Indexing, Learning and Content-Based Retrieval for Special Purpose Image Databases

Abstract

C e n t r u m v o o r W i s k u n d e e n I n f o r m a t i c a PNA Probability, Networks and Algorithms Probability, Networks and AlgorithmsIndexing, learning and content-based retrieval for special purpose image databases M.J. Huiskes, E.J. Pauwels Indexing, learning and content-based retrieval for special purpose image databases ABSTRACT This chapter deals with content-based image retrieval in special purpose image databases. As image data is amassed ever more effortlessly, building efficient systems for searching and browsing of image databases becomes increasingly urgent. We provide an overview of the current state-of-the art by taking a tour along the entire "image retrieval chain" -from processing raw image data, through various methods of machine learning, to the interactive presentation of query results. As the key to building successful image retrieval systems is in the detailed and accurate description of the images, we start out with a discussion on content representation and indexing. We describe various methods to obtain image features, and also introduce the representation of content by means of MPEG-7 metadata. With regard to the search system itself, we focus particularly on interfaces and learning algorithms which facilitate relevance feedback, i.e. on systems that allow for natural interaction with the user in refining queries directly in terms of example images. To this end the literature on this subject is reviewed, and an outline is provided of the special structure of the relevance feedback learning problem. Finally we present a probabilistic approach to relevance feedback that addresses this special structure. REPORT PNA-E0423 DECEMBER 2004

Image Analysis: Performance Gaps of Batik Craft in Yogyakarta, Indonesia

“…This is due to the nature of the dye that is only attached to the outer layer of the fabric, and the fabric does not seep (Huiskes & Pauwels, 2004). In this study, some of the traits or characteristics of a texture described as a distribution of values of gray intensity image showing the distribution of the intensity values of gray.…”

“…Features batik is made to explain the overall appearance of the following colors, texture, complexity and periodicity. Most of the features used to describe the appearance of a single image area (Huiskes & Pauwels, 2004).…”

“…The decomposition pattern recognition is made on the basis of pattern recognition (Huiskes & Pauwels, 2004).…”

“…Standard scale, gray consists of 5 pairs of standard plates, gray and every pair shows the difference or contrast of colors corresponding to the value of the color fastness. Value scale, gray determines the degree of difference or contrast the color of the lower level to the highest of horizontal, vertical and diagonal (Kwartiningsih, Setyawardhani, Wiyatno, & Triyono, 2009;and Huiskes & Pauwels, 2004).…”

“…Feature Extraction, is that the performance of batik craft that has a color fastness to rubbing dry and wet, and washed (Kwartiningsih et al, 2009;and Huiskes & Pauwels, 2004).…”