kumoh national institute of technology
Networked Systems Lab.

Cosmas Ifeanyi Nwakanma, Williams-Paul Nwadiugwu, Jae-Min Lee and Dong-Seong Kim, "Image Similarity Index Tradeoff Model for Industrial Network", 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Zaragoza, Spain, September 10-13,2019 (A)( N8).
By : Cosmas Ifeanyi
Date : 2019-07-02
Views : 302

Feedback from the Reviewers:
Reviewer 1:
C. Clarity of presentation:
English grammar and spelling are proper ------------------------------------------ [2 - I am neutral]
Mathematical symbols and equations are easy to understand ------------------------ [3 - I agree]
Figures and tables are well constructed and informative -------------------------- [3 - I agree]
The paper is well organized ------------------------------------------------------ [3 - I agree]
Considering the issues above, the paper is readable ------------------------------ [3 - I agree]

T. Technical innovation and relevance
The authors cite other relevant publications ------------------------------------- [3 - I agree]
Authors describe relevance of work to the research field ------------------------- [3 - I agree]
The authors apply sound technical approaches ------------------------------------- [3 - I agree]
New ideas are convincingly and logically described ------------------------------- [2 - I am neutral]
Results are convincing ----------------------------------------------------------- [2 - I am neutral]
Considering the issues above, this work should be presented --------------------- [2 - I am neutral]

Comments:
The paper investigated a tradeoff model for analysis and prediction of the
relationship between image size ratio and similarity index of images after
compression. The model presented and results obtained were well
discussed. Some important information is missing for example how many
images were used in each dataset? The work sounds promising and it would
be interesting to see how it performs when deals with real world images,
where often packed with unwanted noise and with colour.

Other issues:

These sentences:
"There is also the development of techniques for evaluating the quality of
image and image size ratio of the compression techniques" and "Several
schemes have been proposed to ensure bandwidth and storage
conservation" require citations.

Reviewer 2:
C. Clarity of presentation:
English grammar and spelling are proper ------------------------------------------ [1 - I disagree]
Mathematical symbols and equations are easy to understand ------------------------ [3 - I agree]
Figures and tables are well constructed and informative -------------------------- [1 - I disagree]
The paper is well organized ------------------------------------------------------ [3 - I agree]
Considering the issues above, the paper is readable ------------------------------ [3 - I agree]

T. Technical innovation and relevance
The authors cite other relevant publications ------------------------------------- [1 - I disagree]
Authors describe relevance of work to the research field ------------------------- [1 - I disagree]
The authors apply sound technical approaches ------------------------------------- [3 - I agree]
New ideas are convincingly and logically described ------------------------------- [2 - I am neutral]
Results are convincing ----------------------------------------------------------- [2 - I am neutral]
Considering the issues above, this work should be presented --------------------- [3 - I agree]

Comments:
The paper aims to investigate the relationship between the
image ratio size and similarity index after compression,
using correlation analysis.

This topic is interesting, but the proposed method has not
been compared to other state-of-art approaches.

English should also be improved. Indeed, the paper contains
many typos (e.g. the fieldbus application interface (API)
read -> reads, etc.).

Reviewer 3:
Clarity of presentation:
English grammar and spelling are proper ------------------------------------------ [1 - I disagree]
Mathematical symbols and equations are easy to understand ------------------------ [1 - I disagree]
Figures and tables are well constructed and informative -------------------------- [1 - I disagree]
The paper is well organized ------------------------------------------------------ [2 - I am neutral]
Considering the issues above, the paper is readable ------------------------------ [1 - I disagree]

T. Technical innovation and relevance
The authors cite other relevant publications ------------------------------------- [3 - I agree]
Authors describe relevance of work to the research field ------------------------- [3 - I agree]
The authors apply sound technical approaches ------------------------------------- [2 - I am neutral]
New ideas are convincingly and logically described ------------------------------- [2 - I am neutral]
Results are convincing ----------------------------------------------------------- [2 - I am neutral]
Considering the issues above, this work should be presented --------------------- [1 - I disagree]

Comments:
The paper investigates a topic that is relevant in the
industrial field, where images are captured, sent over a
network, and processed to serve as sensing element for
controlling industrial robots and equipments. Therefore,
the study of the tradeoff between image size and quality
becomes very relevant.

The paper, however, largely fails in presenting the system
model and the results in a clear and easy to understand
fashion. The paper suffers from a lack of accuracy in the
definition of several key concepts, both in the system
model and in the simulation and performance evaluation.
These inaccuracies and obscure terms make it really hard to
establish the usefulness and the quality of the results and
the contribution. Moreover, many paragraphs are written in
poor English, which further complicates the comprehension
of the content.

Figure 1 should be moved to page 2, where it is actually
referenced.

In page 2, the notation used in (1) and (2) is wrongly
described. The authors say that x and y are the number of
rows and columns in the image, however, in the equations
these terms are more likely to be N_x and N_y. Moreover,
they say that R is "typically used", however, they should
say what is its actual meaning in the equations, despite
its "typical" use (I basically suggest to remove
"typically" from the sentence). Finally, the meaning of the
Y and Y' functions is not explained at all. Moreover, in
(2) the term MSE(Y) is used, which was never introduced
before: notice that in (1) the term MSE is introduced, not
MSE(Y); what is the relationship between the two terms?

The definition of the overall quality index in (3) is
completely obscure: what is Q_j in the equation? M is
defined as "number of steps of scanning ...": what does
this mean, exactly?

In section III.D the authors introduce the regression
model. However, the purpose of the regression model was
never introduced before, nor it is described in the
section. I strongly suggest to better describe the method
used for the evaluation *before* presenting the adopted
mathematical tools. Moreover, since the authors opted to
illustrate the basic formulation of a linear regression
model, they should also explain the meaning of the term
"coefficient of determination".

The description of Bezier curves in section III.E is
confused and poorly stated. Please restate the section.

In section IV.A, what is the meaning of "The image used was
142KB"? Is it the name of a dataset? Is it the number of
images? Is it the size of one single image? Is it the
average dimension of an image? Please be more clear in the
statements!

At the beginning of section IV.A the authors state that
they use black and white images to reduce the computational
complexity of the evaluation. It would be important to
report an indication of the computational complexity
involved in the evaluation process, to motivate the
decision of using black and white images. For example, what
is the computation time required in case of black and white
images? And in case of color images?

In table I, what is the meaning of the values in the first
column? In other words, what do the authors mean with
"Experimental results" in such a column?

Typos

page 1: was a scalable industrial image processing
applications ? -> perhaps it should be "application"
page 1: have remained the widely used -> the most widely
used (although, I suggest to restate the whole sentence)
page 2: R is used typically used to -> R is used typically
to

Accepted or Rejected?
The manuscript is marked as ACCEPTED.
The manuscript is not on the list of registered manuscripts.