Toward cognitive support for automated defect detection
- 32 Downloads
With the development of cognitive computing, machine learning techniques, and big data analytics, cognitive support is crucial for automated industrial production. The real-time automated visual inspection in industrial production is a challenging task. Speed and accuracy are crucial factors for the process of automating the defect detection. Many statistical and spectrum analysis approaches have been introduced; however, they suffer from high computational cost with average performance. This paper proposes a neighborhood-maintaining approach, which is based on the minimum ratio for fast and reliable inspection of industrial products. The minimum ratio between local neighborhood sliding windows is used as a similarity measure for localizing defection. Extreme learning machine is then adapted to classify surfaces to defect or normal. A defect detection accuracy on textile fabrics has achieved 98.07% with 91.29% sensitivity and 99.67% specificity. The minimum ratio shows highly discriminant power to distinguish between normal and abnormal surfaces. A defective region produces a smaller value of minimum ratio than that of a defect-free region. Experimental results show superior speed and accuracy performance over many existing defect detection methods.
KeywordsMinimum ratio Defect detection Visual inspection Cognitive automation
This work was supported by the Deanship of Scientific Research, King Saud University, Riyadh, Saudi Arabia, through the Vice Deanship of Scientific Research Chairs.
Compliance with ethical standards
Conflict of interest
The authors do not have any type of conflict of interest.
- 1.Grand View Research (2018) Cognitive computing market size to reach USD 49.36 billion by 2025. https://www.grandviewresearch.com/press-release/global-cognitive-computing-market. Accessed 11 Feb 2018
- 3.CBR (2017) IBM brings cognitive assistant to factory for cutting down inspection time. https://www.cbronline.com/internet-of-things/cognitive-computing/ibm-brings-cognitive-assistant-to-factory-for-cutting-down-inspection-time/. Accessed 11 Feb 2018
- 4.Melkote AK (2016) The future of cognitive robotic process automation. http://www.sourcingfocus.com/site/opinionscomments/the_future_of_cognitive_robotic_process_automation/. Accessed 11 Feb 2018
- 9.Lapido YL et al (2015) Cognitive high speed defect detection and classification in MWIR images of laser welding. In: Proceedings of SPIE, p 9657Google Scholar
- 27.Guo X, Tang C, Zhang H, Chang Z (2012) Automatic thresholding for defect detection. ICIC Express Lett 6(1):159–164Google Scholar
- 29.Popescu D, Dobrescu R, Nicolae M (2007) Texture classification and defect detection by statistical features. NAUN Int J 1(1):79–84Google Scholar
- 32.Zhang R, Hu Y, Guo W, Zhang C (2009) Multi-scale Markov random field based fabric image segmentation associate with edge information. Int Symp Comput Intell Des 1(7):566–569Google Scholar
- 33.Serafim AFL (1992) Segmentation of natural images based on multiresolution pyramids linking of the parameters of an autoregressive rotation invariant model. Application to leather defects detection. Proc Int Conf Pattern Recognit 3(M1):41–44Google Scholar
- 35.Çelik Hİ, Dülger LC, Topalbekiro M (2014) Fabric defect detection using linear filtering and morphological operations. Indian J Fibre Text Res 39(September):254–259Google Scholar
- 44.Jen Clark (2017) IBM Watson IoT: cognitive visual inspection, July 4, 2017. https://www-01.ibm.com/common/ssi/cgi-bin/ssialias?htmlfid=WWS12361USEN. Accessed April 2018
- 46.Jen Clark. Cognitive inspection: IBM visual insights, July 4, 2017. https://www.ibm.com/blogs/internet-of-things/category/manufacturing/. Accessed April 2018
- 48.Abbas M, Albadr A, Tiun S (2017) Extreme learning machine: a review. Int J Appl Eng Res ISSN 12(14):973–4562Google Scholar
- 50.Eisner R, Poulin B, Szafron D, Lu P, Greiner R (2005) Improving protein function prediction using the hierarchical structure of the gene ontology. IEEE Comput Intell Bioinform Comput Biol 00:1–10Google Scholar
- 51.Sokolova M, Japkowicz N, Szpakowicz N (2006) Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. In: AI 2006: advances in artificial intelligence, pp 1015–1021Google Scholar
- 52.TILDA (1996) Textile defect image database. University of Freiburg, Germany. https://lmb.informatik.uni-freiburg.de/resources/datasets/tilda.en.html. Accessed 10 Jan 2018