Name
Title | ||
|---|---|---|
Logit Inducing With Abnormality Capturing for Semi-Supervised Image Anomaly Detection |
Abstract | ||
|---|---|---|
Image anomaly detection is a significant stage for visual quality inspection in intelligent manufacturing systems. According to the assumption that only normal images are available during the training stage, unsupervised methods have been studied recently for image anomaly detection. But anomalous images of small scale can be collected for training in many real-world industrial scenarios, and the unsupervised methods make no use of them to improve the detection accuracy. This leads to semi-supervised image anomaly detection with an unbalanced detection challenge. In this article, a logit inducing with abnormality capturing (LIAC) method is proposed to address semi-supervised image anomaly detection. First, a logit inducing loss (LIS) is proposed to train a classifier for dealing with unbalanced detection. Second, an abnormality capturing module (ACM) is proposed to address anomaly detection. With labeling only 40 anomalous images for training, the proposed LIAC method achieves a 98.8% F1-score on image anomaly detection of the printed circuit board, compared with the state-of-the-art (SOTA) methods. Moreover, the proposed LIAC method is experimentally compared with the SOTA methods on magnetic tile defect (MTD), retinal optical coherence tomography (ROCT), and electroluminescence images of photovoltaic modules (ELPV), three open-source datasets, respectively, which achieve F1-score of 85.2%, 96.8%, and 66.6% with given 40 anomalous images for training. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1109/TIM.2022.3205674 | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT |
Keywords | DocType | Volume |
Anomaly detection, Training, Feature extraction, Manufacturing, Support vector machines, Neural networks, Visualization, Abnormality capturing, image anomaly detection, logit inducing, semi-supervised | Journal | 71 |
ISSN | Citations | PageRank |
0018-9456 | 0 | 0.34 |
References | Authors | |
0 | 3 | |