Textural features for image database retrieval

This paper presents two feature extraction methods and two decision methods to retrieve images having some sec-tion in them that is like the user input image. The features used are variances of gray level co-occurrences and line-angle-ratio statistics constituted by a 2-D histogram of an-gles between two intersecting lines and ratio of mean gray levels inside and outside the regions spanned by those an-gles. The decision method involves associating with any pair of images either the class “relevant ” or “irrelevant”. A Gaussian classifier and nearest neighbor classifier are used. A protocol that translates a frame throughout ev-ery image to automatically define for any pair of images whether they are in the relevance class or the irrelevance class is discussed. Experiments on a database of 300 gray scale images with 9,600 groundtruth image pairs showed that the classifier assigned 80 % of the image pairs we were sure were relevant, to the relevance class correctly. The ac-tual retrieval accuracy is greater than this lower bound of 80%. 1