Cotton seed quality plays a crucial role in agricultural productivity, fiber characteristics, and overall textile industry efficiency. In recent years, non-invasive and non-destructive measurement techniques have become one of the most promising directions for seed quality analysis due to their ability to preserve seed integrity while ensuring precise evaluation. This study provides a theoretical investigation and comprehensive overview of state-of-the-art computer vision and deep learning–based approaches applied in seed assessment. Special attention is given to modern detection frameworks, including YOLO-based architectures, convolutional attention mechanisms such as CBAM and SegNext, and instance segmentation techniques like SOLO and SOLOv2. Additionally, the effects of model parameters such as batch size on generalizability and the role of modular frameworks like MMDetection are discussed. The findings highlight that integrating non-destructive imaging with advanced neural models significantly improves accuracy, speed, and robustness in seed quality assessment processes.

Non-destructive measurement, cotton seeds, computer vision

Wang, A.; Chen, H.; Liu, L.; Chen, K.; Lin, Z.; Han, J.; Ding, G. YOLOv10: Real-Time End-to-End Object Detection. arXiv 2024. [CrossRef]

Lin, T.-Y.; Maire, M.; Belongie, S.; Hays, J.; Perona, P.; Ramanan, D.; Dollár, P.; Zitnick, C.L. Microsoft COCO: Common objects in context. ECCV 2014. [CrossRef]

Woo, S.; Park, J.; Lee, J.-Y.; Kweon, I.S. CBAM: Convolutional Block Attention Module. ECCV 2018. [CrossRef]

Guo, M.-H.; Lu, C.-Z.; Hou, Q.; Liu, Z.; Cheng, M.-M.; Hu, S.-M. SegNext: Rethinking convolutional attention design. NeurIPS 2022. [CrossRef]

Li, H.; Li, J.; Wei, H.; Liu, Z.; Zhan, Z.; Ren, Q. Slim-neck by GSConv. arXiv 2022. [CrossRef]

Chu, B.; Shao, R.; Fang, Y.; Lu, Y. Weed Detection Based on Improved YOLOv8. CAC 2023. [CrossRef]

Lin, B. Safety Helmet Detection Based on Improved YOLOv8. IEEE Access 2024. [CrossRef]

Kandel, I.; Castelli, M. Effect of Batch Size on CNN Generalizability. ICT Express 2020. [CrossRef]

Wang, X.; Kong, T.; Shen, C.; Jiang, Y.; Li, L. SOLO: Segmenting Objects by Locations. ECCV 2020. [CrossRef]

Wang,X.; Zhang, R.; Kong, T.; Li, L.; Shen, C. Solov2: Dynamic and fast instance segmentation. Adv. Neural Inf. Process. Syst. 2020, 33, 17721–17732. [CrossRef]. https://doi.org/10.48550/arXiv.2003.10152

Chen,K.; Wang, J.; Pang, J.; Cao, Y.; Xiong, Y.; Li, X.; Sun, S.; Feng, W.; Liu, Z.; Xu, J. MMDetection: Open mmlab detection toolbox and benchmark. arXiv 2019. [CrossRef].https://doi.org/10.48550/arXiv.1906.07155

Ugli, Y. A. A., Tokhirovich, B. H., & Abdujabborovich, Y. S. (2021). Research into the effect of stretching couples on the quality of thread in a ring spinning machine. ACADEMICIA: An International Multidisciplinary Research Journal, 11(3), 164-171.

Ergashev, Y., Xusanova, S., & Axmadjonov, D. (2022). Analysis of the fibre quality of cotton varieties grown by region. Gospodarka i Innowacje., 21, 242-244.

Ugli, Y. A. A., Tokhirovich, B. H., & Qambaraliyevich, Y. J. (2021). Analysis of changes in the physical and mechanical properties of twisted yarns as a result of finishing. ACADEMICIA: An International Multidisciplinary Research Journal, 11(3), 117-122.