基于有效能量的3D人脸鼻尖点检测与姿态矫正
|
摘要
为提高鼻尖点检测与姿态矫正的精度,结合有效能量判断曲面的凹凸性,提出一种三维人脸鼻尖点检测与姿态矫正算法。利用有效能量在预处理后的三维人脸图像上确定候选鼻尖点,并根据其均值和方差进行二次筛选,将候选点最密集的区域作为鼻尖区域,进一步得到鼻尖点。计算鼻尖点到三维人脸上其他点的测地距离后切割出有效的人脸区域,同时采用主成分分析法对其进行矫正,通过迭代最近点算法精确对齐后得到对齐误差。基于大量三维人脸数据的仿真结果表明,该算法的检测和矫正成功率分别达到98.8%和98.3%,运行耗时仅为1.489 8 s。
To improve the accuracy of the nasal tip point detection and posture correction,a three-dimensional human face nasal tip point detection and posture correction algorithm based on effective energy is proposed,which combines the judgment ability of effective energy for the surface concavity and convexity. Firstly,the nasal tip candidate points are determined by effective energy in the pre-processed 3 D face image,then the second screening is carried out according to the mean and variance of the effective energy. The densest region with the most intensive candidate points is selected as the nasal tip region to further obtain the tip of the nose. The effective face area is cut off after calculating the geodesic distance from the tip of the nasal to the other points on the three-dimensional human face,the principal component analysis is used to make correction for the cut face area,and the alignment error is obtained by precise alignment of the Iterative Closest Point( ICP) algorithm. The comparison experiment is simulated based on a large number of 3 D face data,and the results show that the nasal tip point detection and posture correction success rate of proposed algorithm respectively reach 8. 8% and 8. 3%,and the operation time is only 1. 489 8.
To improve the accuracy of the nasal tip point detection and posture correction,a three-dimensional human face nasal tip point detection and posture correction algorithm based on effective energy is proposed,which combines the judgment ability of effective energy for the surface concavity and convexity. Firstly,the nasal tip candidate points are determined by effective energy in the pre-processed 3 D face image,then the second screening is carried out according to the mean and variance of the effective energy. The densest region with the most intensive candidate points is selected as the nasal tip region to further obtain the tip of the nose. The effective face area is cut off after calculating the geodesic distance from the tip of the nasal to the other points on the three-dimensional human face,the principal component analysis is used to make correction for the cut face area,and the alignment error is obtained by precise alignment of the Iterative Closest Point( ICP) algorithm. The comparison experiment is simulated based on a large number of 3 D face data,and the results show that the nasal tip point detection and posture correction success rate of proposed algorithm respectively reach 8. 8% and 8. 3%,and the operation time is only 1. 489 8.
引文
[1]YANG M,ZHU P,LIU F,et al.Joint representation and pattern learning for robust face recognition[J].Neurocomputing,2015,168(C):70-80.
[2]SHARMA R,PATTERH M S.A new pose invariant face recognition system using PCA and ANFIS[J].Optik-International Journal for Light and Electron Optics,2015,126(23):3483-3487.
[3]程晓雅,王春红.基于特征化字典的低秩表示人脸识别[J].计算机应用,2016,36(12):3423-3428.
[4]徐俊,达飞鹏.一种基于局部描述符的三维人脸识别方法[J].模式识别与人工智能,2012,25(1):45-53.
[5]PENG W,XU C,FENG Z.3D face modeling based on structure optimization and surface reconstruction with B-Spline[J].Neurocomputing,2016,179(12):228-237.
[6]刘佳,傅卫平,王雯,等.基于改进SIFT算法的图像匹配[J].仪器仪表学报,2013,34(5):1107-1112.
[7]冯思宇,雷印杰,周新志.针对单样本人脸的三维部分人脸识别[J].计算机工程,2016,42(9):144-150.
[8]邹红艳,达飞鹏.基于轮廓线局部描述符的三维人脸识别[J].计算机应用研究,2013,30(5):1561-1563.
[9]魏明俊,许道云,徐梦珂.基于均方差度量分块的自动加权稀疏表示算法[J].计算机工程,2017,43(5):174-178.
[10]刘丹,童卫青.基于鼻子下轮廓线的鼻尖定位法[J].华东师范大学学报(自然科学版),2014(4):54-61.
[11]邓星,达飞鹏,杨乔生.基于自适应人脸切割的三维人脸识别算法[J].东南大学学报(自然科学版),2016,46(2):260-264.
[12]XU C,TAN T,WANG Y,et al.Combining local features for robust nose location in 3D facial data[J].Pattern Recognition Letters,2006,27(13):1487-1494.
[13]陈强,田杰,黄海宁,等.基于统计和纹理特征的SAS图像SVM分割研究[J].仪器仪表学报,2013,34(6):1413-1420.
[14]ZLATANOVIC'M,HINTERLEITNER I,NAJDANOVIC'M.Geodesic mapping onto Khlerian spaces of the first kind[J].Czechoslovak Mathematical Journal,2014,64(4):1113-1122.
[15]郭迪,周明全,王学松,等.基于测地距离三维模型瑕疵外观模拟[J].系统仿真学报,2014,26(9):1984-1987,1996.
[16]陈芙蓉,唐棣,王露晨,等.基于动态路径优化的人体姿态识别[J].计算机工程与设计,2016,37(10):2759-2763.
[17]朱立才,王汝传,杨浩,等.一种能量有效的RPL多路径数据分发机制[J].北京邮电大学学报,2016,39(6):82-87.
[18]甄岩,许稳,王汝言,等.间断连接无线网络中能量有效的数据转发策略[J].工程科学学报,2016,38(10):1489-1498.
[19]刘霁雨,龚敬,聂生东.利用测地线距离直方图分割血管粘连型肺结节的算法[J].计算机辅助设计与图形学学报,2017,29(3):493-500.
[20]范炯,朱志宇.基于MapInfo的Dijkstra最短路径算法研究[J].江苏科技大学学报(自然科学版),2017,31(1):79-83.
[21]张晓博,潘纲,任豪毅,等.实时三维人脸特征点定位[J].计算机辅助设计与图形学学报,2013,25(9):1325-1337.
[22]潘仁林,达飞鹏,邹红艳,等.基于面部曲线弹性匹配的三维人脸识别方法[J].图学学报,2014,35(3):358-367.
[2]SHARMA R,PATTERH M S.A new pose invariant face recognition system using PCA and ANFIS[J].Optik-International Journal for Light and Electron Optics,2015,126(23):3483-3487.
[3]程晓雅,王春红.基于特征化字典的低秩表示人脸识别[J].计算机应用,2016,36(12):3423-3428.
[4]徐俊,达飞鹏.一种基于局部描述符的三维人脸识别方法[J].模式识别与人工智能,2012,25(1):45-53.
[5]PENG W,XU C,FENG Z.3D face modeling based on structure optimization and surface reconstruction with B-Spline[J].Neurocomputing,2016,179(12):228-237.
[6]刘佳,傅卫平,王雯,等.基于改进SIFT算法的图像匹配[J].仪器仪表学报,2013,34(5):1107-1112.
[7]冯思宇,雷印杰,周新志.针对单样本人脸的三维部分人脸识别[J].计算机工程,2016,42(9):144-150.
[8]邹红艳,达飞鹏.基于轮廓线局部描述符的三维人脸识别[J].计算机应用研究,2013,30(5):1561-1563.
[9]魏明俊,许道云,徐梦珂.基于均方差度量分块的自动加权稀疏表示算法[J].计算机工程,2017,43(5):174-178.
[10]刘丹,童卫青.基于鼻子下轮廓线的鼻尖定位法[J].华东师范大学学报(自然科学版),2014(4):54-61.
[11]邓星,达飞鹏,杨乔生.基于自适应人脸切割的三维人脸识别算法[J].东南大学学报(自然科学版),2016,46(2):260-264.
[12]XU C,TAN T,WANG Y,et al.Combining local features for robust nose location in 3D facial data[J].Pattern Recognition Letters,2006,27(13):1487-1494.
[13]陈强,田杰,黄海宁,等.基于统计和纹理特征的SAS图像SVM分割研究[J].仪器仪表学报,2013,34(6):1413-1420.
[14]ZLATANOVIC'M,HINTERLEITNER I,NAJDANOVIC'M.Geodesic mapping onto Khlerian spaces of the first kind[J].Czechoslovak Mathematical Journal,2014,64(4):1113-1122.
[15]郭迪,周明全,王学松,等.基于测地距离三维模型瑕疵外观模拟[J].系统仿真学报,2014,26(9):1984-1987,1996.
[16]陈芙蓉,唐棣,王露晨,等.基于动态路径优化的人体姿态识别[J].计算机工程与设计,2016,37(10):2759-2763.
[17]朱立才,王汝传,杨浩,等.一种能量有效的RPL多路径数据分发机制[J].北京邮电大学学报,2016,39(6):82-87.
[18]甄岩,许稳,王汝言,等.间断连接无线网络中能量有效的数据转发策略[J].工程科学学报,2016,38(10):1489-1498.
[19]刘霁雨,龚敬,聂生东.利用测地线距离直方图分割血管粘连型肺结节的算法[J].计算机辅助设计与图形学学报,2017,29(3):493-500.
[20]范炯,朱志宇.基于MapInfo的Dijkstra最短路径算法研究[J].江苏科技大学学报(自然科学版),2017,31(1):79-83.
[21]张晓博,潘纲,任豪毅,等.实时三维人脸特征点定位[J].计算机辅助设计与图形学学报,2013,25(9):1325-1337.
[22]潘仁林,达飞鹏,邹红艳,等.基于面部曲线弹性匹配的三维人脸识别方法[J].图学学报,2014,35(3):358-367.