Please use this identifier to cite or link to this item: http://hdl.handle.net/2080/4655
Full metadata record
DC FieldValueLanguage
dc.contributor.authorNayak, Rashmiranjan-
dc.contributor.authorDutta, Pritha-
dc.contributor.authorPati, Umesh Chandra-
dc.date.accessioned2024-08-16T07:40:21Z-
dc.date.available2024-08-16T07:40:21Z-
dc.date.issued2024-08-
dc.identifier.citationFirst International Conference Electronics, Communication and Signal Processing (ICECSP), NIT Delhi, India, 08-10 August 2024en_US
dc.identifier.urihttp://hdl.handle.net/2080/4655-
dc.descriptionCopyright belongs to proceeding publisheren_US
dc.description.abstractThe process of automatically finding and localizing the available anomalies (or defects) in the images of the products is known as Image Anomaly Detection (IAD). In this paper, an attention-enabled convolutional autoencoder has been proposed to detect industrial defects using images of the products. The proposed model uses image-wise defect detection. The model classifies each test image as either defective or defectfree based on the magnitude of its reconstruction error. The Structural Similarity Index Measure (SSIM) is employed to assess image quality by quantifying the reconstruction error. SSIM goes beyond comparing individual pixel values and analyzes the inter-relationships between local image regions. This incorporates luminance, contrast, and structural information, providing a more comprehensive evaluation aligned with human visual perception. Comparative result analysis and ablation study validate the superiority of the proposed model.en_US
dc.subjectAttention-enabled Convolutional Autoencoderen_US
dc.subjectDeep learningen_US
dc.subjectOptimal Thresholden_US
dc.subjectImage Anomaly Detectionen_US
dc.subjectIndustrial Defect Detectionen_US
dc.titleAttention-enabled Convolutional Autoencoder with Optimal Threshold to Detect Image Anomaly for Industrial Quality Assuranceen_US
dc.typeArticleen_US
Appears in Collections:Conference Papers

Files in This Item:
File Description SizeFormat 
2024_ICECSP_RNayak_Attention-enabled.pdf1.12 MBAdobe PDFView/Open    Request a copy


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.