Uyghur document image retrieval based on gray gradient co-occurrence matrix

The gray gradient co-occurrence matrix based Uyghur document image retrieval method is proposed in this paper. 15 parameters of gray gradient co-occurrence matrix such as small gradient advantage, high gradient strengths, intensity in homogeneity etc are extracted separately, and document image features are matched with the characteristic distance classifier and the Euclidean distance classifier. The document image retrieval experiments are conducted using 1948 images, it has been obtained 96.68% of matching rate with a half page image as query image, and 100% of matching rate is achieved using hole page image. After the query image is divided into several sub images and with the increasing of the number of sub images, the percentage of image matching is decreased, and the changing of average retrieval time is quite little. The experimental results indicated that the proposed method is a kind of effective retrieval method for Uyghur document images.