Recognition algorithm for huge number of very similar objects

In order to identify a large number of very similar objects, a novel recognition approach is proposed by mean of combination of two dynamic grouping algorithms, the visual processing mechanism, PCA and multi-pathway SVM. The samples have been segmented to appropriate groups by grouping features, and then features with rotation invariance and translation invariance of each group are extracted. Finally, the features' reduced by PCA are put into the SVM to build classification models. The experimental results show that the proposed algorithms in this paper error rates are obviously less than the algorithms in which samples not be grouped and put the classification features into SVM to build a classification model directly.