FAECCD-CNet: Fast Automotive Engine Components Crack Detection and Classification Using ConvNet on Images
Round 1
Reviewer 1 Report
In the paper Authors propose new methodology for automotive component cracking inspection based on ConvNet models instead of manual inspection/detection.
Nice paper, but difficult to read due to huge amount of abbreviations. My first suggestion was to add abbreviation dictionary at the beginning of the paper. Then I found it at the end…in my opinion should be at the beginning and involve much more abbreviations, e.g. used in abstract and later DA? What it means - decision altitude (DA)? I think there is more unclear abbreviations.
Pic’s with diagrams are not fully readable, maybe different font type will help.
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Reviewer 2 Report
The work is well written and organized. The bibliography is up to date and the results are widely described, represented and commented on.
Below, by points, some changes to increase readability and quality of work:
· Avoid triumphant adjectives like 'outstanding' and the like.
· Standardize all figures and increase both quality and shape.
· Move figure 8 to the paragraph describing it. In addition, with regard to Figures 8 and 9, on the axes, there is no description of the quantities and their units of measurement.
· The data reported in the 'Results' section should be accompanied, where possible, by relative graphs highlighting, in a more effective and understandable way, the performance of the approaches used.
Author Response
Please see the attachment
Author Response File: Author Response.pdf