OMAP-L138与OV2460的人脸识别系统
|
摘要
人脸识别技术是一项新兴的生物识别技术,在门禁考勤系统、出入监管系统,智能家居系统中都有广泛的应用。针对手持式嵌入式设备中的低功耗、高性能要求,提出以基于OMAP-L138的异构双核处理器为核心,以200万像素的OV2640摄像头为采集前端的人脸识别平台,基于TI公司SysLink双核通信组件,满足识别的精度与速度的要求。实验采取多组对比试验的方法,通过优化人脸识别算法中的比率,从而达到较高的准确度。
Face recognition technology is an emerging biometrics technology,which has been widely used in the entrance guard system,the access control system,the intelligent home system and so on.In order to meet the requirements of low-power consumption and performance in the handheld embedded devices,the face recognition platform is proposed,which takes the OMAP-L138-based heterogeneous dual-core processor as the core and the OV2640 camera as the acquisition front-end.The TI SysLink dual-core communication components takes into account the recognition of the accuracy and speed requirements.In order to improve the accuracy of the face recognition algorithm,a series of contrast experiments are adopted.
Face recognition technology is an emerging biometrics technology,which has been widely used in the entrance guard system,the access control system,the intelligent home system and so on.In order to meet the requirements of low-power consumption and performance in the handheld embedded devices,the face recognition platform is proposed,which takes the OMAP-L138-based heterogeneous dual-core processor as the core and the OV2640 camera as the acquisition front-end.The TI SysLink dual-core communication components takes into account the recognition of the accuracy and speed requirements.In order to improve the accuracy of the face recognition algorithm,a series of contrast experiments are adopted.
引文
[1]Ban Y,Kim S K,Kim S,et al.Face detection based on skin color likelihood[J].Pattern Recognition,2014,47(4):1573-1585.
[2]Paul Viola,Michael J Jones.Robust Real-Time Face Detection[J].International Journal of Computer Vision,2004,57(2):137-154.
[3]严超,王元庆.基于连续型Adaboost算法和Cascade结构的红外人脸检测[J].激光与红外,2009,39(11):1246-1250.
[4]TI.OMAP-L138 C6000 DSP+ARM Processor Technical Reference Manual(Rev.A),2014.
[5]OmniVision.OV2640_DS,OmniVision Advanced Information Preliminary Datasheet,Version 1.6February 28,2006.
[6]DU C,Hong Z H U,LUO L,et al.Face detection in video based on AdaBoost algorithm and skin model[J].The Journal of China Universities of Posts and Telecommunications,2013(20):6-24.
[7]Yang M,Crenshaw J,Augustine B,et al.AdaBoost-based face detection for embedded systems[J].Computer Vision and Image Understanding,2010,114(11):1116-1125.
[8]武勃,黄畅,艾海舟,等.基于连续Adaboost算法的多视角人脸检测[J].计算机研究与发展,2005,42(9):1612-1621.
[2]Paul Viola,Michael J Jones.Robust Real-Time Face Detection[J].International Journal of Computer Vision,2004,57(2):137-154.
[3]严超,王元庆.基于连续型Adaboost算法和Cascade结构的红外人脸检测[J].激光与红外,2009,39(11):1246-1250.
[4]TI.OMAP-L138 C6000 DSP+ARM Processor Technical Reference Manual(Rev.A),2014.
[5]OmniVision.OV2640_DS,OmniVision Advanced Information Preliminary Datasheet,Version 1.6February 28,2006.
[6]DU C,Hong Z H U,LUO L,et al.Face detection in video based on AdaBoost algorithm and skin model[J].The Journal of China Universities of Posts and Telecommunications,2013(20):6-24.
[7]Yang M,Crenshaw J,Augustine B,et al.AdaBoost-based face detection for embedded systems[J].Computer Vision and Image Understanding,2010,114(11):1116-1125.
[8]武勃,黄畅,艾海舟,等.基于连续Adaboost算法的多视角人脸检测[J].计算机研究与发展,2005,42(9):1612-1621.