[1]师亚亭,李卫军,宁欣,等.基于嘴巴状态约束的人脸特征点定位算法[J].智能系统学报,2016,11(5):578-585.[doi:10.11992/tis.201602006]
SHI Yating,LI Weijun,NING Xin,et al.A facial feature point locating algorithmbased on mouth-state constraints[J].CAAI Transactions on Intelligent Systems,2016,11(5):578-585.[doi:10.11992/tis.201602006]
点击复制
SHI Yating,LI Weijun,NING Xin,et al.A facial feature point locating algorithmbased on mouth-state constraints[J].CAAI Transactions on Intelligent Systems,2016,11(5):578-585.[doi:10.11992/tis.201602006]
基于嘴巴状态约束的人脸特征点定位算法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
11
期数:
2016年第5期
页码:
578-585
栏目:
学术论文—机器感知与模式识别
出版日期:
2016-11-01
- Title:
- A facial feature point locating algorithmbased on mouth-state constraints
- Keywords:
- facial feature points location; ESR; mouth-state classifier; strong shape constraint; HSV color space; convolutional neural network
- 分类号:
- TP183
- 摘要:
- 嘴巴区域特征点的精确定位对于特征匹配、表情分析、唇形识别、驾驶行为分析等应用具有极其关键的作用。然而，用现有的人脸特征点定位算法进行人脸形状估计时，嘴巴区域特征点的定位误差相对较大。针对这一问题，提出了基于HSV颜色空间和基于卷积神经网络的两种嘴巴状态分类器以及一种基于局部特征点位置关系的强形状约束策略，并在此基础上提出了基于嘴巴状态约束的人脸特征点定位算法，根据嘴巴状态标签对显式形状回归ESR算法的估计结果进行约束以获得更加准确的特征的位置。相比传统的ESR算法，该方法在保障人脸形状定位鲁棒性的同时，在Helen数据库和LFPW数据库上的嘴巴特征点定位准确度均明显提高。
- Abstract:
- The precise locations of the feature points of the mouth critically influence applications which use feature matching, expression analysis, lip recognition and driving behavior analysis, etc. However, when estimating facial shapes using current facial landmarks detecting methods, the locating error of feature points around the mouth region is relatively large. In order to solve this problem, two kinds of‘mouth-state’classifiers were proposed, one was based on HSV color space and the other on a convolutional neural network, with a strong shape constraint strategy focusing on the spatial relationship between local facial landmarks. Furthermore a facial feature point locating method was presented based on the mouth-state constraint, which constrains the predicted explicit shape regression (ESR) result and is more accurate as regards locating facial landmarks. Compared with the original ESR algorithm, this method significantly improves the accuracy of locating landmarks for the mouth for both the Helen and LFPW datasets, and has no impact on the robustness of facial shape prediction.
- 参考文献/References:
-
[1] COOTES T F, TAYLOR C J, COOPER D H, et al. Active shape models-their training and application[J]. Computer vision and image understanding, 1995, 61(1):38-59.
[2] COOTES T F, EDWARDS G J, TAYLOR C J. Active appearance models[M]//BURKHARDT H, NEUMANN B. Computer Vision-ECCV’98. Berlin Heidelberg:Springer, 1998:484-498.
[3] CAO Xudong, WEI Yichen, WEN Fang, et al. Face alignment by explicit shape regression[J]. International journal of computer vision, 2014, 107(2):177-190.
[4] REN Shaoqing, CAO Xudong, WEI Yichen, et al. Face alignment at 3000 FPS via regressing local binary features[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Columbus, OH, USA, 2014:1685-1692.
[5] BURGOS-ARTIZZU X P, PERONA P, DOLLáR P. Robust face landmark estimation under occlusion[C]//Proceedings of 2013 IEEE International Conference on Computer Vision (ICCV). Sydney, VIC, 2013:1513-1520.
[6] DOLLáR P, WELINDER P, PERONA P. Cascaded pose regression[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. San Francisco, CA, USA, 2010:1078-1085.
[7] CRISTINACCE D, COOTES T F. Boosted regression active shape models[C]//Proceedings of the British Machine Vision Conference 2007. Warwick, UK, 2007:2.
[8] SAUER P, COOTES T F, TAYLOR C J. Accurate regression procedures for active appearance models[C]//Proceedings of the British Machine Vision Conference 2011. Dundee, 2011:681-685.
[9] 李英, 赖剑煌, 阮邦志. 多模板ASM方法及其在人脸特征点检测中的应用[J]. 计算机研究与发展, 2007, 44(1):133-140.LI Ying, LAI Jianhuang, YUEN Pongchi. Multi-template ASM and its application in facial feature points detection[J]. Journal of computer research and development, 2007, 44(1):133-140.
[10] ZENG A, BODDETI V N, KITANI K M, et al. Face alignment refinement[C]//Proceedings of 2015 IEEE Winter Conference on Applications of Computer Vision. Waikoloa, HI, USA, 2015:162-169.
[11] 徐国庆. 低分辨图像眼睛精确定位方法[J]. 计算机应用研究, 2015, 32(11):3501-3503, 3512.XU Guoqing. Precise eye location in low resolution image[J]. Application research of computers, 2015, 32(11):3501-3503, 3512.
[12] 雷林华, 朱虹, 涂善彬, 等. 一种人脸网格模型的特征区域细节调整方法[J]. 计算机工程与应用, 2006, 44(16):194-196.LEI Linhua, ZHU Hong, TU Shanbin, et al. Adaptation method to adjust characteristic region of facial wire frame model in detail[J]. Computer engineering and applications, 2006, 44(16):194-196.
[13] 张国权, 李战明, 李向伟, 等. HSV空间中彩色图像分割研究[J]. 计算机工程与应用, 2010, 46(26):179-181.ZHANG Guoquan, LI Zhanming, LI Xiangwei, et al. Research on color image segmentation in HSV space[J]. Computer engineering and applications, 2010, 46(26):179-181.
[14] ANDROUTSOS D, PLATANIOTIS K N, VENETSANOPOULOS A N. A novel vector-based approach to color image retrieval using a vector angular-based distance measure[J]. Computer vision and image understanding, 1999, 75(1/2):46-58.
[15] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.
[16] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]//Advances in Neural Information Processing Systems 25:26th Annual Conference on Neural Information Processing Systems. Lake Tahoe, Nevada, USA, 2012:1097-1105.
备注/Memo
收稿日期:2016-02-06。
基金项目:国家自然科学基金项目（61572458）.
作者简介:师亚亭,女,1991年生,硕士研究生,主要研究方向为机器视觉。参与国家自然科学基金项目1项,企业合作项目1项;李卫军,男,1975年生,研究员,博士生导师,主要研究方向为机器视觉、模式识别与智能系统、高维计算、近红外定性分析技术。主持国家自然科学基金项目2项,企业合作研究项目3项,发表学术论文30余篇。
通讯作者:李卫军.E-mail:wjli@semi.ac.cn
更新日期/Last Update:
1900-01-01