Automated leather defect inspection using statistical approach on image intensity
- PDF / 2,988,316 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 5 Downloads / 239 Views
ORIGINAL RESEARCH
Automated leather defect inspection using statistical approach on image intensity Y. S. Gan1 · Sue‑Sien Chee2 · Yen‑Chang Huang3 · Sze‑Teng Liong4 · Wei‑Chuen Yau2 Received: 15 April 2020 / Accepted: 24 October 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Leather is a very important raw material in many manufacturing industries. For example to produce footwear, garments, bags and accessories. Prior to the mass production of certain product, a professional leather visual inspection process for defection spotting is essential as the quality control step. However, to date, there is a lack of fully-automated leather inspection systems in the industry, whereby most manufacturers rely on experienced and trained experts to mark out the defects in the leather. This kind of human assessment work is inefficient and inconsistent. Therefore, this paper proposes a method that based on image processing techniques, namely, gray level histogram analysis, to detect defects of the leather. Specifically, the histogram characteristics such as the mean and standard deviation are extracted and treated as the features. Then, the statistical Kolmogorov–Smirnov’s two-sample test is utilized to perform feature selection. Followed by a thresholding method to reduce the dimensionality of the features. Finally, the features are categorized by several well-known classifiers. The best classification accuracy obtained are 99.16% and 77.13% on two different datasets respectively. Keywords Leather · Defect · Statistical · Classification · Feature selection
1 Introduction Leather is a material made from animal hide that has been treated with chemicals to preserve them and make them suitable for use as clothing, handbags, sports equipment, * Sze‑Teng Liong [email protected] * Wei‑Chuen Yau [email protected] Y. S. Gan [email protected] Sue‑Sien Chee [email protected] Yen‑Chang Huang [email protected] 1
School of Architecture, Feng Chia University, Taichung, Taiwan
2
School of Electrical and Computer Engineering, Xiamen University Malaysia, Sepang, Malaysia
3
Department of Applied Mathematics, National University of Tainan, Tainan, Taiwan
4
Department of Electronic Engineering, Feng Chia University, Taichung, Taiwan
furniture, footwear, and tools. A recent 2018 study reveals that the world’s leather goods market is at 95.4 billion USD, and it is forecasted to reach 128.61 billion USD by 2022, with a rate of growth of 4.36% (APLF 2018). Because of the importance of leather in the manufacturing industry, it is vital to ensure the good quality of the leather to improve customer satisfaction. Normally, a natural leather piece may contain imperfections like insect bites, cuts, stains and wrinkles, as illustrated in Fig. 1. To produce leather products of high quality, these defects must be identified and removed during the defect determination process. In brief, the quality of leather can be judged based on established quality standards such as the standard listed by SATRA (Techn
Data Loading...
