Vision Transformers for Anomaly Detection and Localisation in Leather Surface Defect Classification Based on Low-Resolution Images and a Small Dataset
Genuine leather manufacturing is a multibillion-dollar industry that processes animal hides from varying types of animals such as sheep, alligator, goat, ostrich, crocodile, and cow. Due to the industry’s immense scale, there may be numerous unavoidable causes of damages, leading to surface defects...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-07-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/13/15/8716 |
_version_ | 1797587120480583680 |
---|---|
author | Antony Douglas Smith Shengzhi Du Anish Kurien |
author_facet | Antony Douglas Smith Shengzhi Du Anish Kurien |
author_sort | Antony Douglas Smith |
collection | DOAJ |
description | Genuine leather manufacturing is a multibillion-dollar industry that processes animal hides from varying types of animals such as sheep, alligator, goat, ostrich, crocodile, and cow. Due to the industry’s immense scale, there may be numerous unavoidable causes of damages, leading to surface defects that occur during both the manufacturing process and the bovine’s own lifespan. Owing to the heterogenous and manifold nature of leather surface characteristics, great difficulties can arise during the visual inspection of raw materials by human inspectors. To mitigate the industry’s challenges in the quality control process, this paper proposes the application of a modern vision transformer (ViT) architecture for the purposes of low-resolution image-based anomaly detection for defect localisation as a means of leather surface defect classification. Utilising the low-resolution defective and non-defective images found in the opensource Leather Defect detection and Classification dataset and higher-resolution MVTec AD anomaly benchmarking dataset, three configurations of the vision transformer and three deep learning (DL) knowledge transfer methods are compared in terms of performance metrics as well as in leather defect classification and anomaly localisation. Experiments show the proposed ViT method outperforms the light-weight state-of-the-art methods in the field in the aspect of classification accuracy. Besides the classification, the low computation load and low requirements for image resolution and size of training samples are also advantages of the proposed method. |
first_indexed | 2024-03-11T00:32:45Z |
format | Article |
id | doaj.art-e2ad9c12ef6a444aa121449b01c85098 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-11T00:32:45Z |
publishDate | 2023-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-e2ad9c12ef6a444aa121449b01c850982023-11-18T22:36:36ZengMDPI AGApplied Sciences2076-34172023-07-011315871610.3390/app13158716Vision Transformers for Anomaly Detection and Localisation in Leather Surface Defect Classification Based on Low-Resolution Images and a Small DatasetAntony Douglas Smith0Shengzhi Du1Anish Kurien2Department of Electrical Engineering, Faculty of Engineering and the Built Environment, Pretoria 0184, South AfricaDepartment of Electrical Engineering, Faculty of Engineering and the Built Environment, Pretoria 0184, South AfricaDepartment of Electrical Engineering, Faculty of Engineering and the Built Environment, Pretoria 0184, South AfricaGenuine leather manufacturing is a multibillion-dollar industry that processes animal hides from varying types of animals such as sheep, alligator, goat, ostrich, crocodile, and cow. Due to the industry’s immense scale, there may be numerous unavoidable causes of damages, leading to surface defects that occur during both the manufacturing process and the bovine’s own lifespan. Owing to the heterogenous and manifold nature of leather surface characteristics, great difficulties can arise during the visual inspection of raw materials by human inspectors. To mitigate the industry’s challenges in the quality control process, this paper proposes the application of a modern vision transformer (ViT) architecture for the purposes of low-resolution image-based anomaly detection for defect localisation as a means of leather surface defect classification. Utilising the low-resolution defective and non-defective images found in the opensource Leather Defect detection and Classification dataset and higher-resolution MVTec AD anomaly benchmarking dataset, three configurations of the vision transformer and three deep learning (DL) knowledge transfer methods are compared in terms of performance metrics as well as in leather defect classification and anomaly localisation. Experiments show the proposed ViT method outperforms the light-weight state-of-the-art methods in the field in the aspect of classification accuracy. Besides the classification, the low computation load and low requirements for image resolution and size of training samples are also advantages of the proposed method.https://www.mdpi.com/2076-3417/13/15/8716deep learningcomputer visiondefect detectionleather qualityvision transformer networkssemi-supervised learning |
spellingShingle | Antony Douglas Smith Shengzhi Du Anish Kurien Vision Transformers for Anomaly Detection and Localisation in Leather Surface Defect Classification Based on Low-Resolution Images and a Small Dataset Applied Sciences deep learning computer vision defect detection leather quality vision transformer networks semi-supervised learning |
title | Vision Transformers for Anomaly Detection and Localisation in Leather Surface Defect Classification Based on Low-Resolution Images and a Small Dataset |
title_full | Vision Transformers for Anomaly Detection and Localisation in Leather Surface Defect Classification Based on Low-Resolution Images and a Small Dataset |
title_fullStr | Vision Transformers for Anomaly Detection and Localisation in Leather Surface Defect Classification Based on Low-Resolution Images and a Small Dataset |
title_full_unstemmed | Vision Transformers for Anomaly Detection and Localisation in Leather Surface Defect Classification Based on Low-Resolution Images and a Small Dataset |
title_short | Vision Transformers for Anomaly Detection and Localisation in Leather Surface Defect Classification Based on Low-Resolution Images and a Small Dataset |
title_sort | vision transformers for anomaly detection and localisation in leather surface defect classification based on low resolution images and a small dataset |
topic | deep learning computer vision defect detection leather quality vision transformer networks semi-supervised learning |
url | https://www.mdpi.com/2076-3417/13/15/8716 |
work_keys_str_mv | AT antonydouglassmith visiontransformersforanomalydetectionandlocalisationinleathersurfacedefectclassificationbasedonlowresolutionimagesandasmalldataset AT shengzhidu visiontransformersforanomalydetectionandlocalisationinleathersurfacedefectclassificationbasedonlowresolutionimagesandasmalldataset AT anishkurien visiontransformersforanomalydetectionandlocalisationinleathersurfacedefectclassificationbasedonlowresolutionimagesandasmalldataset |