International Journal of Engineering and Advanced Technology (IJEAT) ISSN: 2249 – 8958, Volume-2 Issue-1, October 2012 4 Published By: Blue Eyes Intelligence Engineering & Sciences Publication Retrieval Number: F0611071612/2012©BEIESP Abstract— The decreasing costs of consumer electronic devices such as digital cameras and digital camcorders, along with the ease of transportation facilitated by the Internet, has lead to a phenomenal rise in the amount of multimedia data. With this rapid development of multimedia technologies, the problem of how to retrieve a specified image from large amount of image databases becomes an important issue. In this paper we have developed a CBIR system based on the color features in RGB and HSV color space. Global color histogram (GCH) which lacks spatial information about the image colors has been compared with LCH. Algorithms were tested on two Databases one comprising of 500 JPEG images and another comprising of 120 JPEG images of national flags of different countries. The LCH approach has been found to be better and more accurate than GCH approach. Index Terms—GCH, LCH, RGB & HSV. I. INTRODUCTION Human vision is the most advanced of all our senses and as such we gather majority of information from the real world by visual sense. The twentieth century has witnessed unparalleled growth in the number, availability and importance of images in all walks of life. As the diversity and size of digital image collections have grown exponentially, efficient image retrieval is becoming increasingly important. Large image databases are difficult to browse with traditional text searches because the task of user based annotation become very time consuming, as the text often fails to convey the rich structure of images. A content-based retrieval system solves this problem where retrieval is based on the automating matching of feature of query image with that of image database through some image-image similarity evaluation [1]. Therefore images will be indexed according to their own visual content such as color, texture, shape or any other feature or a combination of set of visual features. In this paper, our research is limited to color feature of the image. There are several techniques available for the color feature extraction like color histogram, color layout, clustering and color correlogram etc [2]. The aim of the paper is to study various color based approaches and implement color histogram approach at global and local level. II. LITERATURE REVIEW Currently the most popular search engines for images have resulted in the development of algorithms to augment and replace tag based image retrieval with content based image retrieval. These algorithms compare the actual content of the Manuscript Received on October 2012. Gaurav Jaswal, ECE, Carrer Point University, Hamirpur, H.P, India Amit Kaul, EED, National Institute of Technology, Hamirpur, India Rajan Parmar, ECS, HPPCL, Shimla, H.P, India images rather than text which has been annotated previously by a human being. Once the specified feature has been extracted from the image, there are also a number of options for carrying out the actual comparison between images [3,4]. Generally similarity between two images is based on a computation involving the Euclidean distance or histogram intersection between the respective extracted features of two images. The three most common characteristics upon which images are compared in content based image retrieval algorithms are color, shape and texture [5]. Utilizing shape information for automated image comparisons requires algorithms that perform some form of edge detection or image segmentation. However, the performance of the algorithm is not invariant on scale or translation manipulations of images. Information regarding the texture of images can be even harder to extract automatically during retrieval. Generally algorithms rely on the comparison of adjacent pixels to determine the contrast or similarity between pixels [6]. A. Color based Image Retrieval The color feature is one of the most widely used visual features in image retrieval. It is relatively robust to background complication and independent of image size and orientation. In image retrieval, the color histogram is the most commonly used color feature representation. Statistically, it denotes the joint probability of the intensities of the three color channels. This paper attempts to explore and analyze such an algorithm that compares images based on their color content. Swain and Ballard proposed histogram intersection, an L1 metric, as the similarity measure for the color histogram [7]. To take into account the similarities between similar but not identical colors, Ioka and Niblack et al. introduced an L2-related metric in comparing the histograms. Furthermore, considering that most color histograms are very sparse and thus sensitive to noise, Stricker and Orengo proposed using the cumulated color histogram [8]. Their research results demonstrated the advantages of the proposed approach over the conventional color histogram approach. Besides the color histogram, several other color feature representations have been applied in image retrieval, including color moments and color sets. To overcome the quantization effects, as in the color histogram, Stricker and Orengo proposed the color moments approach [9]. The mathematical foundation of this approach is that any color distribution can be characterized by its moments. Furthermore, since most of the information is concentrated on the low-order moments, only first moment (mean), second and third central moments (variance and skewness) were extracted as the color feature representation. Weighted Euclidean distance was used to calculate the color similarity. To facilitate fast search over large-scale image collections, Smith Content based Image Retrieval using Color Space Approaches Gaurav Jaswal, Amit Kaul, Rajan Parmar