Quality Assessment of Components of Wheat Seed Using Different Classifications Models

Round 1

Reviewer 1 Report

1. The section "Materials and methods" does not specify why such grain groups were chosen for classification.
2. Were the spectral characteristics of the reflection (color) of the seeds taken into account when choosing a radiation source?
3. What will be the cost of the device for the practical implementation of the wheat quality assessment system proposed by the authors?
4. There are no publications in the list of references for the last five years.

Author Response

We, the authors, appreciate all the time spent by the reviewers and all the ideas, suggestions, and comments presented. We addressed all the ideas, suggestions, and comments below in our revised manuscripts.

 

Comments and Suggestions for Authors:

1- The section "Materials and methods" does not specify why such grain groups were chosen for classification.

Response to reviewer: The study of the production process of certified wheat seeds has been the basis for selecting grain groups in this study. Barley grains, rye and foreign wheat cultivars are difficult to distinguish in the field and also due to the similarity of appearance and physical characteristics of these grains to the main seed wheat also pass through threshing machines and reach the bagging stage. This includes broken, small, and wrinkled grains. The section "Introduction” was revised.

 

 

2- Were the spectral characteristics of the reflection (color) of the seeds taken into account when choosing a radiation source?

Response to reviewer: The spectral characteristics of the reflection (color) of the seeds were not taken into account.

 

 

3- What will be the cost of the device for the practical implementation of the wheat quality assessment system proposed by the authors?

Response to reviewer: The cost of the system depends on the type of hardware for this project is estimated between 2000 and 2500 dollars.

 

 

4- There are no publications in the list of references for the last five years.

Response to reviewer: The references section was also edited and new references were added.

 

 

Author Response File: Author Response.docx

Reviewer 2 Report

This manuscript assessed the quality of wheat seed components using different classifications models. Overall, I consider it worthy of publication in Applied Sciences. Nevertheless, there are several issues that need to be fixed before I can recommend it for publication...

(1) In the “Introduction” section, it was regarded as a difficult, time-consuming task in quality control assessments of wheat seeds. Thus, on the basis of obtaining higher classification accuracy, classification efficiency is also very important. What were the classification efficiencies under different classifications models? Also, how do you make a balance between classification accuracy and classification efficiency?

(2) In the section of “2.3. Image Processing”, the optimized threshold value of 0.25 was applied in the processing of all images. I think more result of image processing (i.e., the results from the seven groups of seeds shown in Figure 1) should be presented to demonstrate the reliability of the optimized threshold.

I think that some additional information and clarification (mentioned above), should contribute to increase the impact of this work, which is in my opinion of good quality and is developed in the right direction.

Comments for author File: Comments.docx

Author Response

We, the authors, appreciate all the time spent by the reviewers and all the ideas, suggestions, and comments presented. We addressed all the ideas, suggestions, and comments below in our revised manuscripts.

 

This manuscript assessed the quality of wheat seed components using different classifications models. Overall, I consider it worthy of publication in Applied Sciences. Nevertheless, there are several issues that need to be fixed before I can recommend it for publication...

(1) In the “Introduction” section, it was regarded as a difficult, time-consuming task in quality control assessments of wheat seeds. Thus, on the basis of obtaining higher classification accuracy, classification efficiency is also very important. What were the classification efficiencies under different classifications models? Also, how do you make a balance between classification accuracy and classification efficiency?

Response to reviewer: The efficiency of classification models is determined by the nature of each model. Depending on the speed of the software or the accuracy of the classification model is a priority. We make a balance between classification accuracy and classification efficiency.

 

 

(2) In the section of “2.3. Image Processing”, the optimized threshold value of 0.25 was applied in the processing of all images. I think more result of image processing (i.e., the results from the seven groups of seeds shown in Figure 1) should be presented to demonstrate the reliability of the optimized threshold.

Response to reviewer: Due to the increase in program execution speed, a constant threshold value of 0.25 was applied in the processing of all images. This value was optimal for the conditions of this project.

 

 

I think that some additional information and clarification (mentioned above), should contribute to increase the impact of this work, which is in my opinion of good quality and is developed in the right direction.

 

The authors thank the esteemed reviewer for his/her positive attitudes.

Author Response File: Author Response.docx