Species Identification of Caterpillar Eggs by Machine Learning Using a Convolutional Neural Network and Massively Parallelized Microscope

Round 1

Reviewer 1 Report

This paper proposed a Species Identification of Caterpillar Eggs apporach Using a Convolutional Neural Network and Massively Parallelized Microscope. Overall, the structure of this paper is well organized, and the presentation is clear. However, there are still some crucial problems that need to be carefully addressed before a possible publication. More specifically,

1.     A deep literature reviews should be given, particularly advanced and SOTA deep learning or AI models in classification and recognition. Therefore, the reviewer suggests discussing some related works by analyzing the following papers in the revised manuscript, e.g., 10.1109/TGRS.2020.3016820, 10.1109/TGRS.2020.3015157, 10.1109/TGRS.2021.3124913.

2.     Please clarify the contributions to this field, for example, which are the existing ones and which are your own ones?

3.     What are the differences in techniques between the proposed method and existing methods?

4.     Some future directions should be pointed out in the conclusion.

Author Response

see attached.  

Author Response File: Author Response.docx

Reviewer 2 Report

1. Because the sizes of eggs are very small, it is not easy to find eggs in natural environment.

“In the future, Applications can be developed enabling farmers to photograph eggs on a leaf and receive an immediate species identification before the eggs hatch. "Mentioning this sentence in the abstract will arouse readers' doubts about how farmers can find these small-sized eggs in the natural environment and then photograph them.

2. “Imaging and the traditional analysis of insect eggs is significantly more challenging because of their small size, minute differences in their size or color between species in some cases, and in general lack of easily distinguishable features.”In this case, why don't the authors describe the size distribution and color distribution of eggs in detail, so that readers can have a clearer understanding of eggs.

3. Through the complicated three steps from 2.1 to 2.3, the images of eggs are obtained. This process is very complicated. Can the images taken by farmers through mobile phones in the field meet the recognition requirements? This problem directly determines whether this technology can only stay in the laboratory or not.

4. ”Thus, it cannot be assumed that our model can generalize to field use at this juncture.”“Because our data set is specific, we cannot expect our algorithm to identify either type of egg when any variable is altered outside of the conditions of training except for perhaps lighting.” Since it cannot be assumed that it can be used in practical applications, why does the authors mention the future application prospects many times in this paper? At least the authors should mention what problems need to be solved firstly.

5. The formats of references [25] and [30] are not standardized.

Author Response

See attached

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

The authors have well addressed the reviewer's concerns. No more comments. The current version is in a good shape.

Reviewer 2 Report

The authors have answered all of my questions and the paper has been greatly improved.