ABSTRACT

Always the thrust for better and faster image retrieval techniques has nourished the research in content based image retrieval. The paper presents 32 novel image retrieval techniques using the feature vectors obtained by applying Walsh transform on row mean and column mean of full image, four fragments, sixteen fragments and 64 fragments of image. All the proposed CBIR techniques are tested on generic image database of size 1000 with 11 image classes. From the average precision and average recall values obtained by firing 55 queries on the image database it is found that use of row mean and column mean with image fragmentation improves the performance resulting in better image retrieval. In all these techniques to speed up the image retrieval process notion of energy compaction is introduced and tested for 100%, 95%, 90% and 85% of energy of feature vectors using Walsh transform.