Please use this identifier to cite or link to this item:
http://hdl.handle.net/2080/4655
Title: | Attention-enabled Convolutional Autoencoder with Optimal Threshold to Detect Image Anomaly for Industrial Quality Assurance |
Authors: | Nayak, Rashmiranjan Dutta, Pritha Pati, Umesh Chandra |
Keywords: | Attention-enabled Convolutional Autoencoder Deep learning Optimal Threshold Image Anomaly Detection Industrial Defect Detection |
Issue Date: | Aug-2024 |
Citation: | First International Conference Electronics, Communication and Signal Processing (ICECSP), NIT Delhi, India, 08-10 August 2024 |
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 (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. |
Description: | Copyright belongs to proceeding publisher |
URI: | http://hdl.handle.net/2080/4655 |
Appears in Collections: | Conference Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
2024_ICECSP_RNayak_Attention-enabled.pdf | 1.12 MB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.