Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Assessing neural network scene classification from degraded images
Tadros T., Cullen N., Greene M., Cooper E. ACM Transactions on Applied Perception16 (4):1-20,2019.Type:Article
Date Reviewed: Mar 23 2021

One of the major problems faced by deep learning techniques--for example, deep convolutional neural networks (CNNs)--is uncontrolled behavior due to glitches in the input. For example, you can modify just a few pixels in a photo’s background and the neural network won’t be able to recognize it anymore. CNNs are less affected by changes to an image via color or contrast; however, an increase in blur or noise level negatively affects performance. Scrambling or cutting block pixels out from an image also worsens CNN performance, especially for indoor scenes. In general, humans are very tolerant of such image modifications.

The authors of this paper study this problem and help readers to understand it better. To do so, they compare the classification results of distorted images made by human subjects--real indoor or outdoor scenes--to the classifications made by CNNs. Furthermore, they compare the network’s classification accuracy to the accuracy of other classic image classifiers based on hue saturation and GIST descriptors. Thus, CNN is compared to five classifiers: human subjects, PlacesNet, InOutNet, GIST-LDA, and HSV-LDA. Different classification agreements between some and all of them are induced.

This paper targets a hot topic in image recognition--CNNs are being considered in biological vision research and in real-world scene analysis (like autonomous robots). This is a very-well-written scientific paper that is easy to read due to its clear and consistent explanatory style. It is also well organized. I highly recommend it to researchers interested in computer vision and image perception.

Reviewer:  Mario Antoine Aoun Review #: CR147222 (2107-0187)
Bookmark and Share
  Featured Reviewer  
 
General (I.4.0 )
 
 
Manipulators (I.2.9 ... )
 
 
Psychology (J.4 ... )
 
 
General (I.3.0 )
 
Would you recommend this review?
yes
no
Other reviews under "General": Date
Matrix structured image processing
Dougherty E., Giardina C., Prentice-Hall, Inc., Upper Saddle River, NJ, 1987. Type: Book (9789780135656235)
Jul 1 1988
Digital image processing (2nd ed.)
Gonzales R., Wintz P., Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1987. Type: Book (9789780201110265)
Jul 1 1988
Art and design: AI and its consequences
Howard G., John Wiley & Sons, Inc., New York, NY, 1986. Type: Book (9780471909309)
Dec 1 1987
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy