摘要
系统采用S3C6410芯片作为硬件开发平台,Linux操作系统作为软件开发平台,图像的采集使用OV7640搭配OV511的结构实现,采用VIDEO4LINUX的方法实现视频处理、目标检测和识别程序,完成了准确并快速识别人脸的功能;并对所涉及浮点算法进行了适当优化,较大地提高了嵌入式ARM芯片上视频处理的性能。通过使用基于隐马尔可夫模型(HMM)的方法,优化了面部检测和人脸识别的过程。
The system uses S3C6410 processor as the hardware developing platform and the Linux Operation System as the software platform. The image acquisition is realized by the structure of OV7640 plus OVSll, the VIDEO4LINUX is used to realizes the video processing, goal detecting and identifying procedure so as to accurately and quickly fulfill the function of face identification. The float image-pretreatment algorithm is optimized in the article and highly improves the image-pretreatment implementation for ARM11 micro- processor. This new design is suitable for the face detection and recognition, thus makes an important step towards low-cost and porta- ble systems. The Hidden Markov Model based on this method predigests the process of face detection and recognition.
出处
《山西电子技术》
2012年第6期92-94,共3页
Shanxi Electronic Technology
