An Effective Similarity Measure via Genetic Algorithm for Content Based Image Retrieval with Extensive Features

Baddeti Syam1 and Yarravarapu Srinivasa Rao2
1Associate Professor and HOD, Department of ECE, Mandava Institute of Engineering and Technology, Jaggayyapet -521 275, Andhrapradesh, India.
2Senior Associate Professor, Instrument Technology Department, AU College of Engineering, Andhra University, Visakhapatnam, Andhra Pradesh, India.

 

Abstract: Recently, the construction of large datasets has been facilitated by the developments in data storage and image acquisition technologies. In order to manage these datasets in an efficient manner development of suitable information systems are necessary. Content-Based Image Retrieval is commonly utilized in most of the systems. Based on image content, CBIR extracts images that are relevant to the given query image from large image databases. Most of the CBIR systems available in the literature extract only concise feature sets that limit the retrieval efficiency. In this paper, extensive features are extracted from the database images and stored in the feature library. The extensive features set is comprised of shape feature along with the color, texture and the contourlet features, which are utilized in the previous work. When a query image is given, the features are extracted in the similar fashion.  Subsequently, Genetic Algorithm-based similarity measure is performed between the query image features and the database image features. The Squared Euclidean Distance (SED) aids the similarity measure in determining the Genetic Algorithm fitness. Hence, from the Genetic Algorithm-based similarity measure, the database images that are relevant to the given query image are retrieved. The proposed CBIR technique is evaluated by querying different images and the retrieval efficiency is evaluated by determining precision-recall values for the retrieval results.

Keywords: Content Based Image Retrieval (CBIR), Genetic Algorithm (GA), Squared Euclidean Distance (SED), and shape feature, similarity measure.

 

  

Full Text