Lossless parameterisation of image contour for shape recognition

被引:0
|
作者
Lin, W. -S. [1 ]
Fang, C. -H. [1 ]
机构
[1] Natl Taiwan Univ, Dept Elect Engn, Taipei 106, Taiwan
关键词
AFFINE INVARIANT FUNCTION; OBJECT RECOGNITION; REPRESENTATION; ALGORITHM;
D O I
10.1049/iet-cvi:20070042
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A parameterised contour that is invariant against affine transformations is a convenient substitution of the object image for shape recognition. Generally, parameterisation needs several representative signals of the image contour to fit the affine transformation model. When the representative signals fail to carry the contour information thoroughly, information loss occurs in the resulting parameterised contour, and so the accuracy of shape recognition may deteriorate. Synthesised feature signals are shown, which represent that an image contour without information loss can be extracted with partial Fourier synthesis or partial cosine synthesis. Lossless parameterisation of the image contour is obtained by substituting the synthesised feature signals into the affine invariant function. Experimental results verify its representative, affine invariance and recognition rate in shape recognition. The results are compared with those by partial wavelet synthesis, which has insignificant information loss.
引用
收藏
页码:36 / 46
页数:11
相关论文
共 50 条
  • [1] Soft Compression for Lossless Image Coding Based on Shape Recognition
    Xin, Gangtao
    Fan, Pingyi
    ENTROPY, 2021, 23 (12)
  • [2] Efficient lossless image contour coding
    Turner, MJ
    Wiseman, NE
    COMPUTER GRAPHICS FORUM, 1996, 15 (02) : 107 - 117
  • [3] Efficient lossless image contour coding
    De Montfort Univ, Leicester, United Kingdom
    Comput Graphics Forum, 2 (107-117):
  • [4] Pitch Contour Parameterisation based on Linear Stylisation for Emotion Recognition
    Sethu, Vidhyasaharan
    Ambikairajah, Eliathamby
    Epps, Julien
    INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 1979 - +
  • [5] Visual shape recognition with contour propagation
    Rasche, C
    BIOLOGICAL CYBERNETICS, 2005, 93 (01) : 31 - 42
  • [6] Decomposed Contour Prior for Shape Recognition
    Yang, Zhi
    Kong, Yu
    Fu, Yun
    2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012, : 767 - 770
  • [7] The effect of contour closure on shape recognition
    Garrigan, Patrick
    PERCEPTION, 2012, 41 (02) : 221 - 235
  • [8] Visual shape recognition with contour propagation
    C. Rasche
    Biological Cybernetics, 2005, 93 : 31 - 42
  • [9] Lifting Parameterisation of the 9/7 Wavelet Filterbank and its Application in Lossless Image Compression
    Strutz, Tilo
    PROCEEDINGS OF THE 8TH WSEAS INTERNATIONAL CONFERENCE ON RECENT ADVANCES IN SIGNAL PROCESSING, ROBOTICS AND AUTOMATION, 2009, : 161 - 166
  • [10] MODEL OF THE CONTOUR OF THE IMAGE WITH A RANDOM SHAPE
    Khafizov, R. G.
    COMPUTER OPTICS, 2014, 38 (01) : 127 - 130