Age group classification via face images
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 identi...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2011
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/44371 |
| _version_ | 1826130612798357504 |
|---|---|
| author | Lee, Lai Soon. |
| author2 | Teoh Eam Khwang |
| author_facet | Teoh Eam Khwang Lee, Lai Soon. |
| author_sort | Lee, Lai Soon. |
| collection | NTU |
| description | 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. |
| first_indexed | 2024-10-01T07:59:10Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/44371 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:59:10Z |
| publishDate | 2011 |
| record_format | dspace |
| spelling | ntu-10356/443712023-07-07T16:10:36Z Age group classification via face images Lee, Lai Soon. Teoh Eam Khwang School of Electrical and Electronic Engineering DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision 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. Bachelor of Engineering 2011-06-01T03:55:01Z 2011-06-01T03:55:01Z 2011 2011 Final Year Project (FYP) http://hdl.handle.net/10356/44371 en Nanyang Technological University 97 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Lee, Lai Soon. Age group classification via face images |
| title | Age group classification via face images |
| title_full | Age group classification via face images |
| title_fullStr | Age group classification via face images |
| title_full_unstemmed | Age group classification via face images |
| title_short | Age group classification via face images |
| title_sort | age group classification via face images |
| topic | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision |
| url | http://hdl.handle.net/10356/44371 |
| work_keys_str_mv | AT leelaisoon agegroupclassificationviafaceimages |