Tea leaf disease detection and identification based on YOLOv7 (YOLO-T)

Abstract

A reliable and accurate diagnosis and identification system is required to prevent and manage tea leaf diseases. Tea leaf diseases are detected manually, increasing time and affecting yield quality and productivity. This study aims to present an artificial intelligence-based solution to the problem of tea leaf disease detection by training the fastest single-stage object detection model, YOLOv7, on the diseased tea leaf dataset collected from four prominent tea gardens in Bangladesh. 4000 digital images of five types of leaf diseases are collected from these tea gardens, generating a manually annotated, data-augmented leaf disease image dataset. This study incorporates data augmentation approaches to solve the issue of insufficient sample sizes. The detection and identification results for the YOLOv7 approach are validated by prominent statistical metrics like detection accuracy, precision, recall, mAP value, and F1-score, which resulted in 97.3%, 96.7%, 96.4%, 98.2%, and 0.965, respectively. Experimental results demonstrate that YOLOv7 for tea leaf diseases in natural scene images is superior to existing target detection and identification networks, including CNN, Deep CNN, DNN, AX-Retina Net, improved DCNN, YOLOv5, and Multi-objective image segmentation. Hence, this study is expected to minimize the workload of entomologists and aid in the rapid identification and detection of tea leaf diseases, thus minimizing economic losses.

Few‐shot object detection based on global context and implicit knowledge decoupled head

“…The primary objective of object detection is to accurately identify objects in an image or video and label their location. Recently, deep learning algorithms have been successfully deployed in practical applications such as pathology analysis [1], ore detection [2], tea disease detection [3], and crop weed detection [4]. However, obtaining a large amount of labelled data for training and testing is often necessary for deep‐learning object detection.…”

“…used a target localization method [1, 18]. (a) Few people have considered improving the neck part of the deep neural network model, which will limit model performance and increase code runtime [2–4]. (b) The high computational resource requirements of high‐resolution object detection [16, 17] hinder its widespread adoption in many enterprises.…”

Diagnosis of cervical lymphoma using a YOLO-v7-based model with transfer learning

“…YOLO-v7 leverages a trainable bag-of-freebies approach, enabling significant improvements in precision for real-time detection tasks without incurring additional inference costs. By integrating extend and compound scaling, it effectively reduce the number of parameters and calculations, resulting in a substantial acceleration of the detection rate 25 . To the best of our knowledge, no studies have applied this YOLO model to the diagnostic distinction of cervical lymphadenopathy.…”

Detection and identification of plant leaf diseases using YOLOv4

“…Although these models cannot recognize high-resolution images in real-time, faster R-CNN, consisting of region proposal networks (RPN) ( Chen and Wu, 2023 ) and classification networks, considerably decrease detection time. By combining target categorization and localization into a regression problem, the recently suggested You Only Look Once (YOLO) ( Soeb et al., 2023 ) method simplifies the problem. Due to its lack of RPN, YOLO employs regression to directly locate targets in the image, significantly improving its detection speed.…”