Spectra of shape contexts: An application to symbol recognition

被引：5
|
作者：
Yang, Su [1 ]
机构：
[1] Fudan Univ, Coll Comp Sci & Technol, Shanghai Key Lab Intelligent Informat Proc, Shanghai 201203, Peoples R China
来源：
PATTERN RECOGNITION | 2014年 / 47卷 / 05期
关键词：
Symbol recognition; Shape matching; Histogram-based descriptor; Shape context; FFT; Histogram comparison; Point pattern matching; Maximum clique; Image retrieval; Object recognition; MODEL;
D O I：
10.1016/j.patcog.2013.11.020
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The pixel-level constraint (PLC) histograms are known for robustness and invariance in symbol recognition but limited in O(N-3) complexity. This paper proves that matching two PLC histograms can approximately be solved as matching the power spectra of the corresponding shape contexts. As a result, spectra of shape contexts (SSC) inherit robustness and invariance from PLC while the computational cost can be reduced. Moreover, a maximum clique based scheme is proposed for outlier rejection. The theoretical and experimental validation justifies that SSC possesses the desired properties for symbol recognition, that is, robustness, invariance, and efficiency. It outperforms PLC in terms of robustness and time efficiency, and shape context in terms of rotation invariance. (C) 2013 Elsevier Ltd. All rights reserved.
引用
收藏
页码：1891 / 1903
页数：13
相关论文
共 50 条
  • [1] Symbol and shape recognition
    Cordella, LP
    Vento, M
    GRAPHICS RECOGNITION, RECENT ADVANCES, 2001, 1941 : 167 - 182
  • [2] Aligning Bags of Shape Contexts for Blurred Shape Model Based Symbol Classification
    Battiato, Sebastiano
    Farinella, Giovanni Maria
    Giudice, Oliver
    Puglisi, Giovanni
    2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012, : 1598 - 1601
  • [3] Shape Matching and Object Recognition Using Shape Contexts
    Salve, Suhas G.
    Jondhale, Kalpana C.
    PROCEEDINGS OF 2010 3RD IEEE INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND INFORMATION TECHNOLOGY, VOL 9 (ICCSIT 2010), 2010, : 471 - 474
  • [4] Shape matching and object recognition using shape contexts
    Belongie, S
    Malik, J
    Puzicha, J
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (04) : 509 - 522
  • [5] Symbol Recognition By Multiresolution Shape Context Matching
    Su, Feng
    Lu, Tong
    Yang, Ruoyu
    11TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2011), 2011, : 1319 - 1323
  • [6] Hand shape recognition based on coherent distance shape contexts
    Hu, Rong-Xiang
    Jia, Wei
    Zhang, David
    Gui, Jie
    Song, Liang-Tu
    PATTERN RECOGNITION, 2012, 45 (09) : 3348 - 3359
  • [7] Hierarchical projective invariant contexts for shape recognition
    Jia, Qi
    Fan, Xin
    Liu, Yu
    Li, Haojie
    Luo, Zhongxuan
    Guo, He
    PATTERN RECOGNITION, 2016, 52 : 358 - 374
  • [8] TV symbol recognition based on shape and color features
    Shi, Ying-Chun
    Zhou, Xian-Zhong
    Fang, Peng-Fei
    Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence, 2005, 18 (02): : 216 - 222
  • [9] Circular Blurred Shape Model for Multiclass Symbol Recognition
    Escalera, Sergio
    Fornes, Alicia
    Pujol, Oriol
    Llados, Josep
    Radeva, Petia
    IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2011, 41 (02): : 497 - 506
  • [10] Peculiarities of Melin transform application to symbol recognition
    Furgala, Yu. M.
    Rusyn, B. P.
    2018 14TH INTERNATIONAL CONFERENCE ON ADVANCED TRENDS IN RADIOELECTRONICS, TELECOMMUNICATIONS AND COMPUTER ENGINEERING (TCSET), 2018, : 251 - 254
12345