Dr. Pradipta K. Banerjee

Research Interests :

• Automatic target detection, recognition and tracking

• Emotion Recognition

• Pattern Classification Machine Learning

• Computer Vision

Thesis Topic

Tilte : "Some Studies on Performance Improvement of Frequency Domain Correlation Technique for Face Recognition"

Highlights

• Nonlinear correlation filtering in class specific subspace approach

• Design of PSO optimized preferential correlation filter

• Regression network based trained preprocessing for MUMACE filter

• Extending 3D correlation filter in single face detection and recognition from video

Selected Publications

1. Pradipta K. Banerjee and Asit K. Datta, Class specific subspace dependent nonlinear correlation filtering for illumination tolerant face recognition,Pattern Recognition Letters, Elsevier, 36,177-185,2013

2. Pradipta K. Banerjee and Asit K. Datta, Generalized regression neural network based preprocessing of frequency domain correlation filter for improved face recognition and its optical implementation, Optics and Laser Technology,Elsevier, 45, 217-227, 2013

3. Pradipta K. Banerjee and Asit K. Datta, A preferential digital-optical correlator optimized by particle swarm technique for multi class face recognition”, Optics and Laser Technology, Elsevier, 50, 33-42, 2013

4. Pradipta K. Banerjee, Asit K. Datta, ”An illumination tolerant class specific 2D subspace based face recognition technique using optimum correlation filter”, Optik , Elsevier 124(17), 3173-3179, 2013

5. Pradipta K. Banerjee, Jayanta K. Chandra, Asit K. Datta, ”Face detection and eye localization in video by 3D unconstrained filter and neural network”, A. Abraham et al. (Eds. ) : ACC 2011, Part II , CCIS 191, pp.480 489, 2011.Springer-Verlag Berlin Heidelberg , 2011, India

6. Research Gate..    google scholar citations

Demonstration videos

In thesis work an unconstrained 3D video correlation filter is developed which is further used to localize a talking face (without audio) in a video scene