Indian Society for Education and Environment Content Based Image Retrieval Using Signature Based Similarity Search Indian Society for Education and Environment

iSee© category: Research article " Image retrieval " by Rajya Lakshmi et al. Abstract: Two of the main components of the visual information are texture and color. In this paper, a content-based image retrieval system (CBIR), which computes texture and color similarity among images, is presented. CBIR is a set of techniques for retrieving semantically-relevant images from an image database based on automatically-derived image features. One of the main tasks for CBIR systems is similarity comparison, extracting feature signatures of every image based on its pixel values and defining rules for comparing images. These features become the image representation for measuring similarity with other images in the database. Images are compared by calculating the difference of its feature components to other image descriptors. Previously CBIR methods used global feature extraction to obtain the image descriptors. For example, several features like color, texture and shape extracted from each image. These descriptors are obtained globally by extracting information on the means of color histograms for color features; global texture information on coarseness, contrast, and direction; and shape features about the curvature, moments invariants, circularity, and eccentricity. These global approaches are not adequate to support queries looking for images where specific objects in an image having particular colors and/or texture are present, and shift/scale invariant queries, where the position and/or the dimension of the query objects may not relevant. For example, suppose in one image there are two flowers with different colors: red and yellow, the global features describe the image as the average of the global average color which is orange. This description is certainly not the representation of the semantic meaning of the image. Therefore, the weakness of global features is observable. Region-based retrieval systems attempt to overcome previous method limitations of global based retrieval systems by representing images as collections of regions that may correspond to objects such as flowers, trees, skies, and mountains. Introduction In recent years, very large collections of images and videos have grown rapidly. In parallel with this growth, content-based retrieval and querying the indexed collections are required to access visual information. There are two general approaches for image retrieval. One is Text Based Image Retrieval and Content Based Image Retrieval. The text-based approaches apply traditional text retrieval techniques to image annotations or descriptions. One major problem with this is the task of describing image content is highly subjective. The perspective of textual descriptions given by …