Search

Image anomaly detection is a trending research topic in computer vision. The objective is to build models using available normal samples to detect various abnormal images without depending on real abnormal samples. It has high research significance and value for applications in the detection of defects in product appearance, medical image analysis, hyperspectral image processing, and other fields. This paper proposes an image anomaly detection algorithm based on feature distillation and an autoencoder structure, which uses the feature distillation structure of a dual-teacher network to train the encoder, thus suppressing the reconstruction of abnormal regions. This system also introduces an attention mechanism to highlight the detection objects, achieving effective detection of different defects in product appearance. In addition, this paper proposes a method for anomaly evaluation based on patch similarity that calculates the difference between the reconstructed image and the input image according to different regions of the image, thus improving the sensitivity and accuracy of the anomaly score. This paper conducts experiments on several datasets, and the results show that the proposed algorithm has superior performance in image anomaly detection. It achieves 98.8% average AUC on the SMDC-DET dataset and 98.9% average AUC on the MVTec-AD dataset. [ABSTRACT FROM AUTHOR]

In the integrated circuit (IC) packaging, the surface defect detection of flexible printed circuit boards (FPCBs) is important to control the quality of IC. Although various computer vision (CV)-based object detection frameworks have been widely used in industrial surface defect detection scenarios, FPCB surface defect detection is still challenging due to non-salient defects and the similarities between diverse defects on FPCBs. To solve this problem, a decoupled two-stage object detection framework based on convolutional neural networks (CNNs) is proposed, wherein the localization task and the classification task are decoupled through two specific modules. Specifically, to effectively locate non-salient defects, a multi-hierarchical aggregation (MHA) block is proposed as a location feature (LF) enhancement module in the defect localization task. Meanwhile, to accurately classify similar defects, a locally non-local (LNL) block is presented as a SEF enhancement module in the defect classification task. What is more, an FPCB surface defect detection dataset (FPCB-DET) is built with corresponding defect category and defect location annotations. Evaluated on the FPCB-DET, the proposed framework achieves state-of-the-art (SOTA) accuracy to 94.15% mean average precision (mAP) compared with the existing surface defect detection networks. Soon, source code and dataset will be available at https://github.com/SCUTyzy/decoupled-two-stage-framework. [ABSTRACT FROM AUTHOR]

In advanced integrated circuit packing, a very important substrate is high-density flexible printed circuit (FPC) board, which is small and foldable. The detection of the circular holes on FPCs’ surfaces through machine vision is very useful to identify root causes in FPC manufacturing process. However, it is a challenge as FPC images always contain many high details. This paper proposes a circle detection method with a modified tri-class thresholding-based contour extraction to detect and measure the circular holes on FPCs’ surfaces. It first extracts object contours by using a modified tri-class thresholding and then uses two circle validation criterions to eliminate noncircles: one is based on geometrical features and the other is based on the Helmholtz principle. Moreover, an iterative circle parameter refinement strategy is proposed. Experiments are carried out on 120 FPC images and the results indicate that the modified tri-class thresholding-based contour extraction method is more efficient than Canny detector, and the proposed circle detection method shows a better performance in terms of false detection rate, computation cost, and robustness than three other popular algorithms for detecting the circles in FPC images. [ABSTRACT FROM AUTHOR]