An optoelectronic automatic real-time human face recognition system, which includes a feature point extractor, a normalization algorithm, an encoding module, an optical recognizer based on hit/ miss transform and an incoherent correlator, and a postprocessing module is presented in this paper.
以计算机为控制中心，CCD摄像机实时获取待识别人脸图像后，由计算机做预处理工作，包括用灰度直方图均衡化做光照归一化，自动提取两个内眼角和嘴的中心三个参考点，利用仿射变换进行几何归一化并进行广义互补编码，以实现数学形态学击中击不中变换；编码图像送入基于非相干光相关器的光学处理器做光学运算；最后对光学识别结果进行判决，从图像库中找出一个或几个与待识别目标相似的人脸图像。
Based on a hybrid opto electrical image processing system with an incoherent correlator, the image matching algorithm using optical Walsh transformation is realized successfully.
基于以非相干光相关器为核心的光电混合图像处理系统 ,实现了基于光学沃尔什变换特征提取的图像匹配算法。
In this paper, a multi channel optical target recognition approach based on morphological hit or miss transformation and incoherent correlator is presented.
本文以形态学击中击不中变换作为理论依据，以非相干光相关器作为光学实现硬件，推导了在非共轴相关条件下相关点位置的计算公式。