An algorithm of image classification based on BP neural network

To improve the performance of image classification, we propose an image classification method based on BP neural network. Firstly, one image is segmented and clustered several visual objects. By means of the unit image library, we calculate one probability vector, which is composed by probability of every visual object of the image and every unit image of the unit image library. So a total feature vector of one image can been attain. By means of the BP neural network, which we construct, we attain a class about the image, thereby we can realize image classification. The end, Ground Truth Database is adopted experimental image library in this paper. The method attains good effect based on experimental result.