基于神经网络集成的旋转人脸快速检测系统

吉林大学学报(工学版) ›› 2013, Vol. 43 ›› Issue (增刊1): 424-429.

基于神经网络集成的旋转人脸快速检测系统

吴清佳

中山大学新华学院信息科学系,广州 510520

收稿日期:2012-06-05 发布日期:2013-06-01
作者简介:吴清佳(1974-),男,讲师.研究方向:人工智能.E-mail:012021179@fudan.edu.cn
基金资助:
广东省中山大学新华学院计算机网络重点课程建设基金资助项目(中新学科[2011]1号).

Rotation invariant face detection system based on neural network ensemble

WU Qing-jia

Department of Information Science, Xinhua College, Sun Yat-sen University, Guangzhou 510520, China

Received:2012-06-05 Published:2013-06-01

摘要/Abstract

摘要：

提出了一个基于神经网络集成的旋转人脸检测系统,与其它类似系统只能检测正面直立的人脸不同,本系统用于检测在图像平面内任何旋转角度的人脸。首先用"预处理"网络处理每个输入窗口,以确定窗口中是否含有人脸及其旋转角度,其输出结果再经一个或多个"检测"网络窗口处理。对两种类型的网络都提出了相应的训练方法,对各个网络进行敏感度分析,并做了大量实验。实验结果表明,本系统在准确率和检测速度方面均有较好表现,特别是检测速度大大高于单个网络的系统。

关键词: 旋转人脸检测, 神经网络集成, 预处理网络, 网络窗口

Abstract:

A neural network-based face detection system was proposed.Unlike similar systems which were limited to detecting upright frontal faces,faces were detected at any degree of rotation in the image plane.Multiple networks were employed;a "router" network first processed each input window to determine its orientation and then used this information to prepare the window for one or more "detector" networks.The training methods for both types of networks were presented.Sensitivity analysis on the networks were performed and empirical results were presented on a large test set.Finally,preliminary results were presented for detecting faces rotated out of the image plane, such as profiles and semi-profiles. Experimental results show that this system has better performance in accuracy and detection speed,and it is faster than a single network system.

Key words: rotation face detection, neural network ensemble, router network, network window

中图分类号:

TP391.41

吴清佳. 基于神经网络集成的旋转人脸快速检测系统[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 424-429.

WU Qing-jia. Rotation invariant face detection system based on neural network ensemble[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 424-429.

参考文献

[1] Rowley H A,Baluja S.Neural network-based face detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(1):67-88.

[2] Colmenarez A J,Huang T S.Face detection with information-based maximum discrimination[C]//In Computer Vision and Pattern Recognition,1997:782-787.

[3] Hafed Z M,Levine M D.Face recognition using the discrete cosine transform[J].International Journal of Computer Vision,2001,43(3):167-188.

[4] Park H,Park C H.A comparison of generalized linear discriminant analysis algorithm[J].Pattern Recognition,2008,41(3):1083-1097.

[5] Vetter T,Jones M J.A boots trapping algorithm for learning linear models of object classes[C]//In Computer Vision and Pattern Recognition,1997:40-46.

[6] Sung K-K.Learning and example selection for object and pattern detection.Massachusetts:MIT AI Lab,1996.

[7] Zhang M,Fulcher J.Face recognition using artificial neural network group-based adaptive tolerance (GAT)trees[J].IEEE Transactions on Neural Networks,1996,7(3):555-567.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed