Content based Image Retrieval using Firefly algorithm and Neural Network

Abstract

Extensive digitization of images, paintings, diagrams and explosion of World Wide Web (www), has made traditional keyword based search for image, an inefficient method for retrieval of required image data. Content-Based Image Retrieval (CBIR) system retrieves the similar images from a large database for a given input query image. Today, various methods for implementation of CBIR which uses low-level image features like color, texture and shape are being found out. In this thesis, global image properties based CBIR using a Firefly algorithm and neural network is proposed. At first, the image is trained with firefly about the features of images in the database. The image features considered here are color histogram. The training is carried out using neural network algorithm. Information retrieval is an information request to a meaningful set of references in the process. Therefore, this problem can be solved by using various algorithms. This work has made several recent works to perform image segmentation based on local information into an image representation. But radon transform and Firefly algorithm has been proposed to improve the retrieval rate. This trained network when presented with a query image retrieves and displays the images which are relevant and similar to query from the database. The results show a considerable improvement in terms of precision and recall of image retrieval. The proposed method is applied on the different Datasets.
Keywords: CBIR; Firefly; Neural Network