PAPER REVIEW FORM

ASME Computers and Information in Engineering Conference

 

An ASME paper should be: Clear, concise, complete, and original; with assumptions plainly identified; data and computation results presented with their uncertainty, precise logic, relevance to practice described, and with actual accomplishments of the work plainly stated and honestly appraised.

 

Paper No.:

CIE-2004-84

TechArea Chair:

Richard Crawford

Title:

Local Feature Extraction Using Scale-Space Decomposition

Author(s):

Dmitriy Bespalov , Ali Shokoufandeh William C. Regli

Reviewer:

Only for TechArea & Program Chairs

Affiliation

 

Date assigned:

3/30/04

Return review by*:

4/13/04

Return e-mail:

rhc@mail.utexas.edu

 

 

*Please inform the TechArea Chair immediately if you cannot complete the review by the indicated date.

Please delete the manuscript file from your computer after the review has been returned to the TechArea Chair.

 

Place a check in the boxes that, in your opinion, best describe the following features of the manuscript.

 

PAPER PROFILE

 

Poor

Marginal

Acceptable

Good

Honor

Originality of work                         

 

 

 

X

 

Engineering relevance

 

 

X

 

 

Significance of contributions

 

 

X

 

 

Fit with ASME-CIE scope                     

 

 

 

X

 

Completeness of the reported work      

 

 

X

 

 

Acknowledgment of the work of others

 

X

 

 

 

Organization of the work                        

 

 

X

 

 

Clarity in writing, Tables, graphs, and illustrations

 

 

X

 

 

 

 

Yes

No

N/A

In your opinion, is the technical treatment plausible and free of technical errors?

X

 

 

Have you checked the equations?

 

X

 

Are you aware of prior publication or presentation of this work?

 

X

 

Is the work free of commercialism?

X

 

 

Is the paper too long?

 

X

 

 

YOUR RECOMMENDATION

This paper is: (check only in one place - justify decision by remarks on next page)

X

Acceptable with Minor Revisions

 

 

REMARKS

To assist the author in revising the paper please separate your remarks into two clearly identified sections:

 

(1) Changes which must be made before publication.

(2) Those suggestions which, in your opinion, would improve the quality of the paper but are not essential for publication

 

Remarks that are not clearly identified will be assumed to fall into the second category (not essential).

 

 

CHANGES WHICH MUST BE MADE BEFORE PUBLICATION

This is a good paper on a new method of feature extraction from 
tessellated CAD models.  The new method is based on scale-space 
decomposition from the computer vision literature.  The extensive examples 
aid in communicating results.  Although the work is still early, it is 
promising and may lead to new methods of archiving and retrieving CAD 
models of parts.

Some minor corrections and additions are needed before presentation:
- The first paragraph of the Abstract looks like it was for a different 
paper.  The last sentence talks about a "problem of matching" that is not 
mentioned anywhere in the Abstract or the paper.  Furthermore, a "distance 
measure between vertex-labeled rooted trees" is not discussed in the paper 
(at least not using those terms).

- Section 2 is too short.  Many references are cited, but their 
contribution to the work is unclear.

- 2nd paragraph of section 3 mentions that the computer vision literature 
was the basis for the authors usage of features.  However, no references 
are cited in that literature.  A couple of paragraphs are needed in 
Section 2 to explain and motivate the feature extraction method.

- Theorem 1 refers to Eckart-Young (I believe), so this is an incomplete 
reference.

- The caption for Figure 4 mentions part names (Part 9, Part 10, Simple 
Boeing, etc.).  Explanation is needed for the origin of these names.




SUGGESTIONS FOR IMPROVING PAPER BUT NOT ESSENTIAL FOR PUBLICATION


        



SUGGESTED DISCUSSERS