《计算机应用研究》|Application Research of Computers

梯度-LBP优化深度图像分析的性别人脸识别

Depth image analysis optimized by gradient-LBP for gender face recognition

免费全文下载 (已被下载 次)  
获取PDF全文
作者 李晓丽,李小红
机构 1.南通大学 现代教育技术中心,江苏 南通 226000;2.武汉大学 计算机学院,武汉 430072
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2014)11-3502-04
DOI 10.3969/j.issn.1001-3695.2014.11.069
摘要 针对目前最先进的3DLBP人脸识别算法中仍存在特征长度大、编码不稳定等固有缺陷,提出了一种基于梯度LBP的深度图像分析算法。从各种不同方向视觉化LBP算子,计算相邻像素的深度差,产生多个有导向的深度差图像,串联合并各个深度差直方图信息,形成唯一有导向的深度差直方图。在Kinect和范围扫描仪数据库图像上的所有实验均证明了所提描述符优于3DLBP。此外,还加权合并所提描述符和灰度图像的LBPU2,在高质量3D范围扫描仪数据库图像(Texas 3DFR)和Kinect设备采集的低质量图像(EURECOM Kinect人脸数据库)上的总体平均识别率可高达96.70%。
关键词 性别人脸识别;局部二值模式;梯度-LBP;深度图像分析;加权合并
基金项目 国家自然科学基金资助项目(61171132)
南通大学自然科学基金资助项目(12Z057)
本文URL http://www.arocmag.com/article/01-2014-11-069.html
英文标题 Depth image analysis optimized by gradient-LBP for gender face recognition
作者英文名 LI Xiao-li, LI Xiao-hong
机构英文名 1. Modern Education Technology Center, Nantong University, Nantong Jiangsu 226000, China; 2. College of Computer Science, Wuhan University, Wuhan 430072, China
英文摘要 According to the present that many inherent defects such as characteristic length and coding instability exist in the most advanced 3DLBP face recognition algorithm, this paper proposed a depth image analysis optimized by gradient-LBP.Firstly, it visualized the LBP operator from different directions.Then, it calculated the adjacent pixels’ depth differences, which would produce multiple guided images of depth differences.Finally, it tandem combined histogram information of each depth difference, formed a unique oriented depth difference histogram.All experiments on the images of Kinect and range scanner image database prove that the proposed descriptor is better than 3DLBP.In addition, this paper also proposed the weighted combination of the proposed descriptor and gray image LBPU2.Recognition accuracy of proposed descriptor on the high quality 3D range image scanner database (Texas 3DFR) and the low quality images collected by Kinect (EURECOM Kinect face database) experiment equipments can achieve 96.70%.
英文关键词 gender face recognition; local binary pattern; gradient-LBP; depth differences; weighted combination
参考文献 查看稿件参考文献
  [1] 戴金波, 肖霄, 赵宏伟. 基于低分辨率局部二值模式的人脸识别[J] . 吉林大学学报:工学版, 2013, 21(2):435-438.
[2] 袁宝华, 王欢, 任明武. 基于完整LBP特征的人脸识别[J] . 计算机应用研究, 2012, 29(4):1557-1559.
[3] 刘伟锋, 李树娟, 王延江. 人脸表情的LBP特征分析[J] . 计算机工程与应用, 2011, 47(2):149-152.
[4] 张建明, 房芳, 陈立, 等. 基于优选LBP与加权 SVM 的年龄估计[J] . 计算机应用研究, 2010, 27(1):389-392.
[5] 赵海英, 杨一帆, 徐正光. 基于多角度LBP特征的三维人脸性别分类[J] . 自动化学报, 2012, 38(9):1544-1549.
[6] 王晓云, 苑玮琦, 郭金玉. 低分辨率人耳图像识别算法研究[J] . 计算机应用研究, 2010, 27(11):4329-4334.
[7] 叶长明, 蒋建国, 詹曙. 不同姿态人脸深度图识别的研究[J] . 电子测量与仪器学报, 2011, 25(10):870-878.
[8] 杨扬, 曹其新, 朱笑笑, 等. 面向机器人手眼协调抓取的3维建模算法[J] . 机器人, 2013, 35(2):151-155.
[9] SMISEK J, JANCOSEK M, PAJDLA T. 3D with Kinect[M] //Consumer Depth Cameras for Computer Vision. London:Springer, 2013:3-25.
[10] HUANG Yong-gang, WANG Yun-hong, TAN Tie-niu. Combining statistics of geometrical and correlative features for 3D face recognition[C] //Proc of the British Machine Vision Conference. 2006:879-888.
[11] CIOCCA G, CUSANO C, SCHETTINI R. Image orientation detection using LBP-based features and logistic regression[EB/OL] . 2013. http://www. ivl. disco. unimib. it/publications/pdf/ciocca 2013 imageorientation. pdf.
[12] GUO Zhen-hua, ZHANG Lei, ZHANG D. A completed modeling of local binary pattern operator for texture classification[J] . IEEE Trans on Image Processing, 2010, 19(6):1657-1663.
[13] LIAN Hui-cheng, LU Bao-liang. Multi-view gender classification using local binary patterns and support vector machines[M] //Advances in Neural Networks. Berlin:Springer, 2006:202-209.
[14] SANDBACH G, ZAFEIRIOU S, PANTIC M. Local normal binary patterns for 3D facial action unit detection[C] //Proc of the 19th IEEE International Conference on Image Processing. [S. l. ] :IEEE Press, 2012:1813-1816.
[15] ULLAH I, HUSSAIN M, ABOALSAMH H, et al. Gender recognition from face images with dyadic wavelet transform and local binary pattern[M] //Advances in Visual Computing. Berlin:Springer, 2012:409-419.
[16] SHAN Cai-feng. Learning local binary patterns for gender classification on real-world face images[J] . Pattern Recognition Letters, 2012, 33(4):431-437.
收稿日期 2013/11/5
修回日期 2013/12/28
页码 3502-3505,3513
中图分类号 TP391.41
文献标志码 A