Research On Key Technologies For Scene Classification

Given a set of images of scenes containing multiple object categories (e.g. grass, roads, buildings) our objective is to discover these objects in each image in an unsupervised manner, and to use this object distribution to perform scene classification. We investigate the classification performance under changes in the visual vocabulary and number of latent topics learnt, and develop a novel vocabulary using SIFT descriptors. Then based on this method ,we developed vocabulary using multi-level SIFT descriptors in order to improve the classification performance. Finally Using a variety of features generate vocabulary, We achieve this discovery using probabilistic Latent Semantic Analysis (PLSA), a generative model from the statistical text literature, here applied to a bag of visual words representation for each image. The scene classification on the object distribution is carried out by a k-nearest neighbour classifier.In all cases the Scene Classification Based on Multi-level SIFT and Multi-feature for the combination of (unsupervised) PLSA followed by (supervised) K-nearest neighbour classification achieves more superior results .