Memory-Tree Based Design of Optical Character Recognition in FPGA

Round 1

Reviewer 1 Report

The authors presented a practical work for OCR systems. I have comments as follows:

 

1. The contents for “traditional algorithm” (2.1.1 & 2.1.2) are not clear enough.

2.    Following 1, the authors should clearly explain the “traditional algorithm” used for comparisons in Figures 8 and 13, and discuss the reason their work can have better performances.

3.  Also following 1, the “traditional” works for Tables 3 and 4 should be addressed.

4.   For Table 4, the authors claimed their hardware design can reach better results (lines 322/323). However, it seemed that more LUT & FF resources were used to reach shorter processing time. Also, the operation frequency for different works should also be compared in Table 4.

Author Response

Please see the attachment. Thank you again for your work.

Author Response File: Author Response.pdf

Reviewer 2 Report

  This paper presents the Memory-tree based Design of Optical Character Recognition in FPGA. It is a nice research paper. The authors studied their research considering the recent reference papers as well. The authors can add the contributions of their research to science as bullet points in the introduction section and some more articles can be added to the comparison table in sections 5 and 6.). The authors implemented their idea using HLS and IDE under Ubuntu 18.04 Operating System. Why Ubuntu OS has been preferred? The Tables 3 and 4 can be improved by adding more references for comparison purpose and a future work can be suggested considering the CPU Time and the power consumed, how they can be improved.

Author Response

Please see the attachment. Thank you again for your work.

Author Response File: Author Response.pdf

Reviewer 3 Report

In this study, the authors proposed an approach based on the Memory-centric computing and Memory-tree algorithm. The method applied by the authors are sound and can help answer the objectives (their approach achieved accurate recognition of numbers and English capital letters and saved 77.87% of power consumption compared with the traditional 84W processor computing). 

In a general way, the manuscript is interesting, well-written and easy to read. Experiments are clear and report on good quality work that has been well executed. I list here below some comments to improve the presentation, but in general I would say that the manuscript requires minor revisions only.

 

1. Introduction

Some references are missing (e.g. LL. 59-61).

 

2. Background and Related Work

More reviews are required.

You only cited [16-18] in 2.1.1 and 2.1.2.

Author Response

Please see the attachment. Thank you again for your work.

Author Response File: Author Response.pdf