Batik image retrieval based on similarity of shape and texture characteristics

This research develops the concept of CBIR on the image motif. For processes that do not only find images that have been stored in database, but also be able to recognize some resemblance ornament image or texture as well as form. Although different size, direction of slope, and the layout of texture and shape, but the concept will be recognized. In calculating the percentage of similarity is not only based on performance measurement precision but also the image of the relevant. From the results of over 250 studies batik motif images and 25 images in the database query, it is used for texture feature extraction methods canny edge detection and shape invariant moment feature extraction. For the calculation of the similarity distance and Canberra distance is used euclid functions. Threshold Algorithm which will display the image based on the value of the highest grade representation on each image query, followed by comparing the results of feature extraction using the operator min on fuzzy logic to generate maximum value. Excess Threshold algorithm, compared with other methods lies in simplicity retrieval method in the image, so that the performance of CBIR becomes more reliable and effective.