An image processing and machine learning solution to automate Egyptian cotton lint grading
Source abstract
Abstract
Egyptian cotton is one of the most important commodities for the Egyptian economy and is renowned globally for its quality, which is largely assessed and graded by manual inspection. This grading has several drawbacks, including significant labor requirements, low inspection efficiency, and influence from inspection conditions such as light and human subjectivity. This work proposes a low-cost solution to replace manual inspection with classification models to grade Egyptian cotton lint using images captured by a charge-coupled device camera. While this method has been evaluated for classifying US and Chinese upland cotton staples, it has not been tested on Egyptian cotton, which has unique characteristics and grading requirements. Furthermore, the methodology to develop these classification models has been expanded to include image processing techniques that remove the influence of trash on color measurements and extract features that capture the intra-sample variance of the cotton samples. Three different supervised machine learning algorithms were evaluated: artificial neural networks; random forest; and support vector machines. The highest accuracy models (82.13–90.21%) used a random forest algorithm. The models’ accuracy was limited by the human error associated with labeling the cotton samples used to develop the classification models. Unsupervised machine learning methods, including k-means clustering, hierarchical clustering, and Gaussian mixture models, were used to indicate where labeling errors occurred.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Textile materials and evaluations · Research in Cotton Cultivation
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Food Water Waste Research Group, Faculty of Engineering, University of Nottingham, UK
Teagasc Food Research Centre, Ireland
Department of Plant Production, Faculty of Agriculture, Saba Basha, Alexandria University, Egypt
Department of Soils and Agricultural Chemistry, Faculty of Agriculture, Saba Basha, Alexandria University, Egypt
References (50)
Show source-provided references
1. Yu C. · 29
2. Dhehibi B · Sustain Agric Res · 2016 · 5 · 38
3. Ahmed YN · J Agric Sci · 2019 · 11 · 88
4. Food and Agriculture Organization of the United Nations. Crops and livestock products, http://www.fao.org/faostat/en/#data/TP (accessed 23 June 2021).
5. Wally A, Tate B. 2018 Cotton and products annual, https://www.fas.usda.gov/data/egypt-cotton-and-products-annual-4 (27 March 2018, accessed 2 February 2021).
6. The United Nations Industrial Development Organisation. From cotton seeds to clothing: enhancing the sustainability, inclusiveness and value addition of the cotton value chain in Egypt, https://open.unido.org/projects/EG/projects/160068?_ga=2.69868693.447703373.1612258725-931943205.1612258725 (2016, accessed 2 February 2021).
7. 10.56454/ZELZ320910.56454/ZELZ3209 ↗
8. 10.2134/cftm2017.07.004810.2134/cftm2017.07.0048 ↗
9. 10.1177/00405175000700050810.1177/004051750007000508 ↗
10. 10.1371/journal.pone.026097110.1371/journal.pone.0260971 ↗
11. Hussein MG · Arab Univ J Agric Sci · 2020 · 28 · 191
12. 10.1016/j.compeleceng.2015.06.02210.1016/j.compeleceng.2015.06.022 ↗
13. 10.1016/j.procs.2020.06.14910.1016/j.procs.2020.06.149 ↗
14. 10.3390/electronics911179510.3390/electronics9111795 ↗
15. Matusiak M · Fibres Text East Eur · 2010 · 18 · 17
16. 10.13031/2013.3258410.13031/2013.32584 ↗
17. 10.1007/978-3-319-94478-4_1510.1007/978-3-319-94478-4_15 ↗
18. 10.1177/00405175980680050510.1177/004051759806800505 ↗
19. 10.1177/00405175980680110110.1177/004051759806801101 ↗
20. 10.1177/00405175990690120210.1177/004051759906901202 ↗
21. 10.1177/004051751349005510.1177/0040517513490055 ↗
22. 10.13031/2013.1830710.13031/2013.18307 ↗
23. 10.1088/2053-1591/aba3e410.1088/2053-1591/aba3e4 ↗
24. 10.1177/00405175020720090510.1177/004051750207200905 ↗
25. 10.1117/12.16432610.1117/12.164326 ↗
26. 10.1109/ICIAFS.2012.641990410.1109/ICIAFS.2012.6419904 ↗
27. 10.1186/1754-1611-8-2910.1186/1754-1611-8-29 ↗
28. 10.3390/s1703051810.3390/s17030518 ↗
29. 10.1177/004051751347848110.1177/0040517513478481 ↗
30. 10.1016/j.indcrop.2015.11.02210.1016/j.indcrop.2015.11.022 ↗
31. 10.3390/info1205019610.3390/info12050196 ↗
32. 10.1117/12.58733410.1117/12.587334 ↗
33. Holst GC · 201110.1117/3.2524677 ↗
34. Bishop CM. · 2006
35. 10.1016/j.rser.2017.02.02310.1016/j.rser.2017.02.023 ↗
36. 10.1016/j.enbuild.2017.04.03810.1016/j.enbuild.2017.04.038 ↗
37. Horning N. Random forests : an algorithm for image classification and generation of continuous fields data sets. In: Anh TV and Yonezawa G (eds) international conference on geoinformatics for spatial infrastructure development in Earth and allied sciences 2010 , Hanoi, Vietnam. Osaka, 9-11 December, 2010. pp. 1–16.
38. James G, Witten D, Hastie T, et al. Unsupervised learning. In: An introduction to statistical learning . New York: Springer, 2013, pp.373–418.10.1007/978-1-4614-7138-7_10 ↗
39. 10.1109/LLS.2016.261508610.1109/LLS.2016.2615086 ↗
40. 10.2118/109018-PA10.2118/109018-PA ↗
41. Kim S. · 2017
42. 10.1109/ICDM.2010.3510.1109/ICDM.2010.35 ↗
43. Indian J Fibre Text Res · 2013 · 3 · 52
44. Sandbhor S · 481
45. Bourland FM · J Cotton Sci · 2010 · 14 · 53
46. 10.1016/j.knosys.2017.02.01410.1016/j.knosys.2017.02.014 ↗
47. 10.1016/j.ins.2016.04.04010.1016/j.ins.2016.04.040 ↗
48. 10.1038/s41598-019-47399-810.1038/s41598-019-47399-8 ↗
49. 10.1016/j.ultras.2021.10646810.1016/j.ultras.2021.106468 ↗
50. 10.1109/COMST.2021.309043010.1109/COMST.2021.3090430 ↗