Defect identification in magnetic tile images using an improved nonlinear diffusion method

Abstract

Visual inspection of surface defects is a crucial step in the magnetic tile manufacturing process. Magnetic tile images suffer from a non-uniform illumination, texture and noise that disperse irregularly in flawless image areas. As a result, common edge detection and threshold segmentation techniques fail to identify these kinds of defects. In this work, we present a robust algorithm for defect identification in magnetic tile images. The proposed method is based on a new anisotropic diffusion filtering model. Unlike traditional anisotropic diffusion models that take into account only gradient magnitude information, the proposed model combines together gradient magnitude and a new local difference image feature. The aim is to remove bright shapes and undesirable artifacts in the faultless region in magnetic tile images. In addition, the method activates a smoothing process in the flawless region to homogenize the background and simultaneously a sharpening in the defect boundaries to highlight anomalies. Experimental results on a number of magnetic tiles samples containing different types of defects have demonstrated the efficiency of the proposed diffusion method.

A feature-based transfer-YOLOv5 model for rapid defect inspection in large mass magnetic tile manufacturing

“…To relieve human labor, a number of image processing techniques [2][3][4] have been proposed to automatically perform such inspection tasks and several machine vision systems have been built and applied in actual production process. Many previous defect inspection techniques are based on traditional computer vision algorithms 5,6 but techniques using deep learning algorithms have become predominant in recent years. 4,[7][8][9] End-to-end deep neural networks have achieved state-of-the-art performance on image classification and object detection tasks.…”

Detection of Surface Defects of Magnetic Tiles Based on Improved YOLOv5

“…Furthermore, the model integrates a novel focal loss function to deal with the problem of class imbalance. Ben Gharsallah and Ben Braiek [12] proposed a novel anisotropic diffusion filtering model. The model considers both gradient magnitude and local difference image feature, in contrast to conventional anisotropic diffusion models that only consider gradient magnitude data.…”

Classification of Magnetic Tile Surface Defects Based on Efficientnet Network with Attention

“…The efficiency of manual visual inspection is low, and the accuracy of detection and classification cannot be guaranteed, so it is important to improve the efficiency of defect recognition on the production line. In recent years, automatic recognition technology has been applied to the identification of magnetic tile defects [2]- [4], but there are also many problems. Due to the many types of magnetic tile defects, the complex surface texture and low contrast, it is difficult for traditional visual inspection and image processing technologies to detect the surface of the magnetic tile.…”