摘要
为解决人脸检测实时性问题,提出了基于DSP实现人脸检测算法。改进了AdaBoost人脸检测算法,在层次型AdaBoost检测算法的基础上,改进了特征定义方式,提出模糊层次型人脸检测器结构。介绍了TI公司的DSP芯片及其外围电路,描述了系统中各个模块的工作流程。最后,阐述了利用CCS对DSP程序进行优化。实验结果表明,在输入图像大小为256×256像素的条件下,检测速度达到每秒26帧,误检率只有0.9%,实现了实时人脸检测的要求。
To solve the technical problem of real-time face detection, DSP is used to implement the algorithm of face detection. The AdaBoost algorithm of human face detection is optimized, A novel feature definition is proposed and an improved cascade-structured classifier which is called fuzzy cascade classifier is presented, The DSP chip of TI Company and its periphery circuit are introduced. The whole procedure of the detecting system is described, Finally, the DSP program is optimized using the CCS, The detecting speed reaches 26 films per second with 256×256 pixels image input, The error rate is only 0,9%, The real-time face detection is implemented.
出处
《计算机工程与设计》
CSCD
北大核心
2008年第14期3654-3656,共3页
Computer Engineering and Design
关键词
人脸检测
硬件处理
层次型分类器
视频采集
算法优化
face detection
hardware processing
cascade-structured classifier
video acquisition
algorithm optimization
