Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/44371
Title: Age group classification via face images
Authors: Lee, Lai Soon.
Keywords: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Issue Date: 2011
Abstract: Derived from rapid advances in computer graphics and machine vision, computer-based age estimation by faces verification has become an interesting topic due to their greatly increasing real-world applications, such as forensic art, biometrics, entertainment, and cosmetology. Age estimation is identifying a face image that is in the age group (year range) of the individual face. Both problem of particularity and difficulties pose challenges to computer based application system designers. This project focuses on age estimation technique using face verification to extract fusion of Gabor and Linear Binary Pattern features is used together with classifier. FG-Net and Morph are used as the training and testing data base. Web image mining is used to further increase the data base. The student implemented histogram is implemented to enhance the accuracy of the age group classification program. Adaboost were used as a classifier to provide a accurate age estimation method and error-correcting output codes (ECOC) methods is used to change the current four age class into two which is 1 and -1. The accuracy result of different features was investigated further. The comparison was based on the accuracy of verifications and the time taken for each simulation. Matlab Computing Language is chosen for training features for the program. C++ programming language is used for age estimation simulations in this project due to its user friendliness and its accuracy to give a reliable age verification results.
URI: http://hdl.handle.net/10356/44371
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 SizeFormat 
EA4123-101.pdf
  Restricted Access
19.02 MBAdobe PDFView/Open

Page view(s) 50

212
checked on Sep 25, 2020

Download(s) 50

13
checked on Sep 25, 2020

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.