Human Facial Feature Point Detection is Based on Improved ASM Method

Abstract:

In view of the traditional Active Shape Model (ASM) method’s flaw and insufficiency, the paper proposed several improvements methods. The traditional ASM method carries on the characteristic search using of the initial point which provided using the person face examination；in the improvement algorithm, the paper has used the method of pupil orientation on the initialization and adopted improvement methods of edge restraint, auto-adapted length of stride to effectively improved the ASM method performance. The experimental result indicated that, the improvement ASM method has a bigger enhancement in the accuracy and robustness.

• Periodical: Advanced Materials Research (Volumes 181-182)
• Pages: 139-144
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.181-182.139
• Online since: January 2011
• Authors: Yan Peng Sun
• Keywords: ASM, Auto-Adapted Length of Stride, Edge Restraint, Face Recognition, Pupil Orientation

References

[1] T F Cootes, C J Taylor, D H Cooper, et al. Active Shape Models-their Training and Application [J]. Computer Vision and Image Understanding, 1995, 61(1): 38-59.

DOI: 10.1006/cviu.1995.1004

[2] T F Cootes, G J Edwards, C J Taylor. Active Appearance Models[ C]. Proc. of ECCV, 1998: 231-236.

[3] T F Cootes, K N Walker, C J Taylor. View-based Active Appearance Models[ C]. Proc. of ICFGR, 2000. 227-232.

[4] Ying Li, J H Lai, Pong C Yuen. Multi-template ASM method for feature points detection of facial image with diverse expressions[C]. The 7th FGR Southhampton, UK, (2006).

DOI: 10.1109/fgr.2006.81

[5] Chun Chen, Ming Zhao, Stan Z Li, et al. Parameter optimization for active shape models [C]. the 6th Asian Conf on Computer Vision, Jeju, Korea, (2004).