Next Article in Journal
Gaussian Processes for Signal Processing and Representation in Control Engineering
Next Article in Special Issue
Target-Oriented High-Resolution and Wide-Swath Imaging with an Adaptive Receiving–Processing–Decision Feedback Framework
Previous Article in Journal
Rod–Airfoil Interaction Noise Reduction Using Gradient Distributed Porous Leading Edges
Previous Article in Special Issue
Risk and Pattern Analysis of Pakistani Crime Data Using Unsupervised Learning Techniques
 
 
Article
Peer-Review Record

Reverse Image Search Using Deep Unsupervised Generative Learning and Deep Convolutional Neural Network

Appl. Sci. 2022, 12(10), 4943; https://doi.org/10.3390/app12104943
by Aqsa Kiran 1,2,3,4, Shahzad Ahmad Qureshi 2, Asifullah Khan 2,3,4, Sajid Mahmood 1,*, Muhammad Idrees 5,*, Aqsa Saeed 3, Muhammad Assam 6, Mohamad Reda A. Refaai 7 and Abdullah Mohamed 8
Reviewer 1:
Reviewer 2:
Appl. Sci. 2022, 12(10), 4943; https://doi.org/10.3390/app12104943
Submission received: 13 April 2022 / Revised: 2 May 2022 / Accepted: 4 May 2022 / Published: 13 May 2022
(This article belongs to the Special Issue Computational Sensing and Imaging)

Round 1

Reviewer 1 Report

Authors presented a novel work for reverse image search using  Deep Unsupervised Generative Learning. My comments are as follows :

1. Negative transfer and overfitting are the two issues which generally affects the performance of transfer learning algorithm. How this issues addressed by authors while dealing with the variants of transfer algorithms reported.

2. What is the specific contribution from authors wrt model development,optimization,exploration of new models and methodology which are least reported.

3.  In pg.9 authors highlighted "The architecture of VGG-16, which consists of sixteen layers". How the various parameters and layers are selected by authors? Any justifications.

4. What is the motivation to choose unsupervised generative learning and how it is giving better result as compare to supervised generative learning. Kindly address in revised manuscript with supporting literature.

5. Quality of all figures need to be improve with high resolution images.



Author Response

Response to Reviewers

 

Manuscript ID:applsci-1704015

Title: “Reverse Image Search using Deep Unsupervised Generative Learning and Deep Convolutional Neural Network”

 

 

Dear Editor,

 

We are thankful to the worthy editor and reviewers for their valuable feedback to further improve our manuscript submitted to the Applied Sciences Journal. We have attentively noted and incorporated the valuable suggestions and comments and also highlighted some additional revisions.

We would like to thank the reviewer for their time and the encouraging remarks. Please find our response surrounded by the revised draft.

 

 

 

 

Best regards,

Corresponding author

 

Sajid Mahmood

Muhammad Idrees

Author Response File: Author Response.docx

Reviewer 2 Report

The authors have presented a two phase reverse image search method based on deep learning to capture low-level details of each image. The accuracy of the proposed method was compared with different data sets. The manuscript is organized well but there are a few minor issues which need to be addressed,

  1. In the implementation details, why MATLAB was chosen? Can the proposed algorithms be implemented using any other frameworks?
  2. How scalable the algorithms are?
  3. What are the sources of the noise in images? Is the noise dependent on the the way the dataset is collected? Please describe the variability in the noise for various datasets.
  4. Are the proposed algorithms are applicable to any dataset? Please comment on the applicability of the proposed algorithms.

Author Response

Response to Reviewers

 

Manuscript ID:applsci-1704015

Title: “Reverse Image Search using Deep Unsupervised Generative Learning and Deep Convolutional Neural Network”

 

 

Dear Editor,

 

We are thankful to the worthy editor and reviewers for their valuable feedback to further improve our manuscript submitted to the Applied Sciences Journal. We have attentively noted and incorporated the valuable suggestions and comments and also highlighted some additional revisions.

We would like to thank the reviewer for their time and the encouraging remarks. Please find our response surrounded by the revised draft.

 

 

 

 

Best regards,

Corresponding author

 

Sajid Mahmood

Muhammad Idrees

Author Response File: Author Response.docx

Back to TopTop