Exploring Deep Learning-based Unsupervised Image Anomaly Detection and Localization Methods for Industrial Quality Assurance

The process of automatically finding and localizing the available anomalies (or defects) in the images of the products is known as Image Anomaly Detection and Localization (IADL). The IADL improves the efficiency of industrial quality inspection and ensures the desired quality level of the final pro...

Full description

Saved in:
Bibliographic Details
Published in2024 1st International Conference on Cognitive, Green and Ubiquitous Computing (IC-CGU) pp. 1 - 6
Main Authors Dutta, Pritha, Nayak, Rashmiranjan, Pati, Umesh Chandra
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.03.2024
Subjects
CFlow
Deep learning
DFKDE
DFM
Estimation
Feature extraction
Image anomaly detection and localization
Industrial quality assurance
Inspection
Location awareness
Measurement
PaDiM
Quality assurance
STFPM
Ubiquitous computing
Online AccessGet full text

Cover

More Information
Summary:The process of automatically finding and localizing the available anomalies (or defects) in the images of the products is known as Image Anomaly Detection and Localization (IADL). The IADL improves the efficiency of industrial quality inspection and ensures the desired quality level of the final products. Further, most of the supervised techniques are unsuitable for the IADL due to inherent data imbalance and ambiguity associated with the anomalies. Hence, this paper investigates key deep learning-based unsupervised IADL methods, such as Patch Distribution Modeling (PaDiM), Student-Teacher Feature Pyramid Matching (STFPM), Conditional Normalizing Flow (CFlow), Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection (DFM), and Deep Feature Kernel Density Estimation (DFKDE), for three publicly available bench-marked industrial defect detection datasets: MVTec AD, Visa and BTAD. Finally, a comparative analysis using both quantitative and qualitative performance metrics at the image as well as pixel levels is performed to draw some insightful conclusions.
DOI:10.1109/IC-CGU58078.2024.10530676