Exploring Neural Networks for Gesture Recognition.

Date of Submission

December 2017

Date of Award

Winter 12-12-2018

Institute Name (Publisher)

Indian Statistical Institute

Document Type

Master's Dissertation

Degree Name

Master of Technology

Subject Name

Computer Science

Department

Computer Vision and Pattern Recognition Unit (CVPR-Kolkata)

Supervisor

Garain, Utpal (CVPR-Kolkata; ISI)

Abstract (Summary of the Work)

Gesture recognition is the task of recognizing human gestures from video data. In this report, we discuss the ChaLearn LAP Isolated Gesture Dataset and different methods used for gesture recognition from RGB-D videos. We also propose three new methods each involving neural networks in some capacity. The first method uses a pre-trained 3D ConvNet model for feature extraction. The second method uses spatio-temporal interest points and unsupervised learning followed by an LSTM network for prediction. The third method describes the generation of composite difference images that represent the video and then uses 2D ConvNets for prediction. We discuss merits and demerits of each method

Comments

ProQuest Collection ID: http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqm&rft_dat=xri:pqdiss:28843127

Control Number

ISI-DISS-2017-364

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

DOI

http://dspace.isical.ac.in:8080/jspui/handle/10263/6823

This document is currently not available here.

Share

COinS