基于模糊逻辑的抗畸变光学模式识别

Distortion invariant Optical Pattern Recognition Based on the Fuzzy Logic

将多值击中击不中变换（ＭＶＨＭＴ）引入用于二值图像识别的联合变换相关器（ＪＴＣ）。ＭＶＨＭＴ对形态学击中击不中变换（ＨＭＴ）的性能进行了改善，基于模糊的概念，引入不确定点的定义，使得容易受到畸变干扰的点对判别结果的作用降低，从而在不损失图像信息的前提下，具有输入图像和参考模板之间进行精确匹配的能力，同时还提高了目标识别的抗畸变能力。利用新颖的多值互补编码方法，通过ＪＴＣ一步实现ＭＶＨＭＴ，相关后的图像通过取高阈值的分割方法来实现对目标的准确判断。

In this paper, multi value hit or miss transformation (MVHMT) is introduced into a joint transform correlator (JTC) for binary image recognition. Considering fuzzy concepts are lost MVHMT improves the ability of the ordinary morphological hit or miss transformation (HMT) because it reduces the decision effect of the pixels that is easily disturbed by rotation and scalling distortion. Not only MVHMT can realize the precision recognition between two images because no information of the input images is lost, but also it has a better distortion invariant ability for scaling and rotation than the ordinary HMT. Using a novel multi value complementary encoding method, MVHMT is performed on a JTC in one step. With a high level thresholding value, the correct justification can be achieved from the correlated resultant image. The simulation results are given.