Image Retrieval using Color-Texture Features Extracted from Walshlet Pyramid

The paper presents novel Walshlet Pyramid based image retrieval techniques. Here content based image retrieval (CBIR) is done using the image feature set extracted from Walshlets applied on the image at various levels of decomposition. Here the database image features are extracted by applying Walshlets on gray plane (average of red, green and blue) and color planes (red, green and blue components). The techniques Gray-Walshlets and Color-Walshlets are tested on image database having 11 categories with total 1000 images. Total 55 queries are fired on image database. The results show that precision and recall of Walshlets are better than complete Walsh based CBIR, which proves that Walshlets gives better discrimination capability in image retrieval at much higher speed of query execution per higher level Walshlets. Color-Walshlets based CBIR have greater precision and recall than Gray-Walshlets based CBIR. The Walshlets level-5 outperforms other Walshlets, because the higher level Walshlets are giving very coarse color-texture features while the lower level Walshlets are representing very fine color-texture features which are less useful to differentiate the images in image retrieval.