Improved Multi-Plant Disease Recognition Method Using Deep Convolutional Neural Networks in Six Diseases of Apples and Pears

Round 1

Reviewer 1 Report

This manuscript proposed Improved multi-plant disease recognition method using deep convolutional neural networks in six diseases for fruits. There are something not pretty clearly in the introduction part.

1. The author said the proposed model combines a KNN algorithm with more powerful deep features extracted from fine-tuned convolutional neural network. The author should accentuate his contributions, for example, should give the difference between the Improved network and the others in this manuscript.
2. It lacks analytical methodologies to support author’s innovation.

Author Response

Thank you for reviewing my manuscript.
I completely agree with the reviewer's comments and have made changes according to their opinions. Please read the attached letter for the revised content.

Author Response File: Author Response.pdf

Reviewer 2 Report

Dear Authors,

I revised the manuscript "Improved multi-plant disease recognition method using deep convolutional neural networks in six diseases of Apple and Pear" submitted to Agriculture journal. The topic of the manuscript is very interesting. Unfortunately, the weakest part of the manuscript is the discussion of results. In addition, I have some concerns, which need to be addressed .

General comment:

The editing (technical) side of the manuscript needs extensive improvement. There is blank space in many places, different font types are used, and text is bolded where it is not required.

Minor comments:

1. Subsection 2.1 should be at the beginning of Section 2.
2. Line 128-134. There is no specification of how many images were used for each class and disease name.
3. Page 5. Table 1. The table caption is missing. It can only be found on line 147.
4. Section "3. Experiments". This section should be included in Section 2. Furthermore, there is no description of the creation of a confusion matrix, which should be included in the results (Section 4).
5. Subsection "3.2. Performance metrics". Consider adding additional performance measures - i.e. Recall and F1 Score.
6. Line 249. The caption of Table 2 should be directly above the table.

Major comment:

Section "4. Results and discussion". This section must be expanded. You must also compare your results with other papers. Scientific work needs a real discussion of results! Additional references are also required.

Author Response

Thank you for reviewing my manuscript.
I completely agree with the reviewer's comments and have made changes according to their opinions. Please read the attached letter for the revised content.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Thanks the authors address all my issues. I think these responds are satisfied. 

Reviewer 2 Report

Dear authors,
all my concerns have been addressed.
In the future, take care to record data to enable further analysis.