Indian Journal of Science and Technology
Year: 2008, Volume: 1, Issue: 5, Pages: 1-6
D. Rajya Lakshmi*1, A.Damodaram1 , M.Sreenivasa Rao2 and J.A.Chandu Lal3
1GITAM Engg. College, Visakhapatnam, India
2JNTU college of Engg, Hyderabad
3JNT University, Hyderabad
4GITAM University, Visakhapatnam.
*Author for the correspondence:
D. Rajya Lakshmi
GITAM Engg. College, Visakhapatnam, India
E-mail: [email protected]
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.
Keywords: Content based, image retrieval, binary signature, region-based, Debouche compression, segmentation.
Subscribe now for latest articles and news.