All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.
Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.
The article is accepted for publication.
The authors should improve the description of the neural network in the revised version of the manuscript.
The authors have improved the clarity and the discussions raised showing sufficient knowledge in the field background.
Authors have further shown satisfactory and detailed discussion of all the methodology steps in the proposed Faster R-CNN.
Authors have shown from the comparison table of the experimental results, that the performance of Faster R-CNN framework was effective in the real-time detection of Rice Leaf Diseases when compared with some of the state-of-the-art methods.
Authors have carefully addressed all the issues raised in previous comments.
This is a well-written paper containing interesting results which merit publication. For the benefit of the reader, however, certain statements require further justification. There are given below.
1. In the Model architecture with Faster R-CNN part, more mathematical inference can help readers understand the network.
2. More detail can be shown about the architecture of CNN and ROI in Figure 4.
no comment
no comment
no comment
Recent state-of-the-art works on plant leaf recognition must be discussed. The novelty and contribution of the paper must be explicitly stated. The results achieved should be compared with experimental results from related studies.
[# PeerJ Staff Note: Please ensure that all review comments are addressed in a rebuttal letter and any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate. It is a common mistake to address reviewer questions in the rebuttal letter but not in the revised manuscript. If a reviewer raised a question then your readers will probably have the same question so you should ensure that the manuscript can stand alone without the rebuttal letter. Directions on how to prepare a rebuttal letter can be found at: https://peerj.com/benefits/academic-rebuttal-letters/ #]
[# PeerJ Staff Note: The review process has identified that the English language must be improved. PeerJ can provide language editing services - please contact us at [email protected] for pricing (be sure to provide your manuscript number and title) #]
No comment
1. Your description of Sub-section "Data collection" is not explanatory enough. Since the experiment was done using two datasets, the first dataset was collected from online database (Kaggle database) and the second database is a primary dataset. Give a detailed summary of the total number of images collected from each database (you can use a Table).
2. For a better view and understanding of the different steps involved in your methodology. Kindly insert all the different stages steps in a textbox with appropriate caption such as:
• The steps of Faster R-CNN:
• RPNs for candidate regions
• Training processes: Faster R-CNN training model:
This would help the reader understand the steps better.
3. Improve discussion of your findings in figures 6 and 7 of Section: Detection and visualization and failure analysis.
4. Figure 9 shows the confusion matrix, it is expected to more detailed as the rate of misclassification of each class is not specified on the figure. Use a more labelled confusion matrix showing the wrong predictions on each class.
1. To identify the validity of your findings, it is expected that the results achieved should be compared with experimental results from related studies. Since an online/ publicly available dataset was used (Kaggle database).
2. Highlights what are the limitations or challenges of your model and how it affects the overall performance.
The paper is very interesting to read with the aim of addressing the challenges of real-time rice leaves disease spot identification using Deep Learning-based Faster R-CNN Framework.
The English language should be improved to ensure that an international audience can clearly understand your text. Some examples where the language could be improved include lines 164-165, 262 the current phrasing makes comprehension difficult.
The summary of the existing technology in the introduction is not comprehensive. I suggest you add a more detailed description in lines 112-116.
no comment
no comment
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.