{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T20:43:03Z","timestamp":1790714583805,"version":"4.1.0"},"reference-count":51,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Fujian Agriculture and Forestry University","award":["KFB23040"],"award-info":[{"award-number":["KFB23040"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Plants"],"abstract":"<jats:p>As a crop with significant medicinal value and nutritional components, the market demand for bitter melon continues to grow. The diversity of bitter melon shapes has a direct impact on its market acceptance and consumer preferences, making precise identification of bitter melon germplasm resources crucial for breeding work. To address the limitations of time-consuming and less accurate traditional manual identification methods, there is a need to enhance the automation and intelligence of bitter melon phenotype detection. This study developed a bitter melon phenotype detection model named CSW-YOLO. By incorporating the ConvNeXt V2 module to replace the backbone network of YOLOv8, the model\u2019s focus on critical target features is enhanced. Additionally, the SimAM attention mechanism was introduced to compute attention weights for neurons without increasing the parameter count, further enhancing the model\u2019s recognition accuracy. Finally, WIoUv3 was introduced as the bounding box loss function to improve the model\u2019s convergence speed and positioning capabilities. The model was trained and tested on a bitter melon image dataset, achieving a precision of 94.6%, a recall of 80.6%, a mAP50 of 96.7%, and an F1 score of 87.04%. These results represent improvements of 8.5%, 0.4%, 11.1%, and 4% in precision, recall, mAP50, and F1 score, respectively, over the original YOLOv8 model. Furthermore, the effectiveness of the improvements was validated through heatmap analysis and ablation experiments, demonstrating that the CSW-YOLO model can more accurately focus on target features, reduce false detection rates, and enhance generalization capabilities. Comparative tests with various mainstream deep learning models also proved the superior performance of CSW-YOLO in bitter melon phenotype detection tasks. This research provides an accurate and reliable method for bitter melon phenotype identification and also offers technical support for the visual detection technologies of other agricultural products.<\/jats:p>","DOI":"10.3390\/plants13233329","type":"journal-article","created":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T11:26:08Z","timestamp":1732706768000},"page":"3329","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Improved CSW-YOLO Model for Bitter Melon Phenotype Detection"],"prefix":"10.3390","volume":"13","author":[{"given":"Haobin","family":"Xu","sequence":"first","affiliation":[{"name":"College of Horticulture, Fujian Agriculture and Forestry University, Fuzhou 350002, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianhua","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Horticulture, Fujian Agriculture and Forestry University, Fuzhou 350002, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weilin","family":"Shen","sequence":"additional","affiliation":[{"name":"College of Horticulture, Fujian Agriculture and Forestry University, Fuzhou 350002, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqiang","family":"Lin","sequence":"additional","affiliation":[{"name":"Fujian Agricultural Machinery Extension Station, Fuzhou 350002, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Horticulture, Fujian Agriculture and Forestry University, Fuzhou 350002, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Jia","sequence":"additional","affiliation":[{"name":"Jiuquan Academy of Agriculture Sciences, Jiuquan 735099, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Honglong","family":"Li","sequence":"additional","affiliation":[{"name":"Fujian Tianmei Seed Industry Technology Co., Fuzhou 350109, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyuan","family":"Zheng","sequence":"additional","affiliation":[{"name":"Institute of Vegetables, Hunan Academy of Agricultural Sciences, Changsha 410125, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fenglin","family":"Zhong","sequence":"additional","affiliation":[{"name":"College of Horticulture, Fujian Agriculture and Forestry University, Fuzhou 350002, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"ref_1","first-page":"2488","article-title":"Comprehensive Evaluation of Agronomic Traits of Bitter Gourd Germplasm Resources under High Temperature Conditions in Summer","volume":"51","author":"Li","year":"2020","journal-title":"J. South. Agric."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"625546","DOI":"10.3389\/fphar.2021.625546","article-title":"Three selected edible crops of the genus Momordica as potential sources of phytochemicals: Biochemical, nutritional, and medicinal values","volume":"12","author":"Muronga","year":"2021","journal-title":"J. Front. Pharmacol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1186\/s43014-022-00089-x","article-title":"A comprehensive review on bitter gourd (Momordica charantia L.) as a gold mine of functional bioactive components for therapeutic foods","volume":"4","author":"Gayathry","year":"2022","journal-title":"J. Food Prod. Process. Nutr."},{"key":"ref_4","first-page":"142","article-title":"Research progress in application of near infrared reflectance spectroscopy in vegetable quality detection","volume":"48","author":"Xue","year":"2021","journal-title":"J. Guangdong Agric. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1016\/j.compag.2019.01.012","article-title":"Apple detection during different growth stages in orchards using the improved YOLO-V3 model","volume":"157","author":"Tian","year":"2019","journal-title":"J. Comput. Electron. Agric."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"118573","DOI":"10.1016\/j.eswa.2022.118573","article-title":"Fruit detection and positioning technology for a Camellia oleifera C. Abel orchard based on improved YOLOv4-tiny model and binocular stereo vision","volume":"211","author":"Tang","year":"2023","journal-title":"J. Expert Syst. Appl."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"13895","DOI":"10.1007\/s00521-021-06029-z","article-title":"A detection algorithm for cherry fruits based on the improved YOLO-v4 model","volume":"35","author":"Gai","year":"2023","journal-title":"J. Neural Comput. Appl."},{"key":"ref_8","first-page":"145","article-title":"Online detection of citrus surface defects using improved YOLOv7 modeling","volume":"39","author":"Jia","year":"2023","journal-title":"J. Trans. Chin. Soc. Agric. Eng."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Aich, S., and Stavness, I. (2017, January 22\u201329). Leaf counting with deep convolutional and deconvolutional networks. Proceedings of the IEEE International Conference on Computer Vision Workshops, Venice, Italy.","DOI":"10.1109\/ICCVW.2017.244"},{"key":"ref_10","first-page":"29","article-title":"Classification and Identification of Succulent Plants Based on WPA-SVM","volume":"36","author":"Wang","year":"2020","journal-title":"J. Microcomput. Appl."},{"key":"ref_11","first-page":"176","article-title":"Identification model of pests on Yuluxiang pear leaves based on TACNN","volume":"57","author":"Zhao","year":"2021","journal-title":"J. Comput. Eng. Appl."},{"key":"ref_12","first-page":"132","article-title":"A tree segmentation method based on ResNet-UNet","volume":"41","author":"Tong","year":"2021","journal-title":"J. Cent. South Univ. For. Technol."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Lobo Torres, D., Queiroz Feitosa, R., Nigri Happ, P., Cu\u00e9 La Rosa, L.E., Marcato Junior, J., Martins, J., Ol\u00e3 Bressan, P., Gon\u00e7alves, W.N., and Liesenberg, V. (2020). Applying fully convolutional architectures for semantic segmentation of a single tree species in urban environment on high resolution UAV optical imagery. J. Sens., 20.","DOI":"10.3390\/s20020563"},{"key":"ref_14","first-page":"234","article-title":"Camellia oleifera Fruit Detection in Natural Scene Based on YOLO v5s","volume":"53","author":"Song","year":"2022","journal-title":"J. Trans. Chin. Soc. Agric. Mach."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1007\/s11119-019-09679-1","article-title":"Detection and counting of flowers on apple trees for better chemical thinning decisions","volume":"21","author":"Farjon","year":"2020","journal-title":"J. Precis. Agric."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.biosystemseng.2023.11.008","article-title":"An improved YOLO algorithm for detecting flowers and fruits on strawberry seedlings","volume":"237","author":"Bai","year":"2024","journal-title":"J. Biosyst. Eng."},{"key":"ref_17","first-page":"1916","article-title":"Research on Identification of Succulents Based on Lightweight Convolutional Neural Network","volume":"36","author":"Sun","year":"2023","journal-title":"J. Chin. J. Sens. Actuators"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"108205","DOI":"10.1016\/j.compag.2023.108205","article-title":"Lightweight green citrus fruit detection method for practical environmental applications","volume":"215","author":"Lu","year":"2023","journal-title":"J. Comput. Electron. Agric."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"108728","DOI":"10.1016\/j.compag.2024.108728","article-title":"Optimizing tomato plant phenotyping detection: Boosting YOLOv8 architecture to tackle data complexity","volume":"218","author":"Solimani","year":"2024","journal-title":"J. Comput. Electron. Agric."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"107576","DOI":"10.1016\/j.compag.2022.107576","article-title":"Small unopened cotton boll counting by detection with MRF-YOLO in the wild","volume":"204","author":"Liu","year":"2023","journal-title":"J. Comput. Electron. Agric."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"106847","DOI":"10.1016\/j.cropro.2024.106847","article-title":"YOLOv8-ECFS: A lightweight model for weed species detection in soybean fields","volume":"184","author":"Niu","year":"2024","journal-title":"J. Crop Prot."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Choudhary, H., Padmanabha, K., Jat, G.S., and Behera, T.K. (2023). Challenges of Traditional Breeding in Watermelon. The Watermelon Genome, Springer International Publishing.","DOI":"10.1007\/978-3-031-34716-0_7"},{"key":"ref_23","unstructured":"Yang, S., Xiao, W., Zhang, M., Guo, S., Zhao, J., and Shen, F. (2022). Image data augmentation for deep learning: A survey. arXiv."},{"key":"ref_24","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Yi, W., Zhang, X., Dai, S., Kuzmin, S., Gerasimov, I., and Cheng, X. (2024). MV-SSRP: Machine Vision Approach for Stress\u2013Strain Measurement in Rice Plants. J. Agron., 14.","DOI":"10.3390\/agronomy14071443"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"102709","DOI":"10.1016\/j.ecoinf.2024.102709","article-title":"Automatic detection of color markings and numbers on trees in point clouds from Personal Laser Scanning (PLS) and Terrestrial Laser Scanning (TLS)","volume":"82","author":"Wagner","year":"2024","journal-title":"J. Ecol. Inform."},{"key":"ref_27","first-page":"1918004","article-title":"Advances in computational optics based on deep learning","volume":"48","author":"Wang","year":"2021","journal-title":"J. Chin. J. Lasers"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Xia, K., Hu, J., Wang, Z., Wang, Z.J., Huang, Z., and Liang, Z. (2024). Vision-Based Algorithm for Precise Traffic Sign and Lane Line Matching in Multi-Lane Scenarios. J. Electron., 13.","DOI":"10.3390\/electronics13142773"},{"key":"ref_29","first-page":"113","article-title":"Unmanned Aerial Vehicle Image Target Detection Algorithm BasedonYOLOv8","volume":"50","author":"Zhao","year":"2024","journal-title":"J. Comput. Eng."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Woo, S., Debnath, S., Hu, R., Chen, X., Liu, Z., Kweon, I.S., and Xie, S. (2023, January 18\u201322). Convnext v2: Co-designing and scaling convnets with masked autoencoders. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canda.","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Chen, Y., Xu, H., Chang, P., Huang, Y., Zhong, F., Jia, Q., Chen, L., Zhong, H., and Liu, S. (2024). CES-YOLOv8: Strawberry Maturity Detection Based on the Improved YOLOv8. J. Agron., 14.","DOI":"10.3390\/agronomy14071353"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, Z., Zhang, F., Wei, Z., Huang, Y., Chen, C., Zheng, Y., Wei, Q., Sun, H., and Chen, F. (2024). Research on detection of potato varieties based on spectral imaging analytical algorithm. J. Spectrochim. Acta Part A Mol. Biomol. Spectrosc., 311.","DOI":"10.1016\/j.saa.2024.123966"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Lei, K., Tan, Z., Wang, X., and Zhou, Z. (2024). Semi-Symmetrical, Fully Convolutional Masked Autoencoder for TBM Muck Image Segmentation. J. Symmetry, 16.","DOI":"10.3390\/sym16020222"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"111482","DOI":"10.1016\/j.knosys.2024.111482","article-title":"MaxCerVixT: A novel lightweight vision transformer-based Approach for precise cervical cancer detection","volume":"289","author":"Pacal","year":"2024","journal-title":"J. Knowl.-Based Syst."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"e2271","DOI":"10.7717\/peerj-cs.2271","article-title":"Research on marine flexible biological target detection based on improved YOLOv8 algorithm","volume":"10","author":"Tian","year":"2024","journal-title":"J. PeerJ Comput. Sci."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Zhou, L., Zhao, H., Liu, Z., Cai, K., Liu, Y., and Zuo, X. (2023). MHLDet: A Multi-Scale and High-Precision Lightweight Object Detector Based on Large Receptive Field and Attention Mechanism for Remote Sensing Images. J. Remote Sens., 15.","DOI":"10.3390\/rs15184625"},{"key":"ref_37","unstructured":"Yang, L., Zhang, R.Y., Li, L., and Xie, X. (2021, January 18\u201324). Simam: A simple, parameter-free attention module for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Virtual."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Liu, Q., Huang, W., Duan, X., Wei, J., Hu, T., Yu, J., and Huang, J. (2023). DSW-YOLOv8n: A new underwater target detection algorithm based on improved YOLOv8n. J. Electron., 12.","DOI":"10.20944\/preprints202308.1729.v1"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Li, X., and Liang, Y. (2024). Fire-RPG: An Urban Fire Detection Network Providing Warnings in Advance. J. Fire, 7.","DOI":"10.3390\/fire7070214"},{"key":"ref_40","unstructured":"Tong, Z., Chen, Y., Xu, Z., and Yu, R. (2023). Wise-IoU: Bounding box regression loss with dynamic focusing mechanism. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Wang, S., Yao, L., Xu, L., Hu, D., Zhou, J., and Chen, Y. (2024). An Improved YOLOv7-Tiny Method for the Segmentation of Images of Vegetable Fields. J. Agric., 14.","DOI":"10.3390\/agriculture14060856"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"32927","DOI":"10.1109\/ACCESS.2024.3365559","article-title":"Research on a Lightweight Method for Maize Seed Quality Detection Based on Improved YOLOv8","volume":"12","author":"Niu","year":"2024","journal-title":"J. IEEE Access"},{"key":"ref_43","unstructured":"Zhao, Y., Wang, J.K., Lin, Z.Y., Zhou, Z.X., and Xu, S. (2024, October 22). Steel Surface Defect Detection Algorithm Based on Improved YOLOv8n[J\/OL]. Electronic Measurement Technology. Available online: http:\/\/kns.cnki.net\/kcms\/detail\/11.2175.TN.20240927.1434.158.html."},{"key":"ref_44","unstructured":"Zhang, C.Y., Zhang, S., Hu, Y.M., Zhang, Y., and Xiong, R.Y. (2024, October 22). Dynamic Focusing Multidimensional Attention Remote Sensing Weak Target Detection[J\/OL]. Radio Communications Technology. Available online: http:\/\/kns.cnki.net\/kcms\/detail\/13.1099.tn.20240822.1338.002.html."},{"key":"ref_45","first-page":"34","article-title":"Visualizing the Unseen: Exploring GRAD-CAM for Interpreting Convolutional Image Classifiers","volume":"4","author":"Kumar","year":"2023","journal-title":"J. Full Length Artic."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Hussain, T., and Shouno, H. (2023). Explainable Deep Learning Approach for Multi-Class Brain Magnetic Resonance Imaging Tumor Classification and Localization Using Gradient-Weighted Class Activation Mapping. J. Inf., 14.","DOI":"10.3390\/info14120642"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Zuo, Z., Gao, S., Peng, H., Xue, Y., Hao, L., Ma, G., and Mao, H. (2024). Lightweight Detection of Broccoli Heads in Complex Field Environments Based on LBDC-YOLO. J. Agron., 14.","DOI":"10.2139\/ssrn.4740379"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Koh, J.C.O., Spangenberg, G., and Kant, S. (2021). Automated machine learning for high-throughput image-based plant phenotyping. J. Remote Sens., 13.","DOI":"10.3390\/rs13050858"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Tripodi, P., Nicastro, N., Pane, C., and Cammarano, D. (2022). Digital applications and artificial intelligence in agriculture toward next-generation plant phenotyping. J. Crop Pasture Sci., 74.","DOI":"10.1071\/CP21387"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"7507131","DOI":"10.34133\/2019\/7507131","article-title":"Plant phenotyping: Past, present, and future","volume":"2019","author":"Pieruschka","year":"2019","journal-title":"J. Plant Phenomics"},{"key":"ref_51","first-page":"1","article-title":"Computer vision technology in agricultural automation\u2014A review","volume":"7","author":"Tian","year":"2020","journal-title":"J. Inf. Process. Agric."}],"container-title":["Plants"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2223-7747\/13\/23\/3329\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:41:04Z","timestamp":1760114464000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2223-7747\/13\/23\/3329"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"references-count":51,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["plants13233329"],"URL":"https:\/\/doi.org\/10.3390\/plants13233329","relation":{},"ISSN":["2223-7747"],"issn-type":[{"value":"2223-7747","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,27]]}}}