TAME-Faster R-CNN model for Image-based Tea Diseases Detection

• 全文链接

基于图像的茶病害检测的TAME-Faster R-CNN模型

关键词：

来源：

CCECE 2024 会议

全文链接：

//agri.nais.net.cn/topic/downloadFile/e2e12dd3-9c26-44b8-b237-4115db5e171e

来源地址：

https://ieeexplore.ieee.org/document/10667130

资源所属：

茶学研究专题

类型：

会议论文

语种：

英语

原文发布日期：

2024-09-24

摘要：

Tea, one of the most consumed non-alcoholic beverages in the world, plays an essential role in the agricultural economy. Nevertheless, it is threatened by various diseases, resulting in critical yields and economic losses. Nowadays, image processing techniques and machine vision algorithms are used to detect tea diseases. However, the existing techniques do not consider the varying lighting (such as shadow) conditions in the data set, which makes the techniques less efficient and robust. Therefore, this paper aims to address these issues by proposing an efficient technique called, TAME-Faster R-CNN. The proposed method combines a trainable Attention Mechanism for Explanations (TAME) module with the backbone network of the Faster R-CNN framework to detect three types of tea diseases (Anthracnose, Brown leaf spot, and Tea white scab). The experimental results and analysis show that the proposed algorithm achieved mAP values of 98.3% to detect Anthracnose, 64.8% to detect Brown leaf spots, and 75.6% to detect white scab diseases and performed better than the state-of-the-art technique. Total mAP is almost 10%, 23% and 1% higher compared to Yolov5, Yolov7 and original Faster R-CNN, respectively. Compared to the original framework of Faster R-CNN, TAME-Faster R-CNN with ResNet101 has improved the precision and F1 score on average by 6% and 4.3%, respectively. Hence, the integration of this technique can effectively detect tea lesion diseases.