[1]董林鹭,赵良军 *,杨明中,等.一种基于 Viola-Jones 的改进人脸定位算法[J].计算机技术与发展,2020,30(10):42-46.[doi:10. 3969 / j. issn. 1673-629X. 2020. 10. 008]
　DONG Lin-lu,ZHAO Liang-jun *,YANG Ming-zhong,et al.An Improved Face Location Algorithm Based on Viola-Jones[J].,2020,30(10):42-46.[doi:10. 3969 / j. issn. 1673-629X. 2020. 10. 008]
点击复制

一种基于 Viola-Jones 的改进人脸定位算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
30
期数:
2020年10期
页码:
42-46
栏目:
智能、算法、系统工程
出版日期:
2020-10-10

文章信息/Info

Title:
An Improved Face Location Algorithm Based on Viola-Jones
文章编号:
1673-629X(2020)10-0042-05
作者:
董林鹭1; 赵良军2 *; 杨明中1; 林国军1; 石小仕1; 何 岚2
1. 四川轻化工大学 自动化与信息工程学院 人工智能四川省重点实验室,四川 自贡 643000; 2. 四川轻化工大学 企业信息化与物联网测控技术四川省高校重点实验室,四川 自贡 643000
Author(s):
DONG Lin-lu1; ZHAO Liang-jun2 *; YANG Ming-zhong1; LIN Guo-jun1; SHI Xiao-shi1; HE Lan2
1. Key Laboratory of Artificial Intelligence of Sichuan Province,School of Automation and Information Engineering,Sichuan University of Science and Engineering,Zigong 643000,China; 2. Key Laboratory of Higher Education of Sichuan Province for Enterprise Informatization and Internet of Things, Sichuan University of Science and Engineering,Zigong 643000,China
关键词:
人脸检测; Viola-Jones 算法; 肤色定位; 任意旋转角度; 形态学; 肤色模型
Keywords:
face detection; Viola-Jones algorithm; skin color location; arbitrary rotation angle; morphology; skin color model
分类号:
TP391. 41
DOI:
10. 3969 / j. issn. 1673-629X. 2020. 10. 008
摘要:
Viola-Jones 算法能快速定位人脸,但该算法存在对有偏角的人脸出现漏检和对周围环境非人脸区域出现误检的情况。 针对该问题,提出一种基于 Viola-Jones 的改进人脸定位算法。 首先将图像中检测到的人脸像素区域排除, 再对剩下未被检测出的区域转为 YCrCr 模式, 设定阈值排除大部分环境中非肤色像素的干扰初步筛选出候选人脸区域,再利用形态学方法进一步排除身体其他部位肤色的干扰和环境中近似人脸像素的背景色干扰并对筛选出的区域进行左角度矫正调整和右角度矫正调整,重新检测,准确定位出人脸位置。 通过在标准人脸检测库 Faces、IMM 和 AFW 上进行实验,结果表明,该算法能有效提高人脸定位的准确性,较原算法在 Faces 测试库中正确检测率提高 5% ,在 AFW 测试库中正确检测率提高 9%。
Abstract:
The Viola-Jones algorithm can quickly locate human face ,but the algorithm fails to detect faces with deflection angle and fails to detect non-face areas in the surrounding environment. In view of this problem,an improved face positioning algorithm based on ViolaJones is proposed. Firstly,the area of face pixels detected in the image is excluded,and then the remaining undetected area is converted to YCrCr mode. The threshold is set to exclude interference of non-skin pixels in most environments to preliminarily screen out the candidate face area. Then the morphological method is used to further eliminate the interference of skin color in other parts of the body and the background color interference of similar face pixels in the environment,and the left angle correction adjustment and right angle correction adjustment are carried out for the selected areas,so as to re-detect and accurately locate the face position. The experiment on Faces,IMM and AFW shows that the proposed algorithm can effectively improve the accuracy of the face location, and the correct detection rate in Faces test library and AFW test library is increased by 5% and 9% respectively compared with the original algorithm.

相似文献/References:

[1]李宏伟 陶亮.复杂背景不同光照条件下彩色图像中人脸检测[J].计算机技术与发展,2009,(02):52.
　LI Hong-wei,TAO Liang.Face Detection in Complicated Backgrounds and Different Illumination Conditions of Color Images[J].,2009,(10):52.
[2]俞扬信 严云洋.视频序列中的人脸检测与定位算法研究[J].计算机技术与发展,2009,(02):109.
　YU Yang-xin,YAN Yun-yang.Algorithm Study of Face Detection and Location in Video Sequence[J].,2009,(10):109.
[3]金燕 陶亮.基于人眼定位的人脸检测与归一化算法[J].计算机技术与发展,2009,(04):95.
　JIN Yan,TAO Liang.Face Detection and Normalization Based on Localization of Human Eyes[J].,2009,(10):95.
[4]佘九华 王敬东 李鹏.基于Camshift的人脸跟踪算法[J].计算机技术与发展,2008,(09):12.
　SHE Jiu-hua,WANG Jing-dong,LI Peng.Face Tracking Algorithm Based on Camshift[J].,2008,(10):12.
[5]李启娟 李金屏.基于轮廓信息的人脸检测[J].计算机技术与发展,2008,(09):108.
　LI Qi-juan,LI Jin-ping.Face Detection Based on Contour Information[J].,2008,(10):108.
[6]陈伟琦 梁一川 易强 秦文虎.基于肤色和Adaboost算法的人脸检测研究[J].计算机技术与发展,2008,(12):44.
　CHEN Wei-qi,LIANG Yi-chuan,YI Qiang,et al.Face Detection Based on Skin Color and Adaboost Arithmetic[J].,2008,(10):44.
[7]贾灵芝 李岚 钱坤喜.基于自适应光线补偿的人脸检测算法[J].计算机技术与发展,2008,(12):120.
　JIA Ling-zhi,LI Lan,QIAN Kun-xi.Face Detection Algorithm Based on Self- adaptive Light Compensation[J].,2008,(10):120.
[8]袁芬萍 季桂树.基于SVM的三阶段人脸检测方法的研究与应用[J].计算机技术与发展,2007,(09):133.
　YUAN Fen-ping,JI Gui-shu.Research and Application about Three- Stage Face Detection Method Based on SVM[J].,2007,(10):133.
[9]王晶 杨煜.基于边缘方向直方图的Adaboost人脸检测[J].计算机技术与发展,2007,(12):5.
　WANG Jing,YANG Yu.Adaboost for Face Detection Based on Edge Orientation Histograms[J].,2007,(10):5.
[10]邵平 杨路明 曾耀荣.计算旋转Harr型特征的积分图像算法改进[J].计算机技术与发展,2006,(11):146.
　SHAO Ping,YANG. Lu-ming,ZENG Yao-rong.An Improved Algorithm of Integral Image for Computing Rotated Harr- Like Features[J].,2006,(10):146.

更新日期/Last Update: 2020-10-10