Logarithmic distance measure with improved local vector pattern for content-based image retrieval

ABSTRACT

The development of image acquisition and data storage mechanisms have empowered the generation of broad image datasets. Under such circumstances, it is essential to promote the relevant information system to handle these collections properly. For this case, one of the most prominent methods is content-based image retrieval (CBIR) system, which can retrieve the required images from the large dataset. This paper proposes the CBIR system based on an informative pattern descriptor and a nonlinear similarity matching measure. The conventional retrieval process determines the distance between the feature library and the query features at the lower order and, subsequently, identifies the similar images with minimum distance. The proposed similarity measure will introduce the degree of similarity in logarithmic scale, and so the range of similar contents can be quantified. The experimental results affirm the beneficial part of PLVP method in providing a more informative and computationally efficient image-retrieving system.

KEYWORDS:

• CBIR
• texture
• descriptor
• LVP
• PLVP
• log similarity

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes on contributors

Jatothu Brahmaiah Naik holds a BTech degree in Electronics and Communication Engineering from Velagapudi Ramakrishna Siddhartha Engineering College, ANU, Guntur, AP, India and, an MTech degree in Instrumentation Control System from JNTUK. He is presently pursuing a PhD at JNTUK, Kakinada and has twelve years' experience in Teaching. He is currently working as Assistant professor at the Department of ECE in VLITS, Vadlamudi. He has published eight papers in various journals and national conferences. His interest includes signal processing and image processing.

Giri Babu Kande earned a BTech degree in Electronics & Communication engineering from Nagarjuna University, Guntur, India in 1996 and an ME degree in Electronic Instrumentation from Andhra University, Visakhapatnam, India in 2000. In addition, he earned a PhD in Digital Image Processing area from JNTUH India. He is currently working as professor and HoD of ECE at Vasireddy Venkatadri Institute of Technology, Guntur, AP, India. He has published 25 papers in various journals and conferences. He is the Life member of ISTE. His research interests include signal processing, image processing and neural networks.

Dr Chanamallu Srinivasarao is currently working as Professor of ECE at JNTUK University College of Engineering, Vizianagaram, AP, India. He holds an M. Tech degree, and a PhD in Digital Image Processing area from University College of Engineering, JNTUK, Kakinada, A.P, India. He published 26 Research papers in reputed International Journals and Conferences. His research interests include Signal processing Speech processing and Image Processing.

Image note

All images contained within this article have been sourced from the VisTex, Corel-1K and Corel-10K databases.