基于改进版Faster-RCNN的复杂背景下桃树黄叶病识别研究
Recognition of peach tree yellow leaf disease under complex background based on improved Faster-RCNN
张平川 1胡彦军 2张烨 3张彩虹 1陈昭 1陈旭1
作者信息
- 1. 河南科技学院计算机科学技术学院,河南新乡,453003
- 2. 河南科技学院计算机科学技术学院,河南新乡,453003;河南科技大学应用工程学院,河南三门峡,472099;新乡学院机电工程学院,河南新乡,453003
- 3. 新乡学院机电工程学院,河南新乡,453003
- 折叠
摘要
由于桃树黄叶病(以下简称PTYLD)初期症状不明显,现有的基于深度学习的桃树病害识别技术,存在识别准确率不高、识别品种单一的问题,提出一种基于Faster-RCNN的PTYLD识别模型.为提高模型对PTYLD识别准确率和识别多样性,提出使用RS-Loss函数代替RPN中的交叉熵函数、使用Soft-NMS算法代替原来的NMS算法,来改进Faster-RCNN.通过试验对比初始版和改进版Faster-RCNN对PTYLD的识别效果.试验结果显示,改进后的Faster-RCNN对黄叶病识别的各类别平均准确率mAP达90.56％、召回率达94.16％、准确率达92.53％,能识别常见的五种PTYLD.
Abstract
Since the initial symptoms of Peach Tree Yellow Leaf Disease(PTYLD)are not readily apparent,the existing deep learning-based recognition techniques for this disease suffer from issues like inaccurate recognition and limited recognition species.To address this,a recognition model of PTYLD based on Faster-RCNN(Region-based Convolutional Neural Network)is proposed.In order to enhance the recognition accuracy and diversity of PTYLD,RS-Loss function is used to replace the cross-entropy function in the Region Proposal Network(RPN),and the Soft-NMS algorithm is used to replace the original Non-Maximum Suppression(NMS)algorithm,so as to improve Faster-RCNN.The recognition effect of the initial and improved version of Faster-RCNN models on PTYLD is compared by experiments.The experimental results demonstrate that the improved Faster-RCNN achieves a mean average precision(mAP)of 90.56％,recall rate of 94.16％,an accuracy of 92.53％for each category of yellow leaf disease,and can identify five common PTYLD.
关键词
桃树黄叶病/Faster-RCNN/复杂背景/软性非极大值抑制算法Key words
peach tree yellow leaf disease/Faster-RCNN/complex background/Soft-NMS引用本文复制引用
基金项目
河南省科技厅科技攻关计划(222102210116)
河南省科技厅科技攻关计划(212102310553)
出版年
2024
国家科技期刊平台
NSTL
维普
万方数据