Twelve anchor points detection by direct point calculation

Facial features can be categorized it into three approaches; Region Approaches, Anchor Point (landmark) Approaches and Contour Approaches. Generally, anchor points approach provide more accurate and consistent representation. For this reason, anchor points approach has been chose to utilize. Althoug...

Full description

Bibliographic Details
Main Authors: Khalid, Fatimah, Tengku Sembok, Tengku Mohd, Omar, Khairuddin
Format: Article
Language:English
Published: Universiti Utara Malaysia Press 2007
Online Access:http://psasir.upm.edu.my/id/eprint/34839/
http://psasir.upm.edu.my/id/eprint/34839/1/Twelve%20anchor%20points%20detection%20by%20direct%20point%20calculation.pdf
_version_ 1848847886015528960
author Khalid, Fatimah
Tengku Sembok, Tengku Mohd
Omar, Khairuddin
author_facet Khalid, Fatimah
Tengku Sembok, Tengku Mohd
Omar, Khairuddin
author_sort Khalid, Fatimah
building UPM Institutional Repository
collection Online Access
description Facial features can be categorized it into three approaches; Region Approaches, Anchor Point (landmark) Approaches and Contour Approaches. Generally, anchor points approach provide more accurate and consistent representation. For this reason, anchor points approach has been chose to utilize. Although, as the experiment data sets have become larger, algorithms have become more sophisticated even if the reported recognition rates are not as high as in some earlier works. This will cause a higher complexity and computer burden. Indirectly, it also will affect the time for real time face recognition systems. Here, it is proposed the approach of calculating the points directly from the text file to detect twelve anchor points ( nose tip, mouth centre, right eye centre, left eye centre, upper nose and chin). In order to get the anchor points, points for the nose tip have to be detected first. Then the upper nose and face point is localization. Lastly, the outer and inner eyes corner is localized. An experiment has been carried out with 420 models taken from GavabDB in two positions with frontal view and variation of expressions and positions. Our results are compared with three researchers that is similar to and show that better result is obtained with a median error of the eight points is around 5.53mm.
first_indexed 2025-11-15T09:25:43Z
format Article
id upm-34839
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T09:25:43Z
publishDate 2007
publisher Universiti Utara Malaysia Press
recordtype eprints
repository_type Digital Repository
spelling upm-348392016-10-10T04:19:47Z http://psasir.upm.edu.my/id/eprint/34839/ Twelve anchor points detection by direct point calculation Khalid, Fatimah Tengku Sembok, Tengku Mohd Omar, Khairuddin Facial features can be categorized it into three approaches; Region Approaches, Anchor Point (landmark) Approaches and Contour Approaches. Generally, anchor points approach provide more accurate and consistent representation. For this reason, anchor points approach has been chose to utilize. Although, as the experiment data sets have become larger, algorithms have become more sophisticated even if the reported recognition rates are not as high as in some earlier works. This will cause a higher complexity and computer burden. Indirectly, it also will affect the time for real time face recognition systems. Here, it is proposed the approach of calculating the points directly from the text file to detect twelve anchor points ( nose tip, mouth centre, right eye centre, left eye centre, upper nose and chin). In order to get the anchor points, points for the nose tip have to be detected first. Then the upper nose and face point is localization. Lastly, the outer and inner eyes corner is localized. An experiment has been carried out with 420 models taken from GavabDB in two positions with frontal view and variation of expressions and positions. Our results are compared with three researchers that is similar to and show that better result is obtained with a median error of the eight points is around 5.53mm. Universiti Utara Malaysia Press 2007 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/34839/1/Twelve%20anchor%20points%20detection%20by%20direct%20point%20calculation.pdf Khalid, Fatimah and Tengku Sembok, Tengku Mohd and Omar, Khairuddin (2007) Twelve anchor points detection by direct point calculation. Journal of Information and Communication Technology, 6. pp. 59-72. ISSN 1675-414X; ESSN: 2180-3862 http://www.jict.uum.edu.my/index.php/previous-issues/135-journal-of-information-and-communication-technology-jict-vol-6-2007
spellingShingle Khalid, Fatimah
Tengku Sembok, Tengku Mohd
Omar, Khairuddin
Twelve anchor points detection by direct point calculation
title Twelve anchor points detection by direct point calculation
title_full Twelve anchor points detection by direct point calculation
title_fullStr Twelve anchor points detection by direct point calculation
title_full_unstemmed Twelve anchor points detection by direct point calculation
title_short Twelve anchor points detection by direct point calculation
title_sort twelve anchor points detection by direct point calculation
url http://psasir.upm.edu.my/id/eprint/34839/
http://psasir.upm.edu.my/id/eprint/34839/
http://psasir.upm.edu.my/id/eprint/34839/1/Twelve%20anchor%20points%20detection%20by%20direct%20point%20calculation.pdf