瓦纸线出口端纸板翘曲度视觉在线检测及分类

A Visual Online Detection and Classification of Cardboard Warping for the Corrugated Cardboard at the Outlet of Production Line

国内瓦纸线的出口端纸板翘曲检测主要依靠人工肉眼判断,检测精度和效率十分低下,国外检测设备造价昂贵且在中国市场的适应性较差。提出瓦纸线出口端纸板翘曲度视觉在线检测及分类方法,根据瓦楞纸板横截面图像的横截面纹理特征息,经过图像预处理、一元二次函数最小二乘拟合并计算翘曲度。收集各翘曲类型纸板图像建立纸板翘曲模板库,计算翘曲度范围并实现纸板翘曲分类。实验表明,提出的翘曲检测及分类方法可以准确、稳定的算出瓦楞纸板翘曲度并完成分类。该方法可为进一步实现基于机器视觉的瓦纸线出口纸板翘曲在线检测与分类奠定了基础。

The quality of corrugated cardboard at the export end of corrugated cardboard production line mainly relies on human eyes to judge in China.It has low detection accuracy and seriously affects the improvement of production efficiency.The advanced laser detection equipment is expensive,and and its adaptability in the domestic market needs to be improved furtherly.A visual detection and classification method of cardboard warping is proposed to identify the corrugated cardboard at the outlet of tile and paper production line.Image preprocessing method,warping classification method based on warping quantification and warping classification method based on deep learning,the cardboard warping detection can be realized at the outlet of tile and paper production line.It effectively improves the control efficiency of the tile paper production line.