Extended biologically inspired model for object recognition based on oriented Gaussian-Hermite moment

被引:15
|
作者
Lu, Yan-Feng [1 ]
Zhang, Hua-Zhen [1 ]
Kang, Tae-Koo [1 ]
Choi, In-Hwan [1 ]
Lim, Myo-Taeg [1 ]
机构
[1] Korea Univ, Sch Elect Engn, Seoul, South Korea
基金
新加坡国家研究基金会;
关键词
Object recognition; Classification; HMAX; Oriented Gaussian-Hermite moment; Gabor features; RECEPTIVE-FIELDS; INVARIANTS; APPEARANCE; HISTOGRAMS; FEATURES;
D O I
10.1016/j.neucom.2014.02.046
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Hierarchical Model and X (HMAX) presents a biologically inspired model for robust object recognition. The HMAX model, based on the mechanisms of the visual cortex, can be described as a four-layer structure. Although the performance of HMAX in object recognition is robust, it has been shown to be sensitive to rotation, which limits the model's performance. To alleviate this limitation, we propose an Oriented Gaussian-Hermite Moment-based HMAX (OGHM-HMAX). In contrast to HMAX which uses a Gabor filter for local feature representation, OGHM-HMAX employs the Oriented Gaussian-Hermite Moment (OGHM), which is a local representation method that represents features and is robust against distortions. OGHM is an extension of the modified discrete Gaussian-Hermite moment (MDGHM). To show the effectiveness of the proposed method, experimental studies on object categorization are conducted on the CalTech101, CalTech5, Scene13 and GRAZ01 databases. Experimental results demonstrate that the performance of OGHM-HMAX is a significant improvement on that of the conventional HMAX. (C) 2014 Elsevier ay. All rights reserved.
引用
收藏
页码:189 / 201
页数:13
相关论文
共 50 条
  • [41] SAR target configuration recognition based on the biologically inspired model
    Huang, Xiayuan
    Nie, Xiangli
    Wu, Wei
    Qiao, Hong
    Zhang, Bo
    NEUROCOMPUTING, 2017, 234 : 185 - 191
  • [42] A copy-move image forgery detection technique based on Gaussian-Hermite moments
    Meena, Kunj Bihari
    Tyagi, Vipin
    MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (23) : 33505 - 33526
  • [43] Object recognition by learning informative, biologically inspired visual features
    Wu, Yang
    Zheng, Nanning
    You, Qubo
    Du, Shaoyi
    2007 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-7, 2007, : 181 - 184
  • [44] Corners as Interesting Points in Biologically Inspired Object Recognition, HMAX
    Sufikarimi, Hiwa
    Mohammadi, Karim
    PROCEEDINGS OF THE 2017 7TH INTERNATIONAL CONFERENCE ON COMPUTER AND KNOWLEDGE ENGINEERING (ICCKE), 2017, : 119 - 124
  • [45] A copy-move image forgery detection technique based on Gaussian-Hermite moments
    Kunj Bihari Meena
    Vipin Tyagi
    Multimedia Tools and Applications, 2019, 78 : 33505 - 33526
  • [46] Biologically inspired recognition model with extension fields
    Kalocsai, P
    Biederman, I
    PROCEEDINGS OF THE 4TH JOINT SYMPOSIUM ON NEURAL COMPUTATION, VOL 7, 1997, : 116 - 123
  • [47] Biologically inspired recognition model with extension fields
    Kalocsai, P
    INTERNATIONAL CONFERENCE ON IMAGE PROCESSING - PROCEEDINGS, VOL II, 1997, : 450 - 453
  • [48] DIFFERENTIAL OPTICAL MICROSCOPY BASED ON HIGHER-ORDER GAUSSIAN-HERMITE BEAM PATTERNS
    CHRUSCH, P
    VAEZIRAVANI, M
    APPLIED OPTICS, 1992, 31 (34): : 7344 - 7347
  • [49] How Can Selection of Biologically Inspired Features Improve the Performance of a Robust Object Recognition Model?
    Ghodrati, Masoud
    Khaligh-Razavi, Seyed-Mahdi
    Ebrahimpour, Reza
    Rajaei, Karim
    Pooyan, Mohammad
    PLOS ONE, 2012, 7 (02):
  • [50] Remote sensing image registration based on Gaussian-Hermite moments and the Pseudo-RANSAC algorithm
    Li, Ying
    Li, Fangyi
    Yang, Kaixing
    Price, Chris
    Shen, Qiang
    REMOTE SENSING LETTERS, 2017, 8 (12) : 1162 - 1171