一种鲁棒的非均匀光场中SD卡形态识别算法

A Robust SD Card Shape Recognition Algorithm in Inhomogeneous Optical Field

为解决SD卡阵列图像光照不均匀的问题,提出了一种基于明场暗场区域分析的自适应阈值分割算法。算法首先通过改进大津法对SD卡灰度图像进行初次阈值分割,然后利用改进模板匹配算法完成定位,最终依据定位结果完成第2次阈值分割。为解决SD卡姿态多变的问题,提出了一种基于多特征融合的形态识别算法,完成对变化姿态目标的形态识别。试验结果表明,SD卡形态识别准确率大于99.9%,工作节拍小于300ms。算法具备良好的鲁棒性,能够满足工业现场要求。

To solve the problem of uneven illumination in SD card array images,an adaptive threshold segmentation algorithm based on region analysis of bright and dark fields was proposed. Firstly,the improved Otsu method is used to segment the gray image of SD card for the first time,then the improved template matching algorithm is used to complete the location,and finally the second threshold segmentation is completed according to the location results. In order to solve the problem of attitude variability of SD card,a morphological recognition algorithm based on multi-feature fusion is proposed to complete the morphological recognition of changing attitude target. The experimental results show that the accuracy of shape recognition of SD card is more than 99.9%,and the working rhythm is less than 300 ms. The algorithm has good robustness and can meet the requirements of industrial field.