基于小波重构的皮革表面检测方法

Leather surface inspection using automatic selection band for wavelet reconstruction

纹理表面的瑕疵检测是机器视觉的一个重要研究课题,已经广泛用于各种产品表面质量控制。本文主要研究皮革制造业中皮革纹理表面的检测,并提出了一种有效的选取小波频带重建图像的纹理瑕疵检测方法。该方法首先应用小波基函数在较优的分解级数上对纹理图像进行分解,然后在最佳的分辨率级数上正确的选取平滑图像或者细节图像来重建图像。在重建图像中均匀纹理图案被有效的移除,仅仅保留了局部瑕疵区域,小波频带选取是基于小波系数的能量分布自动确定最佳重构参数。实验表明,该方法有效,可用于实时在线检测。

Defects detection for texture surface is one of the important research problems in machine vision,and can be widely used in surface quality control of different products.This paper is focused on the analysis of leather surface inspection to manufacturing industries.A defect detection approach for texture image,which uses an efficient image restoration scheme in wavelet domain,is presented.First,the texture image is decomposed by using wavelet base function in terms of the optimum decomposition levels,and then the restoration image can be reconstructed by properly selecting the smooth subimage or the detail subimages at best resolution levels.The homogeneous texture pattern can be effectively removed and only local defects are preserved in the restored image.A subband selection procedure is developed to automatically determine the best reconstruction parameters based on the energy distribution of wavelet coefficients.Experiments demonstrate the validity of the method,and show the potential possibility of real-time processing in an on-line leather surface inspection.