Computer Graphic and Photographic Image Classification using Local Image Descriptors

Gajanan K Birajdar; Vijay H Mankar

doi:10.14429/dsj.67.10079

Gajanan K Birajdar Department of Electronics and Communication Engineering, Priyadarshini Institute of Engineering and Technology, Nagpur - 400 019 http://orcid.org/0000-0003-3531-3958
Vijay H Mankar Department of Electronics and Telecommunication Engineering, Government Polytechnic, Ahmednagar - 414 001

DOI: https://doi.org/10.14429/dsj.67.10079

Keywords: Binary statistical image feature, Image forensics, Digital image forensic, Discrete wavelet transform, Natural image, Fuzzy entropy measure, Computer graphic image, Photo graphic image

Abstract

With the tremendous development of computer graphic rendering technology, photorealistic computer graphic images are difficult to differentiate from photo graphic images. In this article, a method is proposed based on discrete wavelet transform based binary statistical image features to distinguish computer graphic from photo graphic images using the support vector machine classifier. Textural descriptors extracted using binary statistical image features are different for computer graphic and photo graphic which are based on learning of natural image statistic filters. Input RGB image is first converted into grayscale and decomposed into sub-bands using Haar discrete wavelet transform and then binary statistical image features are extracted. Fuzzy entropy based feature subset selection is employed to choose relevant features. Experimental results using Columbia database show that the method achieves good detection accuracy.

Author Biographies

Gajanan K Birajdar, Department of Electronics and Communication Engineering, Priyadarshini Institute of Engineering and Technology, Nagpur - 400 019

Shri Gajanan K. Birajdar received his BE (Electronics Engineering) and ME (Electronics and Telecommunication Engineering) from Dr Babasaheb Ambedkar Technological University, Maharashtra, in 1996 and 2004, respectively. Currently pursuing his PhD in the area of blind image forensics from Nagpur University. He is working as Associate Professor in the Department of Electronics Engineering, Ramrao Adik Institute of Technology Nerul, University of Mumbai, Navi Mumbai. His current research interests include: Signal and image processing, soft computing and multimedia forensic.

He was responsible for design and development of the algorithm, software implementation, conduction of analysis and interpretation of results.

Vijay H Mankar, Department of Electronics and Telecommunication Engineering, Government Polytechnic, Ahmednagar - 414 001

Dr Vijay H. Mankar received MTech in Electronics Engineering from VNIT, Nagpur University, in 1995 and PhD from Jadavpur University, Kolkata, in 2009. Presently working as a Head of Department in Government Polytechnic, Ahmednagar (MS), India. He has published more than 60 research papers. His field of interest includes : Digital image processing, Digital image forensics, data hiding and watermarking.

He contributed in designing the research and was responsible for overall guidance in implementation of the proposed system.