基于形态学的冷轧薄板板形识别

Cold-rolled Strip Pmate-profile Recognition Based on Morphology

为了解决冷轧薄板板形识别问题,采用基于形态学的图像处理方法。利用高帽变换对板形图像进行增强,对增强后的图像进行二值化,生成缺陷图像,消除二值缺陷图像中的干扰信号,分析二值缺陷图像,判定板形的类别。给出了基于二值形态学的图像消噪算法和基于灰度形态学的图像增强算法。提出了基于高帽变换的板形识别算法和基于对比思想的板形识别算法。根据上述方法进行了板形识别系统的硬件、软件设计,实际应用表明,该方法可以有效地识别出常见的板形。

A cold-rolled strip plate-profile recognition method was presented to improve the detection accuracy based on image morphology processing method. The original flatness stri Pimage were increased through top-hat transform. A binarization method was used to build images with defects, and flatness detecting through denoise and analyze the image with defects. An image denoising algorithm based on binary morphology and an image enhancement algorithm based on gray-level morphology associated with proper structuring elements is fulfilled. The flatness detecting algorithm based on top-hat transform and the flatness detecting algorithm based on comparison is put forward. The effectiveness of the proposed method was shown by the application in an iron steel plant, and the hardware and software system in this application were presented.