Surface defect detection method for electronic panels based on attention mechanism and dual detection heads

Abstract

Automatic detection of surface defects in electronic panels is receiving increasing attention in the quality control of products. The surface defect detection of electronic panels is different from other target detection scenarios and is a meaningful and challenging problem. Its main manifestation is that surface defects of electronic panels usually exhibit extreme irregularity and small target characteristics, which bring great difficulties to the task of surface defect target detection including feature extraction and so on. The traditional methods can only detect a very small number of defect classes under specific detection conditions. And due to the weak robustness of these methods, they cannot be applied in real production scenarios on a large scale. Based on this, this paper applies the target detection technique under deep learning to the surface defect detection scenario of electronic panels for the first time. At the same time, in order to make the designed target detection network applicable to the electronic panel surface defect detection scenario and to enhance the interpretability of the designed target detection network in terms of computer mechanism. We design a deformable convolution module with a convolutional self-attentive module to learn the offset and a dual detection head incorporating the SE (Squeeze-and-Excitation) mechanism for the irregular characteristics of electronic panel surface defects and the small target characteristics, respectively. Finally, we carried out a series of experiments on our own electronic panel defect data set, including comparison with the most advanced target detection algorithms and a series of ablation experiments against our proposed method. The final experimental results prove that our method not only has better interpretability, but also has better metric performance, in which the map_0.5 metric reaches 78.257%, which is an increase of 13.506 percentage points over YOLOV5 and 33.457 percentage points higher than Retinanet. The results prove the proposed method is effective.

Color Mura Defect Detection Method Based on Channel Contrast Sensitivity Function Filtering

“…In this paper, the luminance CSF and color CSF parameters proposed in the ISO15739 standard [25] are used to filter the contrast maps, achieving background noise suppression and contrast enhancement. The formulae and parameters for the luminance and color of the CSF function are shown in Equations ( 7)- (9).…”

“…In the field of machine vision-based defect detection, extensive research has been conducted on Mura defect detection. The methods for detecting Mura defects can be broadly categorized into two main approaches: background reconstruction-based methods [3][4][5][6][7] and deep learning techniques [8][9][10][11][12][13]. Methods based on image background reconstruction are more common.…”

“…This model utilizes multilevel feature enhancement modules and clustering algorithms for screen defect detection. Wang et al [9] proposed a defect detection method based on attention and dual-head mechanisms, using deformable convolution to learn offset in the convolutional attention module, enabling the detection of irregular and small defects. Chen et al [10] proposed a feature extraction network that combines a residual network with an efficient channel attention mechanism to achieve efficient defect segmentation.…”