1000-9825/2005/16(11)1894
2005 Journal of Software 软 件 学 报
Vol.16, No.11
基于遗传算法重采样的人脸样本扩张
陈 杰 1+, 陈熙霖 1,2, 高 文 1,2
1 2
(哈尔滨工业大学 计算机学院,黑龙江 哈尔滨
150001) 100080)
(中国科学院 计算技术研究所 ICT-ISVISION 面像识别联合实验室,北京
Face Samples Expanding Based on the GA Re-Sampling
CHEN Jie1+,
1 2
CHEN Xi-Lin1,2,
GAO Wen1,2
(School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China) (ICT-ISVISION Joint R&D Laboratory for Face Recognition, Institute of Computing Technology, The Chinese Academy of Sciences, Beijing 100080, China)
+ Corresponding author: Phn: +86-10-58858300, Fax: +86-10-58858301, E-mail: chenjie@jdl.ac.cn, http://www.jdl.ac.cn
Received 2004-04-29; Accepted 2004-12-08 Chen J, Chen XL, Gao W. Face samples expanding based on the GA re-sampling. Journal of Software, 2005,16(11):18941901. DOI: 10.1360/jos161894 Abstract: Data collection for both training and testing a classifier is a tedious but essential step towards face
detection and recognition. All of the statistical methods suffer from this problem. In this paper, a genetic algorithm (GA) based method to swell face database through re-sampling from existing faces is presented. The basic idea is that a face is composed of a limited components set, and the GA can simulate the procedure of heredity. This simulation can also cover the variations of faces in different lighting conditions, poses, accessories, and quality conditions. To verify the generalization capability of the proposed method, the expanded database is used to train an AdaBoost-based face detector and test it on the MIT+CMU frontal face test set. The experimental results show that the data collection can be speeded up efficiently by the proposed methods. Key words: 摘 要: face detection; genetic algorithm; SnoW (sparse network of winnow); AdaBoost
无论是对人脸检测还是人脸识别来说,训练或测试一个分类器都要进行数据的收集,目前所有基于统计
学习的方法都存在这个问题.提出了一种针对已有的人脸样本通过采用遗传算法进行重采样来扩张样本的算法.其 基本思想是,基于人脸样本由有限的部件构成,而且遗传算法可以用于模拟自然界中的遗传过程.这种模拟可以涵盖 人脸的一些变化,比如不同的光照,姿态,饰物,图片质量等.为了证明该算法所生成样本的推广能力,将这些生成

下一页