Use of Machine Learning Techniques in Defect Detection of Leather - Review

Öz

It is estimated that leather has existed in human life since ancient times. As a matter of fact, while it was initially thought that it was used only to protect from cold and wind, today leather has a wide range of usage in huge sectors such as fashion, furniture and automotive, due to its durability and aesthetics. The global leather market is growing every year. This situation increases the importance of smart approaches in leather production day by day. It has been a long-standing practice for tanneries to use experienced human inspectors to detect surface defects in leather products. However, this method is tiring, time-consuming, prone to errors and varies depending on the person's experience. A low margin of error in determining the quality of leather products is of serious economic importance. In order to get rid of human errors in the sector and to objectify the decisions made, the need to automatically detect flaws on the leather surface has emerged. In this study, a literature review was conducted on studies using machine learning techniques to detect defects in animal leather. A detailed review of methods for detecting defects on leather surfaces using image analysis and machine learning methods was conducted. Challenges and stages of development are presented with the aim of encouraging future work in this field.

Anahtar Kelimeler

• Leather
• surface defect detection
• computer vision
• machine learning

Hayvan Derisinin Kusur Tespitinde Makine Öğrenmesi Tekniklerinin Kullanımı – Literatür Taraması

Öz

Derinin insan hayatında ilk çağlardan beri var olduğu tahmin edilmektedir. Nitekim ilk başlarda sadece soğuktan ve rüzgârdan korunmak için kullanıldığı düşünülürken günümüzde deri, dayanıklılığı ve estetikliği sebebiyle moda, mobilya ve otomotiv gibi devasa sektörlerde çok geniş bir kullanım alanına sahiptir. Küresel deri pazarı her geçen yıl daha da büyümektedir. Bu durum deri üretiminde akıllı yaklaşımların önemini her geçen gün artırmaktadır. Tabakhanelerde deri ürünlerindeki yüzey kusurlarını tespit edebilmek için tecrübeli insan denetçilerin kullanılması uzun zamandır süregelen bir uygulamadır. Ancak bu yöntem, yorucu, zaman alıcı, hatalara açık ve kişinin tecrübesine göre değişkendir. Kaliteli deri ürünlerinde hata payının düşük olması ekonomik olarak ciddi öneme sahiptir. Sektördeki insan hatalarından kurtulmak ve verilen kararları nesnelleştirebilmek adına deri yüzeyindeki kusurların otomatik tespit edilebilmesi ihtiyacı ortaya çıkmıştır. Bu çalışmada hayvan derisinin kusurlarını tespit edebilmek amacı ile makine öğrenmesi tekniklerini kullanan çalışmalar hakkında literatür taraması yapılmıştır. Görüntü analizi ve makine öğrenmesi yöntemleri ile deri yüzeylerindeki kusurları tespit etme yöntemlerinin detaylı bir incelemesi yapılmıştır. Bu alanda gelecekte yapılacak çalışmaları teşvik etmek amacı ile zorluklar ve gelişim evreleri sunulmuştur.

Anahtar Kelimeler

• Hayvan derisi
• yüzey kusur tespiti
• bilgisayar görüsü
• makine öğrenmesi

Kaynakça

1. Abdullah AB, Jawahar M, Manogaran N, Subbiah G, Seeranagan K, Balusamy B, Saravanan AC (2024). Leather Image Quality Classification and Defect Detection System using Mask Region-based Convolution Neural Network Model. International Journal of Advanced Computer Science & Applications, 15(4).
2. Amorim WP, Pistori H, Jacinto MAC, Sudeste EP (2009). A comparative analysis of attribute reduction algorithms applied to wet-blue leather defects classification. Brazilian Symposium on Computer Graphics and Image Processing, 2009(1):1-2.
3. Amorim WP, Pistori H, Pereira MC, Jacinto MAC (2010). Attributes reduction applied to leather defects classification. Patterns and Images, 2010(1): 353-359.
4. Aslam M, Khan TM, Naqvi SS, Holmes G, Naffa R (2019). On the application of automated machine vision for leather defect inspection and grading: a survey. IEEE Access, 7: 176065-176086.
5. Bong HQ, Truong QB, Nguyen HC, Nguyen MT (2018). Vision-based inspection system for leather surface defect detection and classification. 5th NAFOSTED conference on information and computer science (NICS). Ho Chi Minh City, Vietnam.
6. Bowman CC, Hilton PJ, Power PW, Hayes MP, Gabric RP (1996). Sheep-pelt grading using laser scanning and pattern recognition. Machine vision applications, architectures, and systems integration, SPIE, 1996(2908): 33-42.
7. Branca A, Abbate MG, Lovergine FP, Attolico G, Distante A (1997). Leather inspection through singularities detection using wavelet transforms. Image Analysis and Processing: 9th International Conference, ICIAP’97. Florence, Italy.
8. Branca A, Lovergine FP, Attolico G, Distante A (1997). Defect detection on leather by oriented singularities. Computer Analysis of Images and Patterns. 7th International Conference, CAIP’97. Kiel, Germany.

9. Branca A, Tafuri M, Attolico G, Distante A (1996). Automated system for detection and classification of leather defects. Optical Engineering, 35(12): 3485-3494.
10. Chen SY, Cheng YC, Yang WL, Wang MY (2021). Surface defect detection of wet-blue leather using hyperspectral imaging. IEEE Access, 2021(9): 127685-127702.
11. Chen Z, Deng J, Zhu Q, Wang H, Chen Y (2022). A systematic review of machine-vision-based leather surface defect inspection. Electronics, 11(15): 2383.
12. Chen Z, Xu D, Deng J, Chen Y, Li C (2023). Comparative study on deep-learning-based leather surface defect identification. Measurement Science and Technology, 35(1): 015402.
13. Chen Z, Zhu Q, Zhou X, Deng J, Song W (2024). Experimental Study on YOLO-based Leather Surface Defect Detection. IEEE Access, 2024(12): 32830-32848.
14. Conover W (1965). Several k-sample Kolmogorov-Smirnov tests. The Annals of Mathematical Statistics, 36(3): 1019-1026.
15. Deng J, Liu J, Wu C, Zhong T, Gu G, Ling BWK (2020). A novel framework for classifying leather surface defects based on a parameter optimized residual network. IEEE Access, 8: 192109-192118.
16. Ding C, Huang H, Ming P (2020). Inspection method of leather defect based on convolutional neural network and salient feature. Donghua University Natual Sciences, 2020(46): 408-413.
17. Fuqiang H, Wen W, Zichen C (2006). Automatic defects detection based on adaptive wavelet packets for leather manufacture, In Technology and Innovation Conference (ITIC). Hangzhou, China.
18. Gan YS, Chee SS, Huang YC, Liong ST, Yau WC (2021). Automated leather defect inspection using statistical approach on image intensity. Journal of Ambient Intelligence and Humanized Computing, 12: 9269-9285.
19. Gan YS, Liong ST, Zheng D, Xia Y, Wu S, Lin M, Huang YC (2023). Detection and localization of defects on natural leather surfaces. Journal of Ambient Intelligence and Humanized Computing, 2023(1): 1-15.
20. Gan YS, Liong ST, Zheng D, Xia Y, Wu S, Lin M, Huang YC (2021). Detection and localization of defects on natural leather surfaces. Journal of Ambient Intelligence and Humanized Computing, 2021(1): 1-15.
21. Gan YS, Yau WC, Liong ST, Chen CC (2022). Automated classification system for tick-bite defect on leather. Mathematical Problems in Engineering, 2022(1): 1-12.
22. Georgieva L, Krastev K, Angelov N (2003). Identification of surface leather defects. Proceedings of the 4th international conference on Computer systems and technologies, CompSysTech. New York, United States.
23. Ghimire A, Mahaseth A, Thapa R, Magar SA, Singh SK, Khanal SR (2022). Leather Defect Segmentation Using Semantic Segmentation Algorithms. Journal of Artificial Intelligence and Capsule Networks, 2022(2): 131-138.
24. Iqbal S, Khan TM, Naqvi SS, Holmes G (2023). MLR-Net: A multi-layer residual convolutional neural network for leather defect segmentation. Engineering Applications of Artificial Intelligence, 126: 107007.
25. Jawahar M, Babu NKC, Vani K (2014). Leather texture classification using wavelet feature extraction technique. 2014 IEEE International Conference on Computational Intelligence and Computing Research. TamilNadu, India.
26. Jian L, Wei H, Bin H (2010). Research on inspection and classification of leather surface defects based on neural network and decision tree. International conference on computer design and applications. Qinhuangdao, China.
27. Kasi MK, Rao JB, Sahu VK (2014). Identification of leather defects using an autoadaptive edge detection image processing algorithm. International conference on high performance computing and applications (ICHPCA). Bhubaneswar, India.
28. Khanal SR, Silva J, Magalhães L, Soares J, Gonzalez DG, Castilla YC, Ferreira MJ (2022). Leather Defect Detection Using Semantic Segmentation: A Hardware platform and software prototype. Procedia Computer Science, 2022(204): 573-580.
29. Kohli P, Garg S (2013). Leather quality estimation using an automated machine vision system. IOSR Journal of Eletronics and Communication Engineering, 2013(6): 44-47.
30. Krastev K, Georgieva L (2005). Identification of leather surface defects using fuzzy logic. Proceedings of the International Conference on Computer Systems and Technologies. Washington, United States.
31. Krastev K, Georgieva L, Angelov N (2004). Leather features selection for defects recognition using fuzzy logic. Energy, 2004(3): 1-6.
32. Kwak C, Ventura JA, Tofang-Sazi K (2000). A neural network approach for defect identification and classification on leather fabric. Journal of Intelligent Manufacturing, 2000(11): 485-499.
33. Kwak C, Ventura JA, Tofang-Sazi K (2001). Automated defect inspection and classification of leather fabric. Intelligent Data Analysis, 2001(4): 355-370.
34. Kwon JW, Choo YY, Choi HH, Cho JM, KiI GS (2004). Development of leather quality discrimination system by texture analysis. Region 10 Conference TENCON. Chiang Mai, Thailand.
35. LeCun Y, Bengio Y, Hinton G (2015). Deep learning. Nature, 2015(1): 436-444.
36. Liong ST, Gan YS, Huang YC, Yuan CA, Chang HC (2019). Automatic defect segmentation on leather with deep learning. arXiv preprint arXiv: 1903.12139.
37. Liong ST, Gan YS, Liu KH, Binh TQ, Le CT, Wu CA, Yang CY, Huang YC (2019). Efficient neural network approaches for leather defect classification. arXiv preprint arXiv: 1906.06446.
38. Liong ST, Zheng D, Huang YC, Gan YS (2020). Leather defect classification and segmentation using deep learning architecture. International Journal of Computer Integrated Manufacturing, 2020(33): 10-11.
39. Moganam PK, Seelan DAS (2020). Perceptron Neural Network Based Machine Learning Approaches for Leather Defect Detection and Classification. Instrumentation, Mesures, Métrologies, 2020(6): 421-429.
40. Doble M, Rollins K, Kumar A (2007). Industrial examples in Green Chemistry and Engineering. Academic Press.
41. Omoloso O, Mortimer K, Wise WR, Jraisat L (2021). Sustainability research in the leather industry: A critical review of progress and opportunities for future research. Journal of Cleaner Production, 2021(285): 421-429.
42. Pereira RF, Dias MLD, de Sá Medeiros CM, Rebouças Filho PP (2018). Classification of Failures in Goat Leather Samples Using Computer Vision and Machine Learning. SIBGRAPI 2018. Foz do Iguaçu, Brazil.
43. Peters S, Koenig A (2007). A hybrid texture analysis system based on non-linear & oriented kernels, particle swarm optimization, and kNN vs. support vector machines. 7th international conference on hybrid intelligent systems (HIS 2007). Kaiserslautern, Germany.
44. Pistori H, Paraguassu WA, Martins PS, Conti MP, Pereira MA, Jacinto MA (2018). Defect detection in raw hide and wet blue leather. Computational Modelling of Objects Represented in Images. Fundamentals, Methods and Applications. Cracow, Poland.
45. Prananda AR, Frannita EL (2023). Toward Adaptive Manufacturing Development: Implementation of Artificial Intelligence for Identifying Leather Defects. Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering), 2023(2): 200-207.
46. Rao AR (2012). A taxonomy for texture description and identification. Springer Science & Business Media.
47. Rao AR, Lohse GL (1993). Identifying high level features of texture perception. CVGIP: Graphical Models and Image Processing, 1993(3): 218-233.
48. Santos Filho EQ, de Sousa PHF, Rebouças Filho PP, Barreto GA, de Albuquerque VHC (2020). Evaluation of goat leather quality based on computational vision techniques. Circuits, Systems, and Signal Processing, 2020(2): 651-673.
49. Smith AD, Du S, Kurien A (2023). Vision transformers for anomaly detection and localisation in leather surface defect classification based on low-resolution images and a small dataset. Applied Sciences, 13(15): 8716.
50. Sobral JL (2005). Leather inspection based on wavelets. Iberian conference on pattern recognition and image analysis, Springer, 2005(1): 682-688.
51. Sousa CEB, Medeiros CMS, Pereira RF, Neto AA, Neto MAV (2021). A decision support system for fault detection and definition of the quality of wet blue goat skins. Heliyon, 7(9).
52. Tafuri M, Branca A, Attolico G, Distante A, Delaney W (1996). Automatic leather inspection of defective patterns. Machine vision applications in industrial inspection IV, SPIE, 1996(2665): 108-119.
53. Ticaret Bakanlığı (2022). Deri ve Deri Mamulleri Sektör Raporu. https://ticaret.gov.tr/data/5b87000813b8761450e18d7b/Deri_ve_Deri_Mamulleri_Sekt%C3%B6r%C3%BC.pdf.
54. TÜİK (2020, Aralık). Deri Üretimi Miktarları. Türkiye İstatistik Kurumu. https://data.tuik.gov.tr/Bulten/DownloadIstatistikselTablo?p=/akVjpnzD2nodln2y9MutlfambT1xV5PmEU6zK9rXpGm5Ek0kCvdtPrMKm86QlLt.
55. Viana R, Rodrigues RB, Alvarez MA, Pistori H (2007). SVM with stochastic parameter selection for bovine leather defect classification. Advances in Image and Video Technology: Second Pacific Rim Symposium, PSIVT 2007. Santiago, Chile.
56. Villar P, Mora M, Gonzalez P (2011). A new approach for wet blue leather defect segmentation. Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications: 16th Iberoamerican Congress, CIARP 2011. Pucón, Chile.
57. Wang Q, Liu H, Liu J, Wu T (1992). A new method for leather texture image classification. IEEE International Symposium on Industrial Electronics. Xi'an, China.
58. Winiarti S, Prahara A, Murinto DPI, Ismi P (2018). Pretrained convolutional neural network for classification of tanning leather image. Network (CNN), 9(1): 9.
59. Wu X, Xiong H, Wen P (2016). A defect detection method based on sub-image statistical feature for texture surface. Eighth International Conference on Digital Image Processing (ICDIP 2016). Chengu, China.
60. Yuan S, Li L, Chen H, Li X (2023). Surface Defect Detection of Highly Reflective Leather Based on Dual-Mask Guided Deep Learning Model. IEEE Transactions on Instrumentation and Measurement, 2023(72): 1-13.