Content Based Image Retrieval

Modern image search engines retrieve the images based on their visual contents, commonly referred to as Content Based Image Retrieval (CBIR) systems. Typical CBIR systems can organize and retrieve images from image databases, automatically by extracting some features such as color, texture, shape from images and looking for similar images which have similar feature. One problem of this approach is reliance on visual similarity to judge semantic similarity, which creates problems due to semantic gap between low-level content and high level concepts. Even with the subsistence of this problem, if aggressive attempts are made CBIR can be used for real life applications. For example in spite of the open problems like robust text understanding, Google and Yahoo have become most popular for searching. The work presented here mainly focuses on efficient CBIR methods with help of representation of converting the visual content of images in feature vector using proposed techniques. The proposed CBIR methods using Colour, Transformed Image, Texture and Shape content are proved to be better and faster using test bed of 1000 variable size images spread across 11 image categories.