Jul 21, 2003 Dr. Kirk Martinez University of Southampton Highfield Southampton, SO17 1BJ Paper:TIP-00310-2003 An integrated content and metadata based retrieval system for art Dear Dr. Martinez, I am writing to you concerning the above referenced manuscript, which you submitted to the IEEE Transactions on Image Processing. Based on the enclosed set of reviews, it was recommended that the manuscript be REVISED AND RESUBMITTED (RQ). We hope you will be able to implement the comments of the reviewers. Your revised manuscript must be submitted back to Manuscript Central http://sps-ieee.manuscriptcentral.com no later than 60 days from the date of this letter to be further considered for publication in the IEEE Transactions on Image Processing . Please inform me if, for any reason, you are unable to complete the revision within 60 days. Please be sure to upload the revised manuscript in Dr. Martinez’s account. That is the account that will have the number TIP-00310-2003R1 listed. Once you see this number simply click on the underlined title and follow the submission guidelines. If you do not see this number please send an email to Mrs. Kathy Jackson at k.jackson@ieee.org and he will assist you in finding this number. If you have any questions regarding the reviews, please contact me. Any other inquiries should be directed to Mrs. Kathy Jackson. Best regards, Prof. Henri Maitre henri.maitre@enst.fr Mrs. Kathy Jackson k.jackson@ieee.org SPS Publications Office Any attachments from the reviewers can be found by you, (Dr. Martinez) going to the paper in your account. On the right side of the screen you will see a button "View Comments/Respond". Click on it. You will then see the same email sent to you from Prof. Henri Maitre but the attachments from reviewers are listed at the very bottom. http://sps-ieee.manuscriptcentral.com Reviewer 1 Comments: The IEEE Transactions prepared under the auspices of the IEEE Signal Processing Society publish original, comprehensive, in-depth technical papers for knowledgeable readers including researchers and practitioners. The papers are of long-range interest and are significant to the signal processing and related disciplines. All submitted papers undergo multiple, rigorous, blind peer review. The transactions are: IEEE Transactions on Signal Processing IEEE Transactions on Speech and Audio Processing IEEE Transactions on Image Processing IEEE Transactions on Multimedia (a joint publication of the IEEE Circuits and Systems, Signal Processing, Communications, and Computer Societies) IEEE Sensors Journal As a participant in the peer review of this manuscript, you are required to complete this form and return it, within six weeks of receipt of the manuscript, to the Signal Processing Society Publications Office. Your comments will assist the associate editor in determining the final disposition of the manuscript, and will be used to assist the author in refinement of the manuscript. Your identity will be held in confidence from the author. I. REVIEW Please expand and give details in Section III. A. Suitability of topic 1. Is the topic appropriate for publication in these transactions? (X) Yes ( ) Perhaps ( ) No 2. Is the topic important to colleagues working in the field? (X) Yes ( ) Moderately So ( ) No (explain: ) B. Content 1. Is the paper technically sound? ( ) Yes (X) No (why not? The paper is incomplete and lacks analytical results)

2. Is the coverage of the topic sufficiently comprehensive and balanced? ( ) Yes ( ) Important information is missing or superficially treated. ( ) Treatment somewhat unbalanced, but not seriously so. (X) Certain parts significantly overstresses. 3. How would you describe the technical depth of the paper? (X) Superficial ( ) Suitable for the non-specialist ( ) Appropriate for the Generally Knowledgeable Individual Working in the Field or a Related Field ( ) Suitable only for an Expert 4. How would you rate the technical novelty of the paper? ( ) Novel (X) Somewhat Novel ( ) Not Novel C. Presentation 1. How would you rate the overall organization of the paper? ( ) Satisfactory ( ) Could be improved (X) Poor 2. Are the title and abstract satisfactory? (X) Yes ( ) No (explain: ) 3. Is the length of the paper appropriate? If not, recommend how the length of the paper should be amended, including a possible target length for the final manuscript. ( ) Yes (X) No 4. Are symbols, terms, and concepts adequately defined? ( ) Yes ( ) Not always (X) No 5. How do you rate the English usage? ( ) Satisfactory ( ) Needs improvement (X) Poor 6. Rate the Bibliography. ( ) Satisfactory (X) Unsatisfactory (explain: 1) lack of technical reference; 2) unacceptable use of Electronic preprints) D. Overall rating 1. How would you rate the technical contents of the paper? ( ) Excellent ( ) Good ( ) Fair (X) Poor 2. How would you rate the novelty of the paper? ( ) Highly Novel ( ) Sufficiently Novel (X) Slightly Novel ( ) Not Novel 3. How would you rate the literary presentation of the paper? ( ) Totally Accessible ( ) Mostly Accessible ( ) Partially Accessible (X) Inaccessible 4. How would you rate the appropriateness of this paper for publication in this IEEE Transactions? ( ) Excellent Match ( ) Good Match ( ) Weak Match (X) Poor Match II. RECOMMENDATION ( ) A Publish Unaltered ( ) AQ Publish in Minor, Required Changes (as noted in Section III) ( ) RQ Review Again After Major Changes (as noted in Section III) ( ) R Reject (Paper is not of sufficient quality or novelty to be published in this Transactions) ( ) R Reject (A major rewrite is required. Author should be encouraged to resubmit rewritten paper at some later time.) (X) R Reject (Paper is seriously flawed; do not encourage resubmission.) III. DETAILED COMMENTS Please state why you rated the paper as you did in Sections I and II. If you have indicated that revisions are required, please give the author specific guidance regarding those revisions, differentiating between optional and mandatory changes. The submitted manuscript describes a system developed by the authors to retrieve and navigate European content based on real content and meatadata. It is the opinion of this reviewer that the paper should NOT be accepted for publication at its present form as a number of issues should be addressed. In particular, the following should be considered: 1) Introduction A research paper is not a technical report outlying the efforts of a consortium. Rather than focusing on the specifics of the "image related user requirements" (page 2) your introductory section should explicitly address the following: a) what is the problem to be solved here (art indexing & retrieval or the ARTISTE program ?) b) why the problem is important c) what is the state-of-the-art in this area (you need to include the appropriate references in your refernce list to demonstrate that you have a complete understanding of the state-of-the-art) d) what are the limitations of the techniques available ? e) what are the unique or distinguishing characteristics of your system (that will be explained in detail in subsequent sections) f) what will be the experimental set up to be used to evaluate your method g) interpretation of the results It is customary, although not required, that Transactions papers conclude the introductory section with a small paragraph which summarizes the main points of the rest of the paper. 2) Section I 'System Architecture" a) what is your definition of "metadata". What is "RDF" (what the initials stand for and in what context is used here) A small appendix with soem explainations is needed. b) why this particular approach to the metadata description. Why the "Dublin Core" approach and not the one advocated by "MPEG-7" or the expanded sets to included in the upcoming "MPEG-21" standard. Explain, justify and provide details. c) Why the "RDF" solution provides "cross-collections searching" (page 3 middle). We you feel that you cannot do it using another "metadata" proposal. d) The last paragraph of section II, which describes the particulars of the ARTISTE program implementation should perhaps move to the experimental section. 3) Section III (Sub-image matching) a) A better explanation for the need for this sub-image matching procedure is needed. Although, it can be seen that this is a legitimate need, the authors can make a much better job motivating the reader by using a "walk-though" example involving a real museum and an "actual request". Please reformat page 4, language and grammar need improvement. Last paragraph of page 4 should be moved to the "experiments section" as it refers to the implementation phase of the project. The end-user requests and the mechanism to be addressed by the system should be independent of the current version of the technology used. b) the three types of corruption mentioned on page 5 look artificial and are not properly justified. -> why bluring is an issue; please explain; are real-life blurred images are used or an artificial model is used; -> why this particular type of noise is artificially added to the sub-images; is it a model for "scanning noise" ? "transmission noise (how about impulsive style noise" ? -> resizing is a very important issue which is not explained in detail here; why these particular set of reduction values are considered ? what are thye real life implications ? d) your so-called evaluation procedure is incomplete and lacks credibility as you provide no details on what are the elements consituting the procedure. What is the "feature vector F" mentioned on page 5 ? 4) "Experimentations" There is nothing to be said on the results reported in the paper, as (i) the procedure which is used to be obtained, (ii) the experimental apparatus used, (iii) comparative evalution, (iv) an explanation of findings are either missing or incompletely described. Reviewer 2 Comments: The IEEE Transactions prepared under the auspices of the IEEE Signal Processing Society publish original, comprehensive, in-depth technical papers for knowledgeable readers including researchers and practitioners. The papers are of long-range interest and are significant to the signal processing and related disciplines. All submitted papers undergo multiple, rigorous, blind peer review. The transactions are: IEEE Transactions on Signal Processing IEEE Transactions on Speech and Audio Processing IEEE Transactions on Image Processing IEEE Transactions on Multimedia (a joint publication of the IEEE Circuits and Systems, Signal Processing, Communications, and Computer Societies) IEEE Sensors Journal As a participant in the peer review of this manuscript, you are required to complete this form and return it, within six weeks of receipt of the manuscript, to the Signal Processing Society Publications Office. Your comments will assist the associate editor in determining the final disposition of the manuscript, and will be used to assist the author in refinement of the manuscript. Your identity will be held in confidence from the author. I. REVIEW Please expand and give details in Section III. A. Suitability of topic 1. Is the topic appropriate for publication in these transactions? (X) Yes ( ) Perhaps ( ) No 2. Is the topic important to colleagues working in the field? (X) Yes ( ) Moderately So ( ) No (explain: ) B. Content 1. Is the paper technically sound? (X) Yes ( ) No (why not? )

2. Is the coverage of the topic sufficiently comprehensive and balanced? (X) Yes ( ) Important information is missing or superficially treated. ( ) Treatment somewhat unbalanced, but not seriously so. ( ) Certain parts significantly overstresses. 3. How would you describe the technical depth of the paper? ( ) Superficial (X) Suitable for the non-specialist ( ) Appropriate for the Generally Knowledgeable Individual Working in the Field or a Related Field ( ) Suitable only for an Expert 4. How would you rate the technical novelty of the paper? ( ) Novel (X) Somewhat Novel ( ) Not Novel C. Presentation 1. How would you rate the overall organization of the paper? ( ) Satisfactory (X) Could be improved ( ) Poor 2. Are the title and abstract satisfactory? (X) Yes ( ) No (explain: ) 3. Is the length of the paper appropriate? If not, recommend how the length of the paper should be amended, including a possible target length for the final manuscript. (X) Yes ( ) No 4. Are symbols, terms, and concepts adequately defined? ( ) Yes (X) Not always ( ) No 5. How do you rate the English usage? (X) Satisfactory ( ) Needs improvement ( ) Poor 6. Rate the Bibliography. (X) Satisfactory ( ) Unsatisfactory (explain: ) D. Overall rating 1. How would you rate the technical contents of the paper? ( ) Excellent (X) Good ( ) Fair ( ) Poor 2. How would you rate the novelty of the paper? ( ) Highly Novel (X) Sufficiently Novel ( ) Slightly Novel ( ) Not Novel 3. How would you rate the literary presentation of the paper? ( ) Totally Accessible (X) Mostly Accessible ( ) Partially Accessible ( ) Inaccessible 4. How would you rate the appropriateness of this paper for publication in this IEEE Transactions? ( ) Excellent Match (X) Good Match ( ) Weak Match ( ) Poor Match II. RECOMMENDATION ( ) A Publish Unaltered ( ) AQ Publish in Minor, Required Changes (as noted in Section III) (X) RQ Review Again After Major Changes (as noted in Section III) ( ) R Reject (Paper is not of sufficient quality or novelty to be published in this Transactions) ( ) R Reject (A major rewrite is required. Author should be encouraged to resubmit rewritten paper at some later time.) ( ) R Reject (Paper is seriously flawed; do not encourage resubmission.) III. DETAILED COMMENTS Please state why you rated the paper as you did in Sections I and II. If you have indicated that revisions are required, please give the author specific guidance regarding those revisions, differentiating between optional and mandatory changes. An overall interesting paper. Please check all abbriviations for explanation at their first occurence, like MCCV page 3. At page 2 user requirements are stated. Explaib and make claer at this point which ones will be addressed in the paper. The System architectute should be described in more detaill. The results of III sub-image matching are restricted to only square fixed size sub-images. None of the other requirements is discussed. The MCCV related results in the figure are hard to distinguish. What is the application background for the Query by Low Image Quality. This chapter is the central part of the paper. It should be highlighted. The Query by Crack Type chapter seeems just be added to the paper. It is difficult to see the relevance. The paper presents some particular aspects. A global is still missing. But there are good ideas and good evaluations. Concentrate on a system with a clear application and architecture and philosophy.