Towards automatic landmarking on 2.5D face range images

In this paper, we propose an algorithm to automatically landmark points on 2.5-dimensional (2.5D) face images. We applied the Scale-invariant Feature Transform (SIFT) method to a new automatic landmarking method. Automatic landmarking has a number of added advantages over manual landmarking and...

Full description

Bibliographic Details
Main Authors: Pui, Suk Ting, Jacey-Lynn, Minoi
Format: Proceeding
Language:English
Published: 2013
Subjects:
Online Access:http://ir.unimas.my/id/eprint/10168/
http://ir.unimas.my/id/eprint/10168/1/Towards%20Automatic%20Landmarking%20on%202.5D%20Face%20Range%20Images%20%28abstract%29.pdf
_version_ 1848836721105436672
author Pui, Suk Ting
Jacey-Lynn, Minoi
author_facet Pui, Suk Ting
Jacey-Lynn, Minoi
author_sort Pui, Suk Ting
building UNIMAS Institutional Repository
collection Online Access
description In this paper, we propose an algorithm to automatically landmark points on 2.5-dimensional (2.5D) face images. We applied the Scale-invariant Feature Transform (SIFT) method to a new automatic landmarking method. Automatic landmarking has a number of added advantages over manual landmarking and it is more accurate and less time consuming especially if the dataset is large. We developed an interactive Graphical User Interface (GUI) tool to ease the visualization of the extract face features, which are scale and transformation invariant. The threshold values are then analyzed and generalized to best detect and extract important keypoints or/and regions of facial features. The results of the automatic extracted keypoint features are shown in this paper.
first_indexed 2025-11-15T06:28:16Z
format Proceeding
id unimas-10168
institution Universiti Malaysia Sarawak
institution_category Local University
language English
last_indexed 2025-11-15T06:28:16Z
publishDate 2013
recordtype eprints
repository_type Digital Repository
spelling unimas-101682022-09-15T03:51:06Z http://ir.unimas.my/id/eprint/10168/ Towards automatic landmarking on 2.5D face range images Pui, Suk Ting Jacey-Lynn, Minoi T Technology (General) In this paper, we propose an algorithm to automatically landmark points on 2.5-dimensional (2.5D) face images. We applied the Scale-invariant Feature Transform (SIFT) method to a new automatic landmarking method. Automatic landmarking has a number of added advantages over manual landmarking and it is more accurate and less time consuming especially if the dataset is large. We developed an interactive Graphical User Interface (GUI) tool to ease the visualization of the extract face features, which are scale and transformation invariant. The threshold values are then analyzed and generalized to best detect and extract important keypoints or/and regions of facial features. The results of the automatic extracted keypoint features are shown in this paper. 2013 Proceeding NonPeerReviewed text en http://ir.unimas.my/id/eprint/10168/1/Towards%20Automatic%20Landmarking%20on%202.5D%20Face%20Range%20Images%20%28abstract%29.pdf Pui, Suk Ting and Jacey-Lynn, Minoi (2013) Towards automatic landmarking on 2.5D face range images. In: 8th International Conference on Information Technology in Asia (CITA), 2013, 1-4 July 2013, Kota Samarahan. http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6637553
spellingShingle T Technology (General)
Pui, Suk Ting
Jacey-Lynn, Minoi
Towards automatic landmarking on 2.5D face range images
title Towards automatic landmarking on 2.5D face range images
title_full Towards automatic landmarking on 2.5D face range images
title_fullStr Towards automatic landmarking on 2.5D face range images
title_full_unstemmed Towards automatic landmarking on 2.5D face range images
title_short Towards automatic landmarking on 2.5D face range images
title_sort towards automatic landmarking on 2.5d face range images
topic T Technology (General)
url http://ir.unimas.my/id/eprint/10168/
http://ir.unimas.my/id/eprint/10168/
http://ir.unimas.my/id/eprint/10168/1/Towards%20Automatic%20Landmarking%20on%202.5D%20Face%20Range%20Images%20%28abstract%29.pdf