What question did this study set out to answer?

To develop an intelligent model for accurate detection of bitter gourd fruit morphology and tubercle characteristics.

January 15, 2026Scientific Reports0 citationsOpen Access

Intelligent high-throughput recognition model for bitter gourd fruit morphology and tubercle characteristics

SLShuang LiuBeijing Luhe Hospital Affiliated to Capital Medical University YCYixin CaiFujian Agriculture and Forestry University HXHaobin XuFujian Agriculture and Forestry University

Key Points

To develop an intelligent model for accurate detection of bitter gourd fruit morphology and tubercle characteristics.
Developed YOLOv8-CEFC model integrating ConvNeXt V2 and FCMAE for feature extraction.
Utilized Efficient Multi-scale Attention to capture tubercle textures and fruit shapes.
Incorporated Focal-CIoU Loss to address class imbalance issues.
Achieved precision of 93.9% and recall of 94.4%.
Recorded improvements in mAP50, mAP50-95, and F1 scores compared to original YOLOv8n model.
Confirmed statistical significance of improvements using the bootstrap method.

Abstract

Bitter gourd, an important crop with both economic and medicinal value, requires precise identification of fruit shape and tubercle phenotypes to enhance breeding efficiency. To address the low efficiency and high subjectivity of traditional methods, this study proposes an improved YOLOv8-CEFC model for high-throughput automatic detection of the bitter gourd fruit shape and tubercle characteristics. First, the model integrates the ConvNeXt V2 module into the backbone network, combined with a Fully Convolutional Masked Autoencoder (FCMAE) framework and Global Response Normalization (GRN) layers to enhance feature extraction capabilities. Second, an Efficient Multi-scale Attention (EMA) mechanism is introduced, capturing local tubercle textures and global fruit shape contours simultaneously through a parallel dual-branch structure, while also improving the model’s robustness against cluttered backgrounds and environmental noise. Finally, Focal-CIoU Loss is incorporated to replace CIoU Loss, reducing the impact of class imbalance on model accuracy. The results show that the model achieves precision, recall, mAP50, mAP50-95, and F1 scores of 93.9%, 94.4%, 96.3%, 93.6%, and 94.15%, respectively, which represent improvements of 2.0%, 3.5%, 1.1%, 3.4%, and 2.75% compared to the original YOLOv8n model. The performance gain of the model was further examined using the bootstrap method, which confirmed that the improvement is statistically significant. Further validation through confusion matrix analysis, PR curves, and ablation experiments confirms the effectiveness of the improvements. Compared to other mainstream YOLO models, YOLOv8-CEFC demonstrates more accurate identification, better stability, and higher detection efficiency. The proposed improved YOLOv8-CEFC model provides an efficient solution for phenotypic analysis in Bitter Gourd breeding and holds significant importance for advancing the intelligentization of crop breeding.

Ask AI

Helpful

Bookmark

View Full Paper