Review Reports

Round 1

Reviewer 1 Report

Please see the attached file. 

Comments for author File: Comments.pdf

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

Proposed manuscript "Sugarcane stem node recognition in field by deep learning combining data expansion" deals an interesting topic of sugarcane  nodes identification with high accuracy. The main tool for identfication is presented by CNN (in the mode of supervised learning). Authors brings new methodology which is tested on new dataset.

The manuscript in present form is in good quality and I have following minor comments:

1) The level of English should be improved. I recommend a professional proof-reading.

2) Why did you choose Python environment? Is it good choise for application like this one?

3) Do you plan the extension to unsupervised learning? It would be more complicated but more rubust

Owing fact mentiond above I recommend accept the manuscript after MINIR REVISION.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 3 Report

The study is well approached and nicely written. Congratulations.  Introduction could use a bit more references. Related approaches to a similar problem can be found here.
https://www.sciencedirect.com/science/article/abs/pii/S0168169921000168
https://www.mdpi.com/1424-8220/21/11/3813

The problem is interesting and the addressed solution is good, however, there is not much novelty, or it is not clear to the reader. It seems that YOLOv4 is used as is. Comparison of different approaches would be useful if there is a proposed architecture or a novel methodology. A novelty in methodology or approach should be clearer.

Fix these issues and I will be happy to accept this paper.
Best,

Author Response

Please see the attachment.

Author Response File: Author Response.pdf