An image-based children age range verification and classification based on facial features angle distribution and face shape elliptical ratio
Verifying children are much easier than verifying adults, based on physical and body appearances. However it would be rather difficult to verify children’s age referring only to their face properties. Therefore, this research presents an image-based method to classify children from adult and to veri...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Scientific Publishers
2017
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/60821/ http://psasir.upm.edu.my/id/eprint/60821/1/An%20image-based%20children%20age%20range%20verification%20and%20classification%20based%20on%20facial%20features%20angle%20distribution%20and%20face%20shape%20elliptical%20ratio.pdf |
| _version_ | 1848854282490609664 |
|---|---|
| author | Razalli, Husniza Rahmat, Rahmita Wirza O. K Khalid, Fatimah Sulaiman, Puteri Suhaiza |
| author_facet | Razalli, Husniza Rahmat, Rahmita Wirza O. K Khalid, Fatimah Sulaiman, Puteri Suhaiza |
| author_sort | Razalli, Husniza |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | Verifying children are much easier than verifying adults, based on physical and body appearances. However it would be rather difficult to verify children’s age referring only to their face properties. Therefore, this research presents an image-based method to classify children from adult and to verify children’s age range. The method consists of two main stages; the process to distinguish children from adult based on input facial image and the process to verify children age range. The classification and verification algorithm was based on face shape elliptical ratio and facial features angle distribution. The angle that forms on human face images has been calculated based on selected facial features landmark points. The method was tested on FG-NET aging database. The classification of children from adults and the verification of children age range are implemented using SVM and Multi-SVM classification process. The results show an accuracy of classifying children from adults which are 92% more accurate than previous works. |
| first_indexed | 2025-11-15T11:07:23Z |
| format | Article |
| id | upm-60821 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T11:07:23Z |
| publishDate | 2017 |
| publisher | American Scientific Publishers |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-608212019-03-26T09:20:21Z http://psasir.upm.edu.my/id/eprint/60821/ An image-based children age range verification and classification based on facial features angle distribution and face shape elliptical ratio Razalli, Husniza Rahmat, Rahmita Wirza O. K Khalid, Fatimah Sulaiman, Puteri Suhaiza Verifying children are much easier than verifying adults, based on physical and body appearances. However it would be rather difficult to verify children’s age referring only to their face properties. Therefore, this research presents an image-based method to classify children from adult and to verify children’s age range. The method consists of two main stages; the process to distinguish children from adult based on input facial image and the process to verify children age range. The classification and verification algorithm was based on face shape elliptical ratio and facial features angle distribution. The angle that forms on human face images has been calculated based on selected facial features landmark points. The method was tested on FG-NET aging database. The classification of children from adults and the verification of children age range are implemented using SVM and Multi-SVM classification process. The results show an accuracy of classifying children from adults which are 92% more accurate than previous works. American Scientific Publishers 2017 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/60821/1/An%20image-based%20children%20age%20range%20verification%20and%20classification%20based%20on%20facial%20features%20angle%20distribution%20and%20face%20shape%20elliptical%20ratio.pdf Razalli, Husniza and Rahmat, Rahmita Wirza O. K and Khalid, Fatimah and Sulaiman, Puteri Suhaiza (2017) An image-based children age range verification and classification based on facial features angle distribution and face shape elliptical ratio. Advanced Science Letters, 23 (5). 4026 - 4030. ISSN 1936-6612; ESSN: 1936-7317 https://www.ingentaconnect.com/content/asp/asl/2017/00000023/00000005/art00046 10.1166/asl.2017.8271 |
| spellingShingle | Razalli, Husniza Rahmat, Rahmita Wirza O. K Khalid, Fatimah Sulaiman, Puteri Suhaiza An image-based children age range verification and classification based on facial features angle distribution and face shape elliptical ratio |
| title | An image-based children age range verification and classification based on facial features angle distribution and face shape elliptical ratio |
| title_full | An image-based children age range verification and classification based on facial features angle distribution and face shape elliptical ratio |
| title_fullStr | An image-based children age range verification and classification based on facial features angle distribution and face shape elliptical ratio |
| title_full_unstemmed | An image-based children age range verification and classification based on facial features angle distribution and face shape elliptical ratio |
| title_short | An image-based children age range verification and classification based on facial features angle distribution and face shape elliptical ratio |
| title_sort | image-based children age range verification and classification based on facial features angle distribution and face shape elliptical ratio |
| url | http://psasir.upm.edu.my/id/eprint/60821/ http://psasir.upm.edu.my/id/eprint/60821/ http://psasir.upm.edu.my/id/eprint/60821/ http://psasir.upm.edu.my/id/eprint/60821/1/An%20image-based%20children%20age%20range%20verification%20and%20classification%20based%20on%20facial%20features%20angle%20distribution%20and%20face%20shape%20elliptical%20ratio.pdf |