Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/204946
Title: | Human Activity Recognition Using Gabor Filter with Hidden Markov Model |
Researcher: | Rajeev Shrivastava |
Guide(s): | Shachi Awasthi |
University: | Jayoti Vidyapeeth Women s University |
Completed Date: | |
Abstract: | Human action recognition is one of the most important emerging trend/ newlinetechnology. It has wide application such as surveillance (behavior analysis), security newline(pedestrian detection), control (human-computer interfaces), content based video newlineretrieval, etc. There are many methods of human action recognition. The human newlineaction recognition problem is made difficult by the great variability in body part newlinerotation and tilt, lighting intensity and angle, body part movement, aging, partial newlineocclusion (e.g. Wearing Hats, scarves, glasses etc.), etc. Principal components from newlinethe body parts space are used for human action recognition to reduce dimensionality. newlineA multi scale representation human action recognition is done to preserve the newlinediscriminate information prior to dimensionality reduction. newlineHuman Activity Recognition system is a mechanism of identifying various newlineHuman Activity against some stored pattern Human Activity. This project is a newlineHuman Activity Recognition system for identification of person. It takes input an newlineimage of a person and searches for a match in the stored images. If there is match, newlinethe user can see the result as the Human Activity matched or not matched. User newlineCan not make any kind of change in the stored image files, i.e. a user is not newlineauthorized to add or delete images from the storage data. The administrator of the newlinesystem has authentication to make updates in the storage data. newlineI present a biometrics system performing identification, of automatic Human newlineActivity recognition. This system is based on Gabor features extraction using Gabor newlinefilter. For feature extraction the input image is convolve with Gabor filter and extra newlinepersonal sample generation algorithm is used to select a set of informative and newlinenonredundant Gabor features. I used HMM (Hidden Markov Models) for matching newlinethe input Human Activity mage to the stored images. newlineThe purpose of this research is to develop a novel, accurate and efficient newlineHuman Activity verification system. In this dissertation the system developed uses newlinethe hidden Markov model ( |
Pagination: | |
URI: | http://hdl.handle.net/10603/204946 |
Appears in Departments: | Department of Electrical Electronics and Communication Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
abbreviations.pdf | Attached File | 59.45 kB | Adobe PDF | View/Open |
abstract.pdf | 61.62 kB | Adobe PDF | View/Open | |
acknowledgement.pdf | 101.44 kB | Adobe PDF | View/Open | |
appendix.pdf | 1.12 MB | Adobe PDF | View/Open | |
bibliography.pdf | 254.54 kB | Adobe PDF | View/Open | |
certificate.pdf | 145.96 kB | Adobe PDF | View/Open | |
chap 1.pdf | 366.23 kB | Adobe PDF | View/Open | |
chap 2.pdf | 596.95 kB | Adobe PDF | View/Open | |
chap 3.pdf | 932.29 kB | Adobe PDF | View/Open | |
chap 4.pdf | 1.72 MB | Adobe PDF | View/Open | |
chap 5.pdf | 101.38 kB | Adobe PDF | View/Open | |
contents.pdf | 111.67 kB | Adobe PDF | View/Open | |
symbols.pdf | 176.98 kB | Adobe PDF | View/Open | |
title page.pdf | 318.81 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: