Journal of Advanced Engineering Research ISSN: 2393-8447 Volume 1, Issue 1, 2014, pp.60-65 Research Article 60 www.jaeronline.com Content Based Image Retrieval Method using Fuzzy Heuristics P.E. Rubini* Department of Computer Science, SRM University, Chennai, India *Corresponding author email: iniya29@gmail.com, Tel.: +91 9894188837 ABSTRACT Content based image retrieval (CBIR) refers to image content that is retrieved directly, by which the images with features or containing certain contents will be searched in an image database. The main idea of CBIR is to analyze image information by low level features of an image, which includes color, texture, shape and space relationship of objects etc., and to set up feature vectors of an image as its index. A new CBIR search engine is proposed using three features and similarity is measured and controlled by fuzzy heuristics. CBIR Search Engine relies on the characterization of primitive features such as color, shape, and texture that are automatically extracted from the images. There are several techniques to deal with CBIR problems for retrieving the relevant images. CBIR proposed by using three methods. Colour feature is extracted by using histogram based method, texture feature is extracted by using Gabor filter and shape feature is by moment invariant algorithm. For searching the similar images with the database similarity measure is calculated and is controlled by using fuzzy. Fuzzy similarity measure is implemented by using mamdani fuzzy inference method. The use of these three algorithms ensures that the image retrieval approach produces images which are relevant to the content of an image query. Keywords - Content-based, Fuzzy heuristics, Image retrieval, Search engine. 1. INTRODUCTION Nowadays, with large number of digital images available on Internet, efficient indexing and searching becomes important for large image storage. In traditional approach labeling of images with keywords, provides the diversity and ambiguity of image contents. So, content-based image retrieval (CBIR) approach indexes images by low-level visual features such as color, texture and shape. A typical CBIR system consists of two main parts: (1) feature extraction and (2) similarity measurement as shown in Fig.1. First, features such as shape, texture and colour, which constitute the image signature, are generated to represent the content of a given image. The similarity of a query image to the images in database is then measured using an appropriate distance metric. In typical content based image retrieval approach, a user submits an image based query which is then used by the system to extract visual features from images. The visual feature is based on the type of image retrieval. These features are examined in order to search and retrieve similar images from image database. The similarity of visual features between query image and image in a database is calculated by applying fuzzy rules. 2. BACKGROUNDS In content-based image retrieval systems, a desirable image is retrieved, from the large collection of images stored in the image database, based on their visual content. The visual content of an image is represented by common attributes which are called features. They include ‘shape of the image’, ‘colour histogram of the image’ and ‘texture of the image’. 2.1 Colour features Colour feature is the most commonly used visual feature for image retrieval. Many colour models are available that can be used to represent images such as HSI, HSV, LAB, LUV and YCrCb. Colours play a major role in human perception. The most commonly used colour model is RGB, where each component represents colour, red, green and blue. 2.2 Texture features Texture is another important feature of an image that can be extracted for the purpose of image retrieval. Image texture refers to surface patterns which show granular details of an image. It also gives information about the arrangement of different colours. There exist two main approaches for texture analysis. They include structural and statistical approaches. In structural texture approach, the surface pattern is repeated .In statistical texture; the surface pattern is not regularly repeated in the same pattern such as different flower