Intelligent Measurement of Morphological Characteristics of Fish Using Improved U-Net
Round 1
Reviewer 1 Report
A well-prepared and valuable scientific paper. However, it is worth improving it as suggested below:
- It is worth defining the relative error equally throughout the article. For the tag, it should be made uniform and in Tables 1, 2 and 3 and in Figs. 14, 16, 18, 19 and 20 it should be expressed as a percentage [%] as it is in many places in the body text.
- It would be worth redrafting the section "5. Conclusions and future work" so that it accurately and without doubt presents the valuable achievements described in the text.
Author Response
Please see the attached PDF file for the response to reviewer 1 comments.
Author Response File: Author Response.pdf
Reviewer 2 Report
This work presents an artificial intelligence methodology (i.e., improved U-net) to classify morphological traits of fish to simplify mariculture breeding operations.
Generally, the article is poorly structured (e.g., introduction, materials and methods, etc. are very confused). There is not an aim that specifies the scope of the work. The whole article introduction is not very contextualized: you are talking about specific precision aquaculture activities, but these are not mentioned.
In addition, the work is quite obsolete: nowadays there are many methods using underwater cameras, stereovision technologies, etc., which automatically calculate all the features reported in this study directly in the rearing tanks.
I will consider the work for a publication only if a thorough review will be done.
Minor comments
Not all acronyms are spliced. Report either an initial table with all the explanations acronyms or always specify them before writing.
Generally, figure’s captions are not very detailed and explanatory.
Do not use the same words as the title in the abstract.
Major comments
Introduction
L.20-32: Everything that has been included in this paragraph refers to a very specific activity: precision aquaculture. Insert a conspicuous paragraph describing this activity to better contextualize the work.
L.33-59: YOLOs have also been used for similar purposes. Give some examples.
Mention the presence of many methods using underwater cameras, stereovision technologies, etc., calculating all the features useful for improving breeding, automatically directly in the rearing tanks.
From L.60: all this part must be included in the materials and methods.
There is no real aim. Insert it to make the activity more understandable.
Paragraph 2
Organize the structure in introduction, materials and methods etc. to better understand what you read.
Conclusions
This section is not well organized.
Author Response
Please see the attached PDF file for the response to reviewer 2 comments.
Author Response File: Author Response.pdf
Round 2
Reviewer 2 Report
The manuscript in the present form can be published in Electronics as the authors have been improved it. Parts that better contextualize the work have been added (e.g., precision aquaculture applications) and the fact of not adding some required details has been well justified (e.g., YOLO). The methodology has been better specified and abstract, introduction, aim and discussion are now clearer. Finally, the information in the figure and table captions are now expanded as suggested.
I don’t need to review another version because I accept the work in the present form.