Content Based Image Classification And Retrieval Using Support Vector Machine

Abstract

Content-based image retrieval (CBIR) systems are a special type of Information Retrieval (IR) system where the elements in the repository are pictures. IR works with finding digital resources in large databases. CBIR is developed to retrieve the desired target image from the large collection of images based on the contents of the given query image. The Contents of image can be extracted from any images which are specified color, shape, texture or any other characteristics of images. The system derived two types of different color features - color moment and color auto-correlogram. The moments of image can be used to indicate color distribution of an image which can be described as a probability distribution of colors. To calculate the spatial correlation of pairs of color different with distance, color correlogram is introduced in the system. Gabor wavelets are used to express texture of natural image. The characteristics of Gabor wavelets are similar to those of human visual features. The system firstly created the features vector with these three types of features and used to get higher retrieval results of system. To gives the better result in retrieval of system and classify the query image, Support Vector Machine classifier is used with the combination of these visual features.