An improved automatic defect identification system on natural leather via generative adversarial network

Gan, Yee Siang; Liong, Sze‐Teng; Wang, Shih-Yuan; Cheng, Chin Tiong

doi:10.1080/0951192x.2022.2048421

Cited by 11 publications

(5 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Advancing their previous work in this field of interest, the teams of Gan and Liong adopted a generative adversarial network (GAN) as a means of reliably synthesizing further normal images in order to augment an already limited training set and therefore improve the accuracy of feature extraction and classification of the typical AlexNet architecture [31].…”

Section: Leather Surface Defect Detection Methodsmentioning

confidence: 99%

Vision Transformers for Anomaly Detection and Localisation in Leather Surface Defect Classification Based on Low-Resolution Images and a Small Dataset

Smith

Kurien

2023

Applied Sciences

View full text Add to dashboard Cite

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.

show abstract

Section: Leather Surface Defect Detection Methodsmentioning

confidence: 99%

Vision Transformers for Anomaly Detection and Localisation in Leather Surface Defect Classification Based on Low-Resolution Images and a Small Dataset

Smith

Kurien

2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Aslam [23] believes that deep learning holds great promise in developing new solutions for leather surface defect inspection. Some researchers have also developed corresponding solutions [24][25][26][27]. Although Liong's team conducted an in-depth exploration, their work was also limited to a small local dataset.…”

Section: Related Workmentioning

confidence: 99%

Experimental Study on YOLO-Based Leather Surface Defect Detection

Chen,

Zhu,

Zhou

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Accurate, reliable, and fast intelligent detection of leather surface defects has become an important subject in industrial inspection, which aims at improving production efficiency and increasing automation levels. This work focuses on the rapid defect recognition and localization of leather surface defects for industrious applications, which is based on the state-of-the-art real-time detection model YOLO. Three experimental Schemes with different challenges were designed to find the optimal YOLO-based leather surface defect detection scheme. Typical tanned leather surface defect images from the factory were collected, which are comprised of eight types of defects, namely rotten surface, hole, scratch, crease, healed injury, bacterial injury, growth line, and pinhole, which exhibit variations in shapes, sizes, and colors, reflecting the various characteristics found in tanned leather defects. A comprehensive and in-depth review of the YOLO series of models is presented, including YOLOv1 to YOLOv8. The systematic and extensive experiments indicate that the YOLO models can simultaneously detect multiple types of defects present in each leather image. The multi-defect detection task achieved a maximum of 52.3% mean average precision (mAP), 58.2% precision, and 68.7% recall. For single-class detection tasks, the highest performance reached 85.1% mAP, 90.9% precision, and 81.8% recall. These works provide feasible intelligent solutions for surface defects in the leather industry, laying a solid foundation for the design and development of new solutions for leather defect detection.

show abstract

“…After sintering, dust, oxides, and various types of oxygen content do not meet the standard, causing sedimentation, reducing its strength and causing the product to loosen and fall off. Failure to completely remove impurities and foreign objects can lead to defects in the ceramic body [9][10].…”

Section: Porcelain Product Defect Categorymentioning

confidence: 99%

Dehua porcelain product defect recognition based on image processing

Gao

2023

Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023)

View full text Add to dashboard Cite

In recent years, with the continuous development of the ceramic industry, the problem of Product defect has become increasingly prominent. Therefore, this article conducted recognition research on Dehua porcelain through image processing technology. Firstly, the background and research significance of this article were elaborated; Secondly, a detailed analysis was conducted on the detection technology and application status of powder and particle size in ceramic processing; Next, the principle and implementation process of defect recognition based on machine vision were elaborated, and experimental results were compared and error corrected. At the same time, improved algorithms were proposed to improve identification accuracy; Finally, this paper tests the performance of the porcelain Product defect recognition model, and the test results show that the resource occupancy rate of this model is between 2% and 4%, and the defect recognition rate is relatively high, which can meet the demand. Compared with the traditional visual inspection, the defect recognition method based on image processing can realize the automatic detection process. It can improve production efficiency and reduce the impact of human errors and subjective judgments. This method can identify the defects of Dehua porcelain products in real time and reduce the time and labor cost of traditional detection methods.

show abstract

An improved automatic defect identification system on natural leather via generative adversarial network

Cited by 11 publications

References 37 publications

Vision Transformers for Anomaly Detection and Localisation in Leather Surface Defect Classification Based on Low-Resolution Images and a Small Dataset

Vision Transformers for Anomaly Detection and Localisation in Leather Surface Defect Classification Based on Low-Resolution Images and a Small Dataset

Experimental Study on YOLO-Based Leather Surface Defect Detection

Dehua porcelain product defect recognition based on image processing

Contact Info

Product

Resources

About