Texture-based ancient porcelain shards classifications using Gabor transform

In this paper, based on analysis of gabor-filters parameters, it selects filters which have multi-scale and multi-orientation parameters, extract texture features from the convolution results that use these filters and Ancient porcelain shards Images, and reduce feature-data¿s dimensions based on principal component analysis (PCA). At last, use nearest neighbor method classifies shards, automatically classify and recognize these ancient shards are realized.