Measurement of Seed Cotton Color Using RGB Imaging and Color-Unet
Abstract
1. Introduction
2. Materials and Methods
2.1. Samples
2.2. Seed Cotton Color Detection System
2.3. Dataset Preparation and Data Augmentation
2.4. Image Segmentation Network
2.4.1. Unet Model
2.4.2. Color-Unet Model
2.5. Model Training
2.6. Model Evaluation
2.7. Segmentation Performance Evaluation
2.8. Seed Cotton Color Measurement
2.8.1. Machine Vision Measurement
- Image acquisition
- 2.
- Color calibration
- 3.
- Image segmentation
- 4.
- Color index calculation and correction
2.8.2. Spectrophotometer Measurement
2.9. Evaluation of Cotton Color Measurement Method
3. Results
3.1. Training of the Color-Unet Model
3.2. Segmentation Performance
3.3. Ablation Studies
3.4. Comparison with the SDTS-MF
3.5. Color Measurement Performance of Seed Cotton Color Measurement System
4. Discussion
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Deniz, I.; Müge, E.; Uğur, C.; Özgür, T. The Impact of Environmental Variability on Cotton Fiber Quality: A Comparative Analysis of Primary Cotton-Producing Regions in Türkiye. Agronomy 2024, 14, 1276. [Google Scholar] [CrossRef]
- Shankar, C.; Subham, A.; Ahruti, D. Analysis of Cotton Fibre Properties: A data Mining Approach. J. Inst. Eng. India Ser. E 2018, 99, 163–176. [Google Scholar]
- Michal, V.; Nayab, K.; Bekir, Y.; Martina, V. Non-contact Method for Measurement of Colour Variation in a Cotton Sample. Fibres Text. East. Eur. 2017, 2, 106–111. [Google Scholar]
- Robert, G.; Hardin, E.; Barnes, C.; Delhom, J.; Wanjura, J. Internet of things: Cotton harvesting and processing. Comput. Electron. Agric. 2022, 202, 107294. [Google Scholar]
- Maria, S.; Welma, T.S.; Everaldo, M.; Márcio, P. An analytical method for determination of quality parameters in cotton plumes by digital image and chemometrics. Comput. Electron. Agric. 2016, 123, 89–94. [Google Scholar]
- Khan, N.; Vik, M.; Irshad, F.; Yildirim, B.; Farooq, A.; Ashraf, M. Development of a 3D Color Diagram for Improved Visual Grading System of Cotton. Fibers Polym. 2023, 24, 73–82. [Google Scholar] [CrossRef]
- Nickerson, D.; Hunter, R.; Powell, M. New Automatic Colorimeter for Cotton. J. Opt. Soc. Am. 1950, 40, 446–449. [Google Scholar] [CrossRef]
- Xiong, Z.; Wang, X.; Gu, S.; Mao, L.; Zhang, L.; Zhou, Z. Reviews of the Cotton Fiber Quality Inspection and Evaluation in China. Cotton Sci. 2012, 24, 451–460. [Google Scholar]
- Sluijs, V.; Marinus, H.J. The influence of row unit settings and ground speed of modern spindle-type harvesters on cotton fibre and seed quality. J. Text. Inst. 2021, 112, 1904–1912. [Google Scholar] [CrossRef]
- Li, H.; Zhang, R.; Zhou, W.; Liu, X.; Wang, K.; Zhang, M.; Li, Q. A novel method for seed cotton color measurement based on machine vision technology. Comput. Electron. Agric. 2023, 215, 108381. [Google Scholar] [CrossRef]
- Zhang, C.; Li, T.; Li, J. Detection of Impurity Rate of Machine-Picked Cotton Based on Improved Canny Operator. Electronics 2022, 11, 974. [Google Scholar] [CrossRef]
- Thomasson, J.; Taylor, A. Color relationships between lint and seed cotton. Trans. ASAE 1995, 38, 13–22. [Google Scholar] [CrossRef]
- Cui, X.; Cai, Y.; Rodgers, J.; Martin, V.; Watson, M. An investigation into the intra-sample variation in the color of cotton using image analysis. Text. Res. J. 2014, 84, 214–222. [Google Scholar] [CrossRef]
- Guo, Z.; Zhang, Z.; Zhou, L. Analysis of cotton color visual detection system and its Influencing factors. Mach. Electron. 2022, 40, 3–7. [Google Scholar]
- Heng, C.; Chen, L.; Shen, H.; Wang, F. Study on the measurement and evaluation of cotton color using image analysis. Mater. Res. Express 2020, 7, 075101. [Google Scholar] [CrossRef]
- Juliano, P.; Francisio, A.C.; Daniel, M.; Flora, M.M.; Jayme, G.A.; Emerson, M. Deep learning architectures for semantic segmentation and automatic estimation of severity of foliar symptoms caused by diseases or pests. Biosyst. Eng. 2021, 210, 129–142. [Google Scholar]
- Afshin, A.; Yousef, A.; Edwige, V.; Richard, D.; Tarahom, M.; Hamid, A. Semantic segmentation: A modern approach for identifying soil clods in precision farming. Biosyst. Eng. 2020, 196, 172–182. [Google Scholar]
- Tiago, G.; Tiago, D.; Ricardo, F.M. Semantic Segmentation of Portuguese Agri-Forestry Using High-Resolution Orthophotos. Agronomy 2023, 13, 2741. [Google Scholar] [CrossRef]
- Wei, W.; Deng, D.; Zeng, L.; Zhang, C.; Shi, W. Classification of foreign fibers using deep learning and its implementation on embedded system. Int. J. Adv. Robot. Syst. 2019, 16, 172988141986760. [Google Scholar] [CrossRef]
- Xu, Y.; Wang, G.; Shao, L.; Wang, N.; She, L.; Liu, Y.; Geng, Y.; Yan, G. GlandSegNet: Semantic segmentation model and area detection method for cotton leaf pigment glands. Comput. Electron. Agric. 2023, 212, 108130. [Google Scholar]
- Mohamad, M. A New Winter Wheat Crop Segmentation Method Based on a New Fast-UNet Model and Multi-Temporal Senti-nel-2 Images. Agronomy 2024, 14, 2337. [Google Scholar] [CrossRef]
- Ibarra, J.; Rosa, F.; Ramirea, A. Color Dominance-Based Polynomial Optimization Segmentation for Identifying Tomato Leaves and Fruits. Agriculture 2024, 14, 1911. [Google Scholar] [CrossRef]
- Janakiramaiah, B.; Kalyani, G.; Karuna, A.; Prasad, L.N.; Krishna, M. Military object detection in defense using multi-level capsule networks. Soft Comput. 2023, 27, 1045–1059. [Google Scholar] [CrossRef]
- Singh, N.J.; Nongmeikapam, K. Semantic Segmentation of Satellite Images Using Deep-Unet. Arab. J. Sci. Eng. 2023, 28, 1193–1205. [Google Scholar] [CrossRef]
- Siddique, N.; Paheding, S.; Elkin, C.P.; Devabhaktuni, V. U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications. IEEE Access 2021, 9, 82031–82057. [Google Scholar] [CrossRef]
- Waldner, F.; Diakogiannis, F. Deep learning on edge: Extracting field boundaries from satellite images with a convolutional neural network. Remote Sens. Environ. 2020, 245, 111741. [Google Scholar] [CrossRef]
- Woo, S.; Park, J.; Lee, J.; Kweon, I. CBAM: Convolutional Block Attention Module. arXiv 2018, arXiv:1807.06521. [Google Scholar]
- Zhai, Z.; Chen, X.; Zhang, R.; Qiu, F.; Meng, Q.; Yang, J.; Wang, H. Evaluation of residual plastic film pollution in pre-sowing cotton field using UAV imaging and semantic segmentation. Front. Plant Sci. 2022, 13, 991191. [Google Scholar] [CrossRef]
- Szegedy, C.; Vanhoucke, V.; Ioffe, S.; Shlens, J.; Wojna, Z. Rethinking the inception architecture for computer vision. arXiv 2015, arXiv:1512.00567v3. [Google Scholar]
- Yang, B.; Lei, Y.; Jia, F.; Xing, S. An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings. Mech. Syst. Signal Process. 2019, 122, 692–706. [Google Scholar] [CrossRef]
- Heng, C.; Shen, H.; Wang, F.; Chen, Y. Calibrated color measurement of cashmere using a novel computer vision system. Measurement 2021, 185, 109991. [Google Scholar] [CrossRef]
- Goñi, S.; Salvadori, V. Color measurement: Comparison of colorimeter vs. computer vision system. J. Food Meas. Charact. 2017, 11, 538–547. [Google Scholar] [CrossRef]
- Hu, C.; Mei, H.; Guo, H.; Zhu, J. Color analysis of textile fibers by microspectrophotometry. Forensic Chem. 2020, 18, 100221. [Google Scholar] [CrossRef]
- Xu, B.; Fang, C.; Huang, R. Chromatic Image Analysis for Cotton Trash and Color Measurements. Text. Res. J. 1997, 67, 881–890. [Google Scholar] [CrossRef]
- Kang, T.; Kim, S. Objective evaluation of the trash and color of raw cotton by image processing and neural network. Text. Res. J. 2002, 72, 776–782. [Google Scholar] [CrossRef]
- Thpmasson, J. Effects of nonlint material on hvi color measurements. Am. Soc. Agric. Eng. 1990, 90, 1031. [Google Scholar]
- Matusiak, M.; Walawska, A. Important Aspects of Cotton Colour Measurement. Fibres Text. East. Eur. 2010, 3, 17–23. [Google Scholar]
- Wan, S.; Xiao, B.; Yu, J.; Li, K.; Guo, H. Effect of Moisture Regain on Color Grade During Cotton Storage. Cotton Text. Technol. 2019, 47, 49–51. [Google Scholar]
Model | PA (%) | F1-Score (%) | MIOU (%) | Time Cost (ms) | Parameters (107) |
---|---|---|---|---|---|
FCN | 93.87 | 85.28 | 83.33 | 121.50 | 2.01 |
SegNet | 93.58 | 84.03 | 82.42 | 232.20 | 2.95 |
DeepLabv3 | 93.86 | 85.00 | 83.10 | 276.30 | 3.38 |
Unet | 96.68 | 90.35 | 89.66 | 533.50 | 3.69 |
Color-Unet | 97.20 | 93.09 | 91.81 | 322.30 | 1.41 |
Model | PA (%) | F1-Score (%) | MIOU (%) | Time Cost (ms) | Parameters (107) |
---|---|---|---|---|---|
Unet | 96.68 | 90.35 | 89.66 | 533.54 | 3.69 |
IIEM-Unet | 96.87 | 91.68 | 90.55 | 382.17 | 2.53 |
CBAM-Unet | 96.94 | 92.02 | 90.83 | 326.04 | 2.33 |
Color-Unet | 97.20 | 93.09 | 91.81 | 322.30 | 1.41 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Li, H.; Li, Q.; Zhou, W.; Zhang, R.; Hong, S.; Zhang, M.; Zhai, Z. Measurement of Seed Cotton Color Using RGB Imaging and Color-Unet. Agronomy 2025, 15, 19. https://doi.org/10.3390/agronomy15010019
Li H, Li Q, Zhou W, Zhang R, Hong S, Zhang M, Zhai Z. Measurement of Seed Cotton Color Using RGB Imaging and Color-Unet. Agronomy. 2025; 15(1):19. https://doi.org/10.3390/agronomy15010019
Chicago/Turabian StyleLi, Hao, Qingxu Li, Wanhuai Zhou, Ruoyu Zhang, Shicheng Hong, Mengyun Zhang, and Zhiqiang Zhai. 2025. "Measurement of Seed Cotton Color Using RGB Imaging and Color-Unet" Agronomy 15, no. 1: 19. https://doi.org/10.3390/agronomy15010019
APA StyleLi, H., Li, Q., Zhou, W., Zhang, R., Hong, S., Zhang, M., & Zhai, Z. (2025). Measurement of Seed Cotton Color Using RGB Imaging and Color-Unet. Agronomy, 15(1), 19. https://doi.org/10.3390/agronomy15010019