基于YOLOv5的黑色素瘤图像检测仿真
Simulation of Melanoma Image Detection Based on YOLOv5
刘勇志 1万方 1雷光波 1徐丽1
作者信息
- 1. 湖北工业大学计算机学院,湖北 武汉 430068
- 折叠
摘要
针对黑色素瘤疾病在临床上存在检测准确率低以及人为主观性太强等问题,提出一种改进的YOLOv5 目标检测模型BiC-YOLOv5.首先设计了一种双向特征提取网络BiFPN-L3 替换原模型中的特征提取网络FPN,针对不同分辨率下的特征,使用多尺度特征融合的方式提取特征;其次,在骨干网络中融合CBAM注意力模块,设计了一种C3CBAM模块从通道与空间两个层面捕获特征信息以提升检测精度;最后,使用DIOU_loss损失函数,进一步提高模型的检测精度.通过仿真对比实现,BiC-YOLOv5 的mAP值达到95.2%,相较原YOLOv5 模型,精确度提高了 5.2%,召回率提高了 4.9%,mAP 值提高了5.8%,可以有效的协助临床医学对黑色素瘤进行诊断.
Abstract
To address the problems of low detection accuracy and too much human subjectivity in melanoma dis-ease in clinical practice,an improved YOLOv5 target detection model BiC-YOLOv5 is proposed.Firstly,a bidirec-tional feature extraction network BiFPN-L3 was designed to replace the feature extraction network FPN in the original model,and a multi-scale feature fusion was used to extract features at different resolutions.Second,a CBAM attention module was fused in the backbone network,and a C3CBAM module was designed to capture feature information from both channel and space levels to improve detection accuracy;Finally,the DIOU_loss loss function was used to further improve the detection accuracy of the model.Through simulation comparison,the mAP value of BiC-YOLOv5 reached 95.2%,which is an improvement of 5.2%in accuracy,4.9%in recall,and 5.8%in mAP value compared to the o-riginal YOLOv5 model.This can effectively assist clinical medicine in diagnosing melanoma.
关键词
特征提取网络/注意力机制/黑色素瘤/皮肤镜图像Key words
Feature extraction network/Attention mechanism/Melanoma/Dermoscopic images引用本文复制引用
基金项目
湖北省教育厅指导性项目(B2021070)
出版年
2024
NETL
NSTL
万方数据