Lettuce Plant Trace-Element-Deficiency Symptom Identification via Machine Vision Methods

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

Manuscript, entitled (Lettuce plants trace element deficiency symptoms identifica- tion by machine vision methods).  The experiment shows that under the optimal feature extraction method (color), the Random Forest recognition results are the best, with an accuracy rate of 97.6%, a precision rate of 97.9%, a recall rate of 97.4%, and anF1 Score97.6%; The accuracy of all three deep learning models exceeds99.5%, among which ShuffleNet is the best, with accuracy, precision, recall, and F1 score of 99.9%, 99.9%, 99.9%, and 99.8%, respectively. There are shortcomings that should be included in order to enhance the manuscript for the readers.

Abstract

·   The introduction sentences of the abstract from line 10 to line 16 are too long. Please shorted them.

 

·         Please do not uses pronounce in scientific writing such as we captured in line 16.

Keywords:

should be arranged alphabetic.

Introduction

·   From line 33 to line 43 more citations need to be added. ·   No need to add Figure 1. Plant deficiency images to introduction. ·    No need to add the main contributions and works of this study. Lines from 127 to line140 are related to results and conclusion section. ·   The objective should be written in clear at the end of introduction. ·   Remove from line 141 to line 145. This is structure of the manuscript. ·   Materials and methods ·   Figure 3 should be replaced by clear image ·   Table 1 some errors types were found.       Results and Discussion   ·        The Results and Discussion is not supported by previous studies? It should be modified again. ·        Please, write the practical applications of your work in a separate section, before the conclusions. ·              Conclusions   ·        Please write about the limitations of this work in details. Comments on the Quality of English Language

Minor editing

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

Comments in the attached file

Comments for author File: Comments.pdf

Comments on the Quality of English Language

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

General comments:

The manuscript has several language issues, and it needs thorough proofreading and implementing necessary improvements. Some further improvements are needed also in presenting the results. There is no discussion on the findings of the study. A comparison of (accuracy) results of the methods used so far would be interesting and useful. Also, there is no limitation section to provide points of attention, barriers in identification of deficiencies or other issues that may exist. Given the complexity of the method presented, in discussion and conclusions authors must refer to the practical value of the proposed methodology. 

Detailed comments:

-  Line 17: Add a space before the parenthesis to “groups(potassium”

-  Line 24: Make the correction to “anF1”, I think it is “and F1”

-  Line 24 – 26: add spaces where needed.

-  Line 26: I think instead of “.. of 99.9%, 99.9%, 99.9%, and 99.8%, respectively” it is better this way: “above 99.8%)

-  Line 37: Please remove “web pages” and try to find images from publications. References must be added here. Current photos must be removed because what they present is irrelevant to the study. Also, please try to find lettuce nutrient deficiency disease images and not images from other plants.

-  Line 56: Improve English.

-  Line 63-66: Rewrite, makes no sense.

-  Lines 68 – 76: Try to find references related to lettuce. If you cannot find references with method accuracy results for detecting nutrient deficiency disease issues, then focus on references related to other leafy vegetables.

-  Line 153: Please add information about the experimental lab conditions.

-  Line 157: Provide more details about the nutrient solution used.

-  Line 158: Improve English.

-  Lines 160 – 162: improve English.

-  Line 165 – 180: improve English.

-  Lines 198 – 200: whenever you begin a sentence, please capitalize the first letter of the first word.

-  Line 374 – 377: Improve English.

-  Line 487: it is “discussion” not “discussions”.

-  Line 515: images, although different, look the same. Maybe they need to be enlarged a bit.

-  Line 524: consider enlarging the images; they look the same.

-  Line 560: “.. all ..” you must provide more information on what “all” means.

-  Line 564: “Compared with the previous tomato dataset ..". Why is this comparison made? 

-  Lines 564 – 584: Improve English, it makes no sense.

-  Line 574: Better change the following “.. the random forest has the best recognition effect compared with the other two algorithms.” to “.. the random forest has a slightly better recognition accuracy compared with the other two algorithms.” or just deduce that the three methods have almost the same accuracy performance.

-  Line 588: “Under different feature extraction methods, different lettuce nutrient deficiency physiological diseases have different recognition results”. Better presentation of the results is needed here regarding which deficiency is being better identified.

-  Line 600: “Table 6 represents the identification results of different lightweight models for lettuce 600 nutrient deficiency disease”. However, in line 611, Table 6 is about tomatoes: “Classification results of tomato disease with different light weighed models”.

-  Line 611: tomato?

-  Line 636 – 637: it needs to be explained better.

-  Line 643: literature comparison in results? I suggest you move part of the text to the introduction and remove table 7 or add it as supplementary material.

-  Line 644: "Table 7 lists other studies on the symptoms of deficiency in plants". I cannot see what the point is of referring to other studies in plants in general and not in lettuce. This table would be interesting and useful only if the comparison is about the same methods used in the experiment.

-  Line 652 – 659: This paragraph must be moved to introduction. There is no discussion. Please add a separate section and discuss the importance of your findings compared with the methods used so far. It would be interesting to make a comparison on the accuracy of the methods used so far and the accuracy of the methodology you propose.

-  Line 664: "Our study found that the color feature extraction method is the best". Although this is one of the main findings, it is not clear how it came about.

-  Line 674: "Different nutritional deficiencies can affect the morphological characteristics of lettuce leaves". Obviously yes, but this is not related to the topic of this manuscript, as you do not examine morphological characteristics at all. Please remove.

-  Line 675 – 677: Improve English.

-  Line 693: "achieved" instead of "realized"?

-  Lines 693 – 697: Improve English, it makes no sense.

-  Line 696: Replace “in non-ideal environments” with “in agricultural fields”.

-  Line 698: You may also suggest that these findings can be used for the development of new software that could identify lettuce deficiencies real-time.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

The authors did significant improvment but the discussion still need improvment to cover the results section. 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

Recommendations to authors

- Please enlarge lettuce images (i.e., in Figure 8, 11).

- Please make the font size larger in Figure 16. Check the resolution too.

- I think that there is still space for improvements regarding the proofreading of the manuscript and other English-related issues.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf