3D Face Registration on Simulated Annealing Algorithm
-
摘要: 基于模拟退火算法,利用深度信息对三维人脸进行匹配和识别。通过具有全局优化能力的模拟退火算法搜索获取全局极值,选择合适的适应度函数MLESAC和SIM控制匹配过程获得识别结果。基于“由粗到细”的思想,分3步匹配三维人脸,并对精准匹配阶段进行改进,通过选择合适的区域和分类器能够更好地应对表情的影响。实验结果表明,模拟退火算法跳出了局部最优解而获得了全局优化解,同时通过选择MLESAC和SIM作为不同匹配阶段的适应度函数能够有效控制匹配过程,提高了识别精准率。
-
[1] JU Sheng-gen, ZHOU Ji-liu, HE Kun, et al. Face recognition based on illumination normalization in frequency-domain[J]. Journal of University of Electronic Science and Technology of China, 2009, 38(6): 1021-1026. [2] 琚生根, 周激流, 何坤, 等. 频域光照归一化的人脸识别[J]. 电子科技大学学报, 2009, 38(6): 1021-1026. [3] WANG Yue-ming. Research on 3D face recognition across expression[D]. Hangzhou: Zhejiang University, 2007. [4] GUNLU G, BILGE H S. 3D face decomposition and region selection against expression variations[J]. Internation Conference on Pattern Recognition, 2010, 323: 2-3. [5] BRONSTEIN A M, BRONSTEIN M M, KIMMEL R. Expression invariant 3D face recognition[C]//Proc Int'l Conf Audio-and Video-Based Biometric Person Authentication. Berlin Heidelberg: Springer, 2003: 62-70. [6] LI Yong-an. 3D face recognition using geometric information[D]. Lanzhou: Lanzhou University, 2010. [7] HESHER C, SRIVASTAVA A, ERLEBACHER G. A novel technique for face recognition using range imaging[J]. Proc Int'l Symp Signal Processing and Its Applications. [S.l.]: IEEE, 2003: 201-204. [8] BERRETTI S. 3D face recognition using iso-geodesic stripes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(12): 4-10. [9] WANG Yue-ming, LIU Jian-zhuang. Robust 3D face recognition by local shape difference boosting[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(10): 7-9. [10] 王跃明. 表情不变的三维人脸识别[D]. 杭州: 浙江大学, 2007. [11] WANG Y, PAN G, WU Z. Exploring facial expression effects in 3D face recognition using partial ICP[C]//Proc Asian Conf Computer Vision. Berlin Heidelberg: Springer, 2006, 3851: 581-590. [12] GIVENS G, BEVERIDEG R, DRAPER B. A statistical assessment of subject factors in the PCA recognition of human faces[C]//Proceedings of the 2003 Conference on Computer Vision Pattern Recognition Workshop (CVPRW'03). [S.l.]: IEEE, 2003. [13] CHANG K I, BOWYER K W. Multiple nose region matching for 3D face recognition under varying facial expression[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(10): 3-5. [14] 李永安. 基于几何信息的三维人脸识别研究[D]. 兰州: 兰州大学, 2010。 [15] KIRKPATRICK S, GELATT C D, VECCHI M P. Optimization by simulated annealing science[J]. Science, 1983, 220(4598): 671-680. [16] TORR P, ZISSERMAN A. MLESAC: a new robust estimator with application to estimating image geometry[J]. Computer Vision and Image Understanding, 2000, 78: 138-156. [17] SILVA L, BELLON O R P, BOYER K L. Precision range image registration using a robust surface interpenetration measure and enhanced genetic algorithms[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(5): 2-10. [18] KITTLER J, HATEF M, DUIN R, et al. On combining classifiers[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(3): 226-239.
点击查看大图
计量
- 文章访问数: 5535
- HTML全文浏览量: 215
- PDF下载量: 146
- 被引次数: 0