2014 | International Journal of Current Engineering and Technology, Vol.4, No.3 (June 2014) Research Article International Journal of Current Engineering and Technology E-ISSN 2277 – 4106, P-ISSN 2347 - 5161 ©2014 INPRESSCO ® , All Rights Reserved Available at http://inpressco.com/category/ijcet Adaptive Image Retrieval Technique using Texture and Color Features E Ramalakshmi Ȧ* and Keerthi Lingam Ȧ Ȧ Department of Information Technology, Chaitanya Bharathi Institute of Technology, Hyderabad,India Accepted 30 May 2014, Available online 01 June2014, Vol.4, No.3 (June 2014) Abstract CBIR is the area in image mining system which performs retrieval based on the similarity defined in terms of extracted features with more objectiveness. It aims at searching image databases for specific images that are similar to a given query image. In CBIR the features of the query image alone are considered and this is the drawback of this technique. Thus, a novel method based on clusters is emerged that improves user interaction with image retrieval systems by fully exploiting the similarity information. In order to reduce the searching time of images from the image database, the query image will be classified in this method. The target image is selected optimally according to the color characteristics with feature vectors which represent typical color distributions. The proposed technique aims to reduce the searching time of image retrieval and hence it improves the performance of image retrieval system. Keywords: Image Retrieval, CBIR, Cluster Based. 1. Introduction 1 In this digital era, multimedia data plays a very vital role in every field such as e-commerce, entertainment, education, medicine, aerospace and so on. With the increasing use of internet, there is an enormous volume of multimedia data available to the users. Even though, the huge availability of multimedia data like images, audio, video is useful and appreciable, sometimes it proves to be a bane as there are certain difficulties to gather the required useful data in an appropriate way. A huge volume of digital images are generated every day and if analyzed properly there is a lot of useful information available to the users. With the drastic increase in the multimedia databases, the usefulness of such information is dependent on how well it can be accessed; searched and how well knowledge can be extracted from it. Due to lack of proper extraction methodologies, the users are unable to extract the relevant information from the available databases (Hsu et al, 2002). In the present scenario, the conventional user defined text searches are based on keyword, size, type, date and time of capture, identity of the owner etc. This search based techniques are successful but do not meet the user’s final requirement in all cases. So, many researchers are concentrating on the search based on visual content i.e., finding the images similar to an input query image. There has been a lot of research in text based retrievals, but image retrieval is also gaining its momentum with regard to both still and moving images. Efficient image database retrieval can be done only if we *Corresponding author: E Ramalakshmi have a system that is able to automatically extract relevant features directly from the images stored in the database. So image mining proves to be efficient as it deals with complex operations like image retrieval, indexing and storing. There is a common misconception that image mining is an extension to data mining which is not so. Image mining is an upcoming research field and is still is in its extracting relevant knowledge from image data still remains a difficult task. The next few sections deal with a brief introduction to image mining and a broad explanation of the various phases involved in an image retrieval system. The main objective of image mining is on research and technological activities for automated and user centered extraction of information from very large and heterogeneous image databases. Image mining is focused on extracting patterns, implicit knowledge, image data relationship or patterns which are not explicitly found in the images from databases or collections of images. Some of the methods used to gather knowledge are: image retrieval, data mining, image processing and artificial intelligence. Image information mining is an interdisciplinary effort. Image retrieval is one of the phases in image mining. An image retrieval system is used for browsing, searching and retrieving images from a very large database of digital images. All image retrieval methods use some techniques of adding metadata such as keywords or descriptions to the images such that retrieval can be performed over the annotation words than images. Manual image annotation is slow, lengthy and costly. Determining the complexity of image search system design is important and for this purpose it is crucial to