For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Complex Cell Descriptor Learning for Robust Object Recognition
Zhe WANG Yaping HUANG Siwei LUO Liang WANG
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2011/07/01
Online ISSN: 1745-1361
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Pattern Recognition
Independent Component Analysis, overcomplete, complex cell, invariant feature, object recognition, Caltech-101,
Full Text: PDF(455.2KB)>>
An unsupervised algorithm is proposed for learning overcomplete topographic representations of nature image. Our method is based on Independent Component Analysis (ICA) model due to its superiority on feature extraction, and overcomes the weakness of traditional method in fast overcomplete learning. Besides, the learnt topographic representation, resembling receptive fields of complex cells, can be used as descriptors to extract invariant features. Recognition experiments on Caltech-101 dataset confirm that these complex cell descriptors are not only efficient in feature extraction but achieve comparable performances to traditional descriptors.