一种基于特征捆绑计算模型的物体识别方法
作者:
基金项目:

Supported by the National Natural Science Foundation of China under Grant Nos.60903141, 60933004, 60805041(国家自然科学基金); the National Basic Research Program of China under Grant No.2007CB311004 (国家重点基础研究发展计划(973))

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [17]
  • |
  • 相似文献 [20]
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    利用一种特征捆绑计算模型,以Gabor特征作为模型的初级特征,将相关统计量作为实现特征捆绑的基础,提出了一种物体识别方法.并实现了一组物体识别实验,结果显示,该方法能够进行较快速而准确地识别,说明了此方法和所使用的特征捆绑计算模型的有效性.

    Abstract:

    This paper proposes a novel method for object recognition by using a computational model of feature binding, in which Gabor features are employed as the elementary features and correlation statistics provide the basis for implementing the feature binding. A group of object recognition experiments are conducted with this method,and the results prove the comparatively good performances with high recognition precision and high speed,indicating the validity of this method and the computational model.

    参考文献
    [1] Treisman A. Feature binding, attention and object perception. Philosophical Trans. of the Royal Society, Series B, 1998,353:1295?1306.
    [2] Singer W, Gray CM. Visual feature integration and the temporal correlation hypothesis. Annual Review of Neuroscience, 1995,18:555?586.
    [3] Treisman A, Gelede G. A feature-integration theory of attention. Cognitive Psychology, 1980,12:97?136.
    [4] Damasio AR. The brain binds entities and events by multiregional activation from convergence zones. Neural Computation, 1989,1:123?132.
    [5] Von der Malsburg C. The correlation theory of brain function. Internal Report. 1981. 81?82.
    [6] Gray CM, K?nig P, Engel AK, Singer W. Oscillatory responses in cat visual cortex exhibit inter-columnar synchronization which reflects global stimulus properties. Nature, 1989,338:334?337.
    [7] Horn D, Sagi D, Usher M. Segmentation, binding and illusory conjunctions. Neural Computation, 1991,3:510?525.
    [8] Schillen TB, Koènig P. Binding by temporal structure in multiple feature domains of an oscillatory neuronal network. Biological Cybernetics, 1994,70:397?405.
    [9] Engel AK, Koènig P, Kreiter AK, Schillen TR, Singer W. Temporal coding in the visual cortex: New vistas on integration in the nervous system. Trends Neurosci, 1992,15:218?226.
    [10] Shi ZW, Shi ZZ, Liu X, Shi ZP. A computational model for featuring binding. Science in China Series C, 2008,51(5):470?478 (in Chinese with English abstract).
    [11] Lades M, Vorbruggen JC, Buhmann J, Lange J, von der Malsburg C, Wurtz RP, Konen W. Distortion invariant object recognition in the dynamic link architecture. IEEE Trans. on Computers, 1993,42(3):300?311.
    [12] Daugman JG. Two-Dimensional spectral analysis of cortical receptive field profile. Vision Research, 1980,20:847?856.
    [13] Lee KC, Ho J, Kriegman D. Acquiring linear subspaces for face recognition under variable lighting. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2005,27(5):684?698.
    [14] Georghiades AS, Belhumeur PN, Kriegman DJ. From few to many: Illumination cone models for face recognition under variable lighting and pose. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2001,23(6):643?660.
    [15] Chang CC, Lin CJ. LIBSVM: A library for support vector machines. 2001.
    [16] Griffin G, Holub AD, Perona P. The Caltech-256. Caltech Technical Report, 2007.
    附中文参考文献: [10] 石志伟,史忠植,刘曦,施智平.特征捆绑的计算模型.中国科学(C 辑),2008,38(5):485-493.
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

刘曦,史忠植,石志伟,施智平.一种基于特征捆绑计算模型的物体识别方法.软件学报,2010,21(3):452-460

复制
分享
文章指标
  • 点击次数:5755
  • 下载次数: 7143
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2008-03-14
  • 最后修改日期:2008-10-27
文章二维码
您是第19922737位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号