Human counting versus artificial intelligence for assessing medullation in mohair fibres
DOI:
https://doi.org/10.4314/sajas.v55i5.02Keywords:
Angora goats, animal fibre testing, fleece selection for animal breeding, textile qualityAbstract
The fleeces of mammals with dense coats, such as the mohair fleeces of Angora goats, usually include medullated fibres. These fibres constitute a problem for the textile industry because of their structural characteristics. Three experiments were conducted in this study, with the aim of comparing human image analysis to digital image analysis and artificial intelligence (AI), in terms of their ability to determine the incidence of medullation in mohair samples. The experiments entailed determining the incidences of industry non-objectionable medullated (NOB) fibres and objectionable medullated (SME) fibres, as percentages of the non-medullated fibres. In each experiment, a set of samples was analysed by both laboratory personnel and by different AI models using a Smart Fiber Medullometer. Laboratory personnel showed better coincidence and higher correlations with the AI models when counting SME fibres (r = 0.64–0.97) than when counting NOB fibres (r = 0.57–0.87). This could be the result of the more clearly defined characteristics of SME fibres, in relation to NOB fibres. The results of this study indicate a great advance in the automatic detection of SME and NOB fibres in mohair samples. However, further adjustments of the AI models are required for counting NOB fibres.
Submitted 12 June 2024; Accepted 8 April 2025; Published May 2025
-------------------------------------------------------------------
Significance of research to South African science
The article holds notable significance for South African science, particularly within the textile and agricultural sectors. Mohair is a valuable fibre in South Africa, which is one of the world’s leading producers. The study compares human assessment with artificial intelligence (AI) methods for detecting medullated fibres in mohair, a critical quality determinant for the textile industry. The findings demonstrate the growing potential of AI technologies to enhance the accuracy and efficiency of fibre quality analysis, offering a pathway to modernising mohair processing and improving global competitiveness. This aligns with South Africa's strategic focus on smart agriculture, innovation, and adding value to animal fibre production.
References
Anonymous, 2008. ASTM D2968-95: Standard test methods for med ratio and kemp fibres in wool and other animal fibres by Micro-projection. [Online]. Available: http://www.astm.org/standards/D2968.htm.
Atav, R. & Hunter, L., 2023. Luxury Animal Fibres Part 1: Hair Fibres from Goats (1st edition). Nova Science Publishers, Inc., New York, USA. pp. 15-68.
Baxter, P., 1992. Description and performance of the Optical Fibre Diameter Analyzer (OFDA). Journal of the Textile Institute, 83(4): 507-526. DOI: 10.1080/00405009208631225
Deng, Z. & Ke, W., 2010. A new measuring method of wool fiber diameter based on image processing. In: 2nd International Conference on Signal Processing Systems (ICSPS). DOI: 10.1109/ICSPS.2010.5555676
Goel, R., Sharma, A., & Kapoor, R., 2019. Object recognition using deep learning. Journal of Computational and Theoretical Nanoscience, 16:4044-4052. DOI: 10.1166/jctn.2019.8291
Hunter, L., 1993. Chapter 11: Medullation and kemp. In: Mohair, A Review of its Properties, Processing and Applications. NMB Printers (Pty) Std., Port Elizabeth, South Africa. pp. 88-108.
Krizhenysky, A., Sutskever, I., & Hinton, G.E., 2012. ImageNet classification with deep convolutional neural networks. In: Annual Conference on Neural Information Processing Systems (NIPS).
Krizhenysky, A., Sutskever, I., & Hinton, G., 2017. ImageNet classification with deep convolutional neural networks. Communication of the ACM, 60(6):84-90. DOI: 10.1145/3065386
Lee, J., Maher, A., Frampton, C., & Ranford, S., 1996. Comparison of Medullation in the Same Fiber Sites Using an OFDA (report no. 14). IWTO Technical and Standards Committee, Cape Town, South Africa.
Liang, K.Y. & Zeger S.L., 1986. Longitudinal data analysis using generalized linear models. Biometrika, 73:13-22.
Lupton, C.J., Minikhiem, D.L., Qi, K., Pfeiffer, F.A., & Waldron, D.F., 1994. Measurement of medullation in mohair. Texas Agricultural Experiment Station Progress Reports, 5230, College Station.
Lupton, C.J. & Pfeiffer, F.A., 1998. Measurement of medullation in wool and mohair using an Optical Fibre Diameter Analyser. Journal of Animal Science, 76:1261-1266. DOI: 10.2527/1998.7651261x
Pinares, R., Gutiérrez, G., Cruz, A., Morante, R., Cervantes, I., Burgos, A., & Gutiérrez, J., 2018. Heritability of individual fiber medullation in Peruvian alpacas. Small Ruminant Research, 165:93-100. DOI:10.1016/j.smallrumres.2018.04.007
Qi, K., Lupton, C.J., Pfieffer, F.A., Minikhiem, D.L., Kumar, N.S., & Whittaker, A.D., 1995. Automatic image analysis system for objective measurement of animal fibres. Sheep and Goat Research Journal, 11(2):71-77.
Quispe, M., Benavidez, G., Sauri, R., Bengoechea, J., & Quispe, E., 2017. Development and preliminary validation of an automatic digital analysis system for animal fibre analysis. South African Journal of Animal Science, 47(6):822-833. DOI: 10.4314/sajas.v47i6.10
Quispe, E., Quispe, M., Quispe, C., Poma, A., Paucar Chanca, R., Cruz, A., & McGregor, B., 2022. Relationships between the incidence and degree of medullation with the diameter of alpaca fibres evaluated using a novel device based on artificial intelligence. The Journal of The Textile Institute, 114(7):1016-1031. DOI: 10.1080/00405000.2022.2105110
Quispe, M.D., Quispe, C.C., Serrano-Arriezu, L., Trigo, J.D., Bengoechea, J.J., & Quispe, E.C., 2023. Development and validation of a smart system for medullation and diameter assessment of alpaca, llama and mohair fibres. Animal, 17(5):100800. DOI: 10.1016/j.animal.2023.100800
Shakyawar, D.B., Kadam, V., Surya, A.K., Ahmed, A., Pareek P.K., & Temani, P., 2013. Precise measurement of wool fibre diameter using computerized projection microscope. The Indian Journal of Small Ruminants, 19(2):190-192.
Wildman, A.B., 1954. The Microscopy of Animal Textile Fibres. Wool Industries Research Association, New York, USA.
Published
Issue
Section
License
Copyright (c) 2025 N Giovannini, D Sacchero, C Quispe Bonilla, M Quispe Bonilla, E Quispe Peña (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
- Abstract 195
- PDF 87
- XML 7
