基于图像处理的机织物密度的高精度识别

High-precision identification of woven fabric density via image processing

通过对机织物图像和扫描仪精度的探讨,选择用扫描仪垂直扫描得到高分辨率的机织物表面反射图像,并提出采用特定的图像尺寸对织物图像进行处理。利用纱线间隙定位法对织物图像进行纠偏预处理。在处理后织物图像的亮度投影曲线中,通过区域排查的方法确定纱线间隙的位置。再对纱线间隙的距离依次检查,得到纱线间隙距离的准确平均值,最终得到织物的密度。实验证明,所得结果最高误差为0.07%,准确度较高。

By discussing the fabric image and the precision of the scanner in the article, the scanner is used to get high resolution fabric image by scanning in the vertical direction. A specific image size is put forward to analyze the fabric image. The skew of the complete fabric image has been correctly rectified by locating the yarn clearances. The brightness information and the projection curve of the reflect image from the fabric surface are used to confirm the position of the yarn clearances in the processed image. The accurate average distance of the yarn clearance is acquired by checking the distance of the yarn clearances in turn, and then the density of the fabric is calculated from the distance. High reliability of the technique is proved by experiments with a relative error of 0.07 %