作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程

• 人工智能及识别技术 • 上一篇    下一篇

基于图像引导滤波的人脸光照预处理算法

杨 军,张瑞峰,王小鹏,林岩龙   

  1. (兰州交通大学电子与信息工程学院,兰州 730070)
  • 收稿日期:2013-02-22 出版日期:2014-04-15 发布日期:2014-04-14
  • 作者简介:杨 军(1973-),男,副教授、博士,主研方向:虚拟现实,数字图像处理;张瑞峰,硕士研究生;王小鹏,教授;林岩龙,硕士研究生。
  • 基金资助:
    国家自然科学基金资助项目(61261029);甘肃省自然科学基金资助项目(1208RJZA243);陇原青年创新人才扶持计划基金资助项目(201182)。

Illumination Preprocessing Algorithm of Face Based on Image Guided Filtering

YANG Jun, ZHANG Rui-feng, WANG Xiao-peng, LIN Yan-long   

  1. (School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China)
  • Received:2013-02-22 Online:2014-04-15 Published:2014-04-14

摘要: 针对人脸识别中人脸图像光照预处理的问题,提出一种基于图像引导滤波的人脸光照预处理算法。根据自定义光照标准函数对引导图像和输入图像进行分类,经指数或对数非线性变换调整后进行直方图均衡化处理。采用图像引导滤波对图像细节进行增强,使变换后的图像更清晰。利用空域高通滤波来抑制局部锐化现象。在YaleB人脸数据库上进行验证,结果表明,该算法在识别性能上明显优于经典的主成分分析法,识别率可以提高2%~8%。

关键词: 人脸识别, 光照预处理, 图像引导滤波, 非线性变换, 直方图均衡化, 空域高通滤波

Abstract: Aiming at the problem of illumination preprocessing of face recognition. A new preprocessing algorithm for human face illumination is presented based on image guided filtering. Guided images and input images are classified by an illumination standard function, and Histogram Equalization(HE) is used to adjust images after they are processed by one of non-linear transformation algorithms, logarithm or exponential. Image guided filtering is applied to enhance image details in order to make the processed images clearer. A spatial domain high pass filter is adopted to restrain local sharpening phenomenon. A series of experiments are performed on the YaleB human face image database. Experimental results show that the proposed method is obviously superior to principal component analysis. The recognition rate can be improved by 2%~8% in comparison with other methods.

Key words: face recognition, illumination preprocessing, image guided filtering, nonlinear transformation, Histogram Equalization(HE), spatial-domain high pass filtering

中图分类号: