNITION, 1996, 29 (10) : 1631 - 1646
  • [16] Object Recognition Under Distorted Prosthetic Vision
    Guo, Hong
    Wang, Youmin
    Yang, Yuan
    Tong, Shanbao
    Zhu, Yisheng
    Qiu, Yihong
    ARTIFICIAL ORGANS, 2010, 34 (10) : 846 - 856
  • [17] A new SVM for distorted SAR object classification
    Yuan, C
    Casasent, D
    Optical Pattern Recognition XVI, 2005, 5816 : 10 - 22
  • [18] Curvature tensors on distorted Killing horizons and their algebraic classification
    Pravda, V
    Zaslavskii, OB
    CLASSICAL AND QUANTUM GRAVITY, 2005, 22 (23) : 5053 - 5071
  • [19] Feature space trajectory for distorted-object classification and pose estimation in synthetic aperture radar
    Casasent, D
    Shenoy, R
    OPTICAL ENGINEERING, 1997, 36 (10) : 2719 - 2728
  • [20] A hierarchical object recognition system based on multi-scale principal curvature regions
    Zhang, Wei
    Deng, Hongli
    Dietterich, Thomas G.
    Mortensen, Eric N.
    18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2006, : 778 - +
12345