Hybrid ICA with wavelet for Describing Local Regions
In this paper present a local regions descriptors representation method based on independent components analysis (ICA) and wavelet transform. We reduce the feature dimensions using ICA. The proposed algorithm first finds the characteristic scale and the location for the interest points. And then wavelet transform is performed on the neighborhood of the local regions and get low frequency gradient feature. The experiments show that our method is more accurate and fast than some standard method.
Feature descriptors Wavelet transform Matching
Lili ZHU Hua Yuan
School of Information Media Engineering Changchun University of Technology Changchun,China School of Computer Science & Engineering Changchun University of Technology Changchun,China
国际会议
长春
英文
307-310
2010-08-24（万方平台首次上网日期，不代表论文的发表时间）