TAME-Faster R-CNN model for Image-based Tea Diseases Detection
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".