Virendra P. Vishwakarma

Work place: University School of Information and Communication Technology, Guru Gobind Singh Indarprastha University, Dwarka, Delhi, India



Research Interests: Computing Platform, Image Processing, Pattern Recognition


Dr.Virendra P. Vishwakarma is Head, University IT Services Cell, and an Associate Professor in University School of Information & Communication Technology, Guru Gobind Singh Indraprastha University New Delhi, India. Prior to joining GGSIP University, he worked as Professor in the department of CSE at Indraprastha Engineering College Ghaziabad, India from Dec. 2012 to Aug. 2013. He was with department of CSE at Amity School of Engineering & Technology, New Delhi, and Jaypee Institute of Information Technology, Noida from 2002 to 2010 and from July 2010 to Dec 2012 respectively. From 1996 to 2000, he was in Research Design and Standards Organization, Ministry of Railways, India, where he was involved in many research projects. He was awarded with “Distinguished Service Certificates” for specific contributions there for years 1998 and 2000. He received his B. Tech. degree in Electrical Engineering from H.B.T.I. Kanpur, India, in 1994; M.E. and Ph.D. in Computer Science & Engineering from M.N.N.I.T. Allahabad, and Guru Gobind Singh Indraprastha University New Delhi, India, in 2002 and 2012 respectively. He has published many research papers in refereed International Journals and Conferences and reviewed many research papers of International Journals and Conferences including IET Image Processing (IEE) and Journal of Computer Science and Technology (Springer). His area of research includes digital image processing, soft computing and pattern recognition. He has delivered many invited talks in these areas in FDPs, conferences and seminars.

Author Articles
Pose Normalization based on Kernel ELM Regression for Face Recognition

By Tripti Goel Vijay Nehra Virendra P. Vishwakarma

DOI:, Pub. Date: 8 May 2017

Pose variation is the one of the main difficulty faced by present automatic face recognition system. Due to the pose variations, feature vectors of the same person may vary more than inter person identity. This paper aims to generate virtual frontal view from its corresponding non frontal face image. The approach presented in this paper is based on the assumption of existence of an approximate mapping between the non frontal posed image and its corresponding frontal view. By calculating the mapping between frontal and posed image, the problem of estimating the frontal view will become the regression problem. In the present approach, non linear mapping, kernel extreme learning machine (KELM) regression is used to generate virtual frontal face image from its non frontal counterpart. Kernel ELM regression is used to compensate for the non linear shape of the face. The studies are performed on GTAV database with 5 posed images and compared with linear regression approach.

[...] Read more.
Other Articles