Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/49331
Title: | Face recognition using morphable models | Authors: | Gopalakrishnan, Sai Aparajitha. | Keywords: | DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics | Issue Date: | 2012 | Abstract: | Face recognition is an integral part of many modern applications, one of which is geriatric care. Singapore, in particular, is experiencing a steady rise in the number of elderly, soaring healthcare costs and high requirement for around-the-clock service for the aging population. Robotic systems which can interact saliently with the elderly might be the solution. Such robots need to be able to accurately detect the identity and the expression of the person so that they can respond to his/her needs. The objective of this project, in a bid to move forward affordable robotic healthcare, is to develop a facial recognition system that can detect identity and expression. Faces are flexible objects exhibiting variation in pose, illumination, identity and expression. Due to this special property, identity and expression recognition are serious problems in computer vision. Most methods present in the field today treat faces as rigid objects, and thus fail to solve the problem of recognition. In this project, an alternative approach called morphable model is used which treats the face as a flexible entity. It can henceforth absorb all the variances in face images, while accurately detecting identity and expression. | URI: | http://hdl.handle.net/10356/49331 | Schools: | School of Electrical and Electronic Engineering | Rights: | Nanyang Technological University | Fulltext Permission: | restricted | Fulltext Availability: | With Fulltext |
Appears in Collections: | EEE Student Reports (FYP/IA/PA/PI) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
eA4026-111.pdf Restricted Access | FYP report | 5.07 MB | Adobe PDF | View/Open |
Page view(s)
354
Updated on Mar 27, 2024
Download(s)
9
Updated on Mar 27, 2024
Google ScholarTM
Check
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.