Dissertation/Thesis Abstract

Saliency Estimation Using the Complementary Color Wavelet Transform
by Wadolowski, Karol, M.E., The Cooper Union for the Advancement of Science and Art, 2020, 118; 27964534
Abstract (Summary)

In many image processing tasks it is useful to have a saliency map that highlights the important parts of an image. Many algorithms currently exist that generate saliency maps. In this work a new algorithm is developed that is capable of generating multiple saliency maps from a single image, highlighting different parts of the image. This is done using the Complementary Color Wavelet Transform, a tool which captures various color changes at different scales in an image. The outputs of this transform are then fed into an adapted version of a previously developed saliency map generation algorithm. Using this transform, the algorithm is able to generate four saliency maps for a given image. This algorithm is applied on the images in the CAT2000 dataset. The saliency maps generated using this algorithm are evaluated using two popular performance metrics, the similarity metric and linear correlation coefficient. In many cases, the proposed algorithm provides better results than other approaches.

Indexing (document details)
Advisor: Fontaine, Fred L.
Commitee:
School: The Cooper Union for the Advancement of Science and Art
Department: Electrical Engineering
School Location: United States -- New York
Source: MAI 82/2(E), Masters Abstracts International
Source Type: DISSERTATION
Subjects: Electrical engineering
Keywords: Image Processing, Saliency, Wavelets
Publication Number: 27964534
ISBN: 9798662589346
Copyright © 2020 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest