Please use this identifier to cite or link to this item:
http://hdl.handle.net/2080/4467
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Dutta, Pritha | - |
dc.contributor.author | Nayak, Rashmiranjan | - |
dc.contributor.author | Pati, Umesh Chandra | - |
dc.date.accessioned | 2024-03-12T10:00:01Z | - |
dc.date.available | 2024-03-12T10:00:01Z | - |
dc.date.issued | 2024-03 | - |
dc.identifier.citation | International Conference on Cognitive, Green and Ubiquitous Computing (IC-CGU), C. V. Raman Global University, Bhubaneswar, 1-2 March 2024 | en_US |
dc.identifier.uri | http://hdl.handle.net/2080/4467 | - |
dc.description | Copyright belongs to proceeding publisher | en_US |
dc.description.abstract | 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 Dis- tribution 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. | en_US |
dc.subject | CFlow | en_US |
dc.subject | Deep learning | en_US |
dc.subject | DFKDE | en_US |
dc.subject | DFM | en_US |
dc.subject | Image anomaly detection and localization | en_US |
dc.subject | Indusrtial quality assurance | en_US |
dc.subject | PaDiM | en_US |
dc.subject | STFPM | en_US |
dc.title | Exploring Deep Learning-based Unsupervised Image Anomaly Detection and Localization Methods for Industrial Quality Assurance | en_US |
dc.type | Article | en_US |
Appears in Collections: | Conference Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
2024_ICCGU_PDutta_Exploring.pdf | 3.29 MB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.