V. P. Shukla

Work place: Deptt. Of Mathematics Faculty of Engineering & Tech. MITS Laxmangarh, (India)

E-mail: vpshukla.fet@modyuniversity.ac.in


Research Interests: Computer Vision, Solid Modeling, Image Processing, Medical Image Computing, Models of Computation


Dr. Vidya Prasad Shukla was born in India, in 1954. He received his M.Sc. (Applied Mathematics) in 1976, Ph.D. (Modelling and Computer Simulation) in 1982 and PG Dip. (Computational Hydraulic Engineering) in 1986 from Avadh University Faizabad, Indian Institute of Technology Kanpur and International Institute of Environmental & Hydraulic Engineering (Delft) the Netherlands respectively. He worked and officiated at various posts as Senior Research Officer, Chief Research Officer and HOD Computer Division at from Central Water and Power research Station (CWPRS), Pune from 1982 to 2003. Thereafter, he worked as a Professor in BIT, Sathyamangalam and NIT Durgapur from 2003 to 2009. He has joined as a Professor in Mody Institute of Technology & Science, Deemed University Lakshmangarh in 2009. He has published over 75 papers in refereed journals and conference proceedings and written 29 technical reports on various clients sponsored research projects of international/national importance. He is an editor of the book “Development of Coastal Engineering” from CWPRS, Pune. His current research interest includes Computer Simulation & Modeling, Image processing, Cellular Automata, Soft-Computing, Computer Vision, Nanotech-simulation, Operations Research, Mathematical Biology, Modeling of Arms Race of Nations.

Author Articles
Wavelet Based Histogram of Oriented Gradients Feature Descriptors for Classification of Partially Occluded Objects

By Ajay Kumar Singh V. P. Shukla Shamik Tiwari S. R. Biradar

DOI: https://doi.org/10.5815/ijisa.2015.03.07, Pub. Date: 8 Feb. 2015

Computer vision applications face various challenges while detection and classification of objects in real world like large variation in appearances, cluttered back ground, noise, occlusion, low illumination etc.. In this paper a Wavelet based Histogram of Oriented Gradients (WHOG) feature descriptors are proposed to represent shape information by storing local gradients in image. This results in enhanced representation of shape information. The performance of the feature descriptors are tested on multiclass image data set having partial occlusion, different scales and rotated object images. The performance of WHOG feature based object classification is compared with HOG feature based classification. The matching of test image with its learned class is performed using Back Propagation Neural Network (BPNN) algorithm. Proposed features not only performed superior than HOG but also beat wavelet, moment invariant and Curvelet.

[...] Read more.
Other Articles