基于肤色学习的多人脸前景抽取方法

doi:10.11772/j.issn.1001-9081.2020091397

计算机应用 ›› 2021, Vol. 41 ›› Issue (6): 1659-1666.DOI: 10.11772/j.issn.1001-9081.2020091397

所属专题：人工智能

基于肤色学习的多人脸前景抽取方法

戴嫣然¹, 戴国庆¹, 袁玉波^1,2

1. 华东理工大学信息科学与工程学院, 上海 200237;
2. 上海大数据与互联网受众工程技术研究中心, 上海 200072

收稿日期:2020-09-09 修回日期:2020-12-09 出版日期:2021-06-10 发布日期:2020-12-18
通讯作者: 戴嫣然
作者简介:戴嫣然(1996-),女,福建厦门人,硕士研究生,主要研究方向:数据分析、机器视觉;戴国庆(1996-),男,山东即墨人,硕士研究生,主要研究方向:机器视觉、深度学习;袁玉波(1976-),男,云南宣威人,副教授,博士,主要研究方向:机器学习、数据科学、数据质量评估、数据挖掘。
基金资助:
上海市工程技术中心项目（18DZ2252300）。

Multi-face foreground extraction method based on skin color learning

DAI Yanran¹, DAI Guoqing¹, YUAN Yubo^1,2

1. School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China;
2. Shanghai Engineering Research Center of Big Data and Internet Audience, Shanghai 200072, China

Received:2020-09-09 Revised:2020-12-09 Online:2021-06-10 Published:2020-12-18
Supported by:
This work is partially supported by the Program of Shanghai Engineering Technology Center (18DZ2252300).

摘要/Abstract

摘要： 针对多人脸场景下快速准确提取人脸内容的问题，提出了基于肤色学习的多人脸前景抽取方法。首先，给出了基于肤色学习的肤色前景分割模型。根据肤色专家的论文结果，采集了著名的SPA数据库的1 200张人脸进行肤色抽样，建立学习模型以得到每个人种在颜色空间的肤色参数，据此进行肤色图像分割，得到肤色前景。其次，利用人脸特征点学习算法，以常见人脸68个特征点为目标，结合肤色前景信息分割出人脸种子区域；并计算人脸中心点，来构建人脸椭圆边界模型以及确定遗传范围。最后，建立了有效抽取算法，在人脸椭圆边界内利用遗传机制进行人脸再生，从而抽取得到有效人脸区域。以三类不同数据库为基础，收集了100张有代表性的多人脸图像，实验结果表明所提方法对这些图像的多人脸抽取的结果准确率达到98.4%以上，且该方法对中密度人群的人脸内容抽取有显著效果，并为人脸识别算法的准确性和可用性提供了基础。

关键词: 人脸前景, 肤色学习, 聚类分析, 人脸范围, 遗传机制

Abstract: To solve the problem of quickly and accurately extracting face content in multi-face scenes, a multi-face foreground extraction method based on skin color learning was proposed. Firstly, a skin color foreground segmentation model based on skin color learning was given. According to the results of the papers of skin color experts, 1 200 faces of the famous SPA database were collected for skin color sampling. The learning model was established to obtain the skin color parameters of each race in the color space. The skin color image was segmented according to the parameters to obtain the skin color foreground. Secondly, the face seed area was segmented by using face feature point learning algorithm and skin color foreground information and with 68 common feature points of the face as the target. And the centers of the faces were calculated to construct the elliptical boundary model of the faces and determine the genetic range. Finally, an effective extraction algorithm was established, and the genetic mechanism was used within the elliptical boundaries of the faces to regenerate the faces, so that the effective face areas were extracted. Based on three different databases, 100 representative multi-face images were collected. Experimental results show that the accuracy of the multi-face extraction results of the proposed method is up to 98.4%, and the proposed method has a significant effect on the face content extraction of medium-density crowds as well as provides a basis for the accuracy and usability of the face recognition algorithm.

Key words: face foreground, skin color learning, clustering analysis, face range, genetic mechanism

中图分类号:

TP391.41

戴嫣然, 戴国庆, 袁玉波. 基于肤色学习的多人脸前景抽取方法[J]. 计算机应用, 2021, 41(6): 1659-1666.

DAI Yanran, DAI Guoqing, YUAN Yubo. Multi-face foreground extraction method based on skin color learning[J]. Journal of Computer Applications, 2021, 41(6): 1659-1666.

参考文献

[1] VIOLA P,JONES M. Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2001:I-511-I-518.
[2] NAJI S,JALAB H A,KAREEM S A. A survey on skin detection in colored images[J]. Artificial Intelligence Review,2019,52(2):1041-1087.
[3] HSU R L,ABDEL-MOTTALEB M,JAIN A K. Face detection in color images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):696-706.
[4] SHAIK K B,GANESAN P,KALIST V,et al. Comparative study of skin color detection and segmentation in HSV and YCbCr color space[J]. Procedia Computer Science,2015,57:41-48.
[5] PUJOL F A,PUJOL M,JIMENO-MORENILLA A,et al. Face detection based on skin color segmentation using fuzzy entropy[J]. Entropy,2017,19(1):Article No. 26.
[6] BENCHERIET C. New face features to detect multiple faces in complex background[J]. Evolving Systems,2019,10(2):79-95.
[7] BRUNELLI R, POGGIO T. Face recognition:features versus templates[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1993,15(10):1042-1052.
[8] JIN Z,LOU Z,YANG J,et al. Face detection using template matching and skin-color information[J]. Neurocomputing,2007, 70(4/5/6):794-800.
[9] 胡祖奎, 余建桥, 梁爽. 一种基于分层模板的人脸检测方法[J]. 西南师范大学学报(自然科学版), 2017, 42(6):112-120.(HU Z K,YU J Q,LIANG S. On a face detection method based on layered face template[J]. Journal of Southwest China Normal University (Natural Science Edition),2007,42(6):112-120.)
[10] LUO Y,GUAN Y. Adaptive skin detection using face location and facial structure estimation[J]. IET Computer Vision,2017,11(7):550-559.
[11] WANG Y,HE H. Multi-race face detection based on skin color and eyes[C]//Proceedings of the 2010 International Conference on Machine Learning and Cybernetics. Piscataway:IEEE,2010:659-663.
[12] TAN W R, CHAN C S, YOGARAJAH P, et al. A fusion approach for efficient human skin detection[J]. IEEE Transactions on Industrial Informatics,2012,8(1):138-147.
[13] KLEVAN K,HANAFI M,RAMLI A. Optimal combination of color components for skin detection[C]//Proceedings of the 2014 4th International Conference on Artificial Intelligence with Applications in Engineering and Technology. Piscataway:IEEE, 2014:171-176.
[14] HAO Z,LIU Y,QIN H,et al. Scale-aware face detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2017:1913-1922.
[15] HU P,RAMANAN D. Finding tiny faces[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2017:1522-1530.
[16] LI J,WANG Y,WANG C,et al. DSFD:dual shot face detector[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2019:5055-5064.
[17] 魏嘉旺, 王肖, 袁玉波. 人脸特征点定位的自适应窗回归方法[J]. 计算机应用, 2019, 39(5):1459-1465.(WEI J W,WANG X,YUAN Y B. Adaptive window regression method for face feature point positioning[J]. Journal of Computer Applications, 2019,39(5):1459-1465.)
[18] 陈凯星, 刘赟, 王金海, 等. 基于遗传机制和高斯变差的自动前景提取方法[J]. 计算机应用, 2017, 37(11):3231-3237.(CHEN K X,LIU Y,WANG J H,et al. Foreground extraction with genetic mechanism and difference of Gaussian[J]. Journal of Computer Applications,2017,37(11):3231-3237.)
[19] YOGARAJAH P,CONDELL J,CURRAN K,et al. A dynamic threshold approach for skin segmentation in color images[C]//Proceedings of the 2010 IEEE International Conference on Image Processing. Piscataway:IEEE,2010:2225-2228.
[20] YUAN Y,LIU Y,DAI G,et al. Automatic foreground extraction based on difference of Gaussian[J]. The Scientific World Journal,2014,2014:Article No. 29074.
[21] JIDA S,AKSASSE B,OUANAN M. Face segmentation and detection using Voronoi diagram and 2D histogram[C]//Proceedings of the 2017 International Conference on Intelligent Systems and Computer Vision. Piscataway:IEEE,2017:1-5.

基于肤色学习的多人脸前景抽取方法

Multi-face foreground extraction method based on skin color learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	郭佳, 韩李涛, 孙宪龙, 周丽娟. 自动确定聚类中心的比较密度峰值聚类算法[J]. 计算机应用, 2021, 41(3): 738-744.
[2]	任帅, 徐振超, 王震, 贺媛, 张弢, 苏东旭, 慕德俊. 基于多融合态的低密度三维模型信息隐藏算法[J]. 计算机应用, 2019, 39(4): 1100-1105.
[3]	孙石磊, 王超, 赵元棣. 基于轮廓系数的参数无关空中交通轨迹聚类方法[J]. 计算机应用, 2019, 39(11): 3293-3297.
[4]	陆明炽, 王守华, 李云柯, 纪元法, 孙希延, 邓桂辉. 基于特征匹配和距离加权的蓝牙定位算法[J]. 计算机应用, 2018, 38(8): 2359-2364.
[5]	任帅, 张弢, 徐振超, 王震, 贺媛, 柳雨农. 特征点标注与聚类的三维模型信息隐藏算法[J]. 计算机应用, 2018, 38(4): 1017-1022.
[6]	李晔, 陈奕延, 张淑芬. 基于密度峰值的混合型数据聚类算法设计[J]. 计算机应用, 2018, 38(2): 483-490.
[7]	徐晓伟, 杜一, 周园春. 基于多源出行数据的居民行为模式分析方法[J]. 计算机应用, 2017, 37(8): 2362-2367.
[8]	梁双, 周丽华, 杨培忠. 基于聚类分析分库策略的社交网络数据库查询性能与数据迁移[J]. 计算机应用, 2017, 37(3): 673-679.
[9]	金亮, 于炯, 杨兴耀, 鲁亮, 王跃飞, 国冰磊, 廖彬. 基于聚类层次模型的视频推荐算法[J]. 计算机应用, 2017, 37(10): 2828-2833.
[10]	谢洪安, 李栋, 苏旸, 杨凯. 基于聚类分析的可信网络管理模型[J]. 计算机应用, 2016, 36(9): 2447-2451.
[11]	王少华, 狄岚, 梁久祯. 基于核与局部信息的多维度模糊聚类图像分割算法[J]. 计算机应用, 2015, 35(11): 3227-3231.
[12]	曹永春蔡正琦邵亚斌. 基于K-means的改进人工蜂群聚类算法[J]. 计算机应用, 2014, 34(1): 204-207.
[13]	侯荣涛路郁王琴袁程胜王军. OPTICS算法在雷电临近预报中的应用[J]. 计算机应用, 2014, 34(1): 297-301.
[14]	杜军乐夏良华齐伟伟豆建斌. 面向健康管理的复杂装备维修模糊聚类[J]. 计算机应用, 2012, 32(07): 2053-2055.
[15]	徐翔斌王佳强涂欢穆明. 基于改进RFM模型的电子商务客户细分[J]. 计算机应用, 2012, 32(05): 1439-1442.