An Improved Active Shape Model Application onFacial Feature Localization

Full Text (PDF, 237KB), PP.1-9

Views: 0 Downloads: 0

Author(s)

Min.Wang 1,* Yi ling.Wen 1 Li.Fang 1 Wei ping.Sun 1

1. The School of Information and Control Engineering Xi’an University of Architecture & Technology Xi’an, China

* Corresponding author.

DOI: https://doi.org/10.5815/ijitcs.2010.01.01

Received: 1 Apr. 2010 / Revised: 23 Jun. 2010 / Accepted: 10 Sep. 2010 / Published: 8 Nov. 2010

Index Terms

Active shape model, facial feature localization, texture profile, texture model, multi-resolution pyramid

Abstract

An improved active shape model is proposed in this paper. The proposed algorithm includes the following four aspects. Firstly, this paper adopts a semi-automatic facial feature points marking tool. Secondly, this paper proposes to extract 2D gradient feature on the highest level and the higher level of multi-resolution pyramid images, and use Gabor wavelet transformation to extract the lowest level’s 2D texture feature. Thirdly, this paper adopts a new method of decomposition of multi-resolution pyramid. Pyramid images are got by wavelet transformation. Finally, this paper uses an improved searching scheme of multiresolution pyramid. The length of 2D profile searching rectangle is changed according to different pyramid levels. Experimental results demonstrate that the proposed algorithm exhibits better performance than the original ASM.

Cite This Paper

Min.Wang, Yi ling.Wen, Li.Fang, Wei ping.Sun, "An Improved Active Shape Model Application onFacial Feature Localization", International Journal of Information Technology and Computer Science(IJITCS), vol.2, no.1, pp.1-9, 2010. DOI: 10.5815/ijitcs.2010.01.01

Reference

[1] Kwok-Wai Wan, Kin-Man Lam,Kit-Chong Ng,”An accurate active shape model for facial feature extraction”, Pattern Recognition Letters ,vol.26,pp. 2409–2423,May 2005.

[2] Du Cheng,Su Guangda,Lin Xinggang ,”A modified muti-scale active shape model for face align”,Journal of Optoelectronics Laser,vol.15,pp. 706-709,June 2004.

[3] Fan Yuhua, Ma Jianwei,”ASM and its modified facial feature localization algorithm”, Journal of Computer-Aided Design & Computer Graphics, vol.19, pp.1411-1415, November 2007.

[4] Liu Aiping, Zhou Yan, Guan Xipu,”Improved ASM method of face localization”, Computer Engineer, vol.33, pp. 227-229. June 2007.

[5] Wang Liting,Ding Xiaoqing,Fang Chi,”A robust automatic facial feature localization method”,Acta Automation Sinica ,vol.35,pp.9-16, January 2009.

[6] T.F.Cootes, C.J.Taylor, D.H.Cooper, J.Graham, Active shape models-their training and application, Computer Vision and Image Understanding 61(1995)38–59.

[7] Yan Tong,YangWang,Zhiwei Zhu ,Qiang Ji,”Robust facial feature tracking under varying face pose and facial expression”, Pattern Recognition, vol.40,pp. 3195 – 3208,July 2007.

[8] Fu Yunshu, Fu Zhonghua, Zhang Yanning,”Facial feature extraction based on a modified active shape model”, Application Research Of Computers, vol.11, pp. 255-257, May 2006.

[9] Stephen Milborrow. Locating facial features with active shape models. Master paper of Faculty of Engineering, University of Cape Town, 2007.11.

[10] Jingmin Zhang , Zhijia Zhang, Dongshu Wang, “A pyramid rapid image matching algorithm based on wavelet decomposition”, Information Sciences,vol.17,pp. 1724–1730, January 2007.

[11] Zhonglong Zheng ,Jia Jiong ,Duanmu Chunjiang ,XinHong Liu ,Jie Yang,”Facial feature localization based on an improved active shape model”, Information Sciences,vol.17,pp. 2215–2223,August 2008.

[12] Andreas Koschan ,Sangkyu Kang, Joonki Paik ,Besma Abidi,Mongi Abidi,”Color active shape models for tracking non-rigid objects”,Pattern Recognition Letters ,vol.24,pp.1751-1765,August 2003.

[13] Van.Ginneken.B, Frangi, A.F, Staal, J.J.Active shape model segmentation with optimal features.IEEE Transactions on Medical Imaging, 2002, 21(8):924-933.

[14] Chengzhi Sun, Mei Xie.An enhanced active shape model for facial features extraction. The eleventh IEEE International Conference on Communication Technology, Nov, 2008,661-664.

[15] Shiguang Shan, Wen Gao, Wei Wang, Debin Zhao.Enhanced active shape models with global texture constraints for image analysis. The 14th International Symposium on Methodologies for Intelligent Systems, 2003, 593-597.

[16] Z.Zhao, E.K.Teoh, A new scheme for automated 3D PDM construction using deformable models, Image and Vision Computing 26(2) (2008)275–288.

[17] Stephen Milborrow and Fred Nicolls.Locating facial features with an extended active shape model. W www.milbo.users.sonic.net.

[18] Cootes, T.F., Taylor, C.J., 1992.Active shape models.In: Third British Machine Vision Conf., pp.266–275.

[19] Cootes,T.F.,Taylor,C.J.,Lanitis,A.,Cooper,D.H.,Graham,J.,1993.Building and using flexible models incorporating grey-level information.In:Fourth Internat.Conf.Computer Vision.pp.242–246.

[20] Cootes,T.F.,Hill,A.,Taylor,C.J.,Haslam,J.,1994.The use of active shape models for locating structures in medical images.Image Vision Comput.12(6),355–366.

[21] Froba, B., Kastner, T., Zink, W., Kublbeck, C., 2001.Real time active shape models for face segmentation.In:Internat.Conf.on Image Processing.pp.205–208.

[22] Ginneken,B.,Frangi,A.,Staal,J.,Romeny,B.,Viergever,M.,2001.A nonlinear gray-level appearance model improves active shape model segmentation.In:Proc.Mathematical Methods in Biomedical Image Analysis.pp.205–212.

[23] C.Davatzikos, X.Tao, D.Shen, Hierarchical active shape models, using the wavelet transform, IEEE Transactions on Medical Imaging 22(3) (2003)414–423.

[24] G.Hamarneh, T.Gustavsson, Deformable spatio temporal shape models: extending active shape models to 2D+time, Image and Vision Computing 22(2004)461–470.

[25] W.Wang,Shiguang Shan,Wen Gao,Bo Cao,An improved active shape model for face alignment,in:The Fourth International Conference on Multi-modal Interface,Pittsburgh,USA,2002,pp.523–528.

[26] S.C.Yan,C.Liu,S.Z.Li,H.J.Zhang,H.Y.Shum,Q.S.Cheng,Face alignment using texture-constrained active shape models, Image and Vision Computing 12(2003)69–75.

[27] M.Rogers, J.Graham, Robust active shape model search, Proceedingsof ECCV, vol.4, 2002, pp.517–530.

[28] S.Yan,X.Hou,S.Z.Li,H.Zhang,Q.Cheng,Face alignment using view-based direct appearance models, Special issue on facial image processing, analysis and synthesis,Int.J.Imaging Syst.Technol.13(1) (2003)106–112.

[29] Y.Tian,T.Kanade,J.F.Cohn,Evaluation of Gabor-wavelet-based facial action unit recognition in image sequences of increasing complexity, Proceedings of FGR02,2002,pp.218–223.

[30] F.Jiao,S.Z.Li,H.Y.Shum,D.Schuurmans,Face alignment using statistical models and wavelet features, Proceedings of CVPR03,vol.1, 2003,pp.321–327.