Please use this identifier to cite or link to this item:
Title: Performance evaluation of bottom-up and top-down approaches in computational visual attention system
Researcher: Amudha, J
Guide(s): Soman, K P
Keywords: computational visual attention system
Visual Attention
Treismanand#8223;s Feature Integration Theory
Upload Date: 30-Apr-2012
University: Amrita Vishwa Vidyapeetham (University)
Completed Date: February 2012
Abstract: The world around us has abundant of visual information and it is indeed a hilarious job for the brain to process this continuous flow of visual information bombarding the retina and to extract the small portions of information that are important for further actions. Visual attention systems provides the brain with a mechanism of focusing computational resources on one object at a time, either driven by low-level properties (bottom-up attention) or based on a specific task (top-down attention). Moving the focus of attention to locations one by one enables sequential recognition of objects at these locations. What appears to be a straight-forward sequence of processes (first focus attention to a location, then process object information there) is in fact an intricate system of interactions between visual attention and object recognition. How, for instance, can the focus of attention from one object to the next is performed? Can the existing information used for processing the attention can be used for the next object recognition task also? If so how to use it? Whether the existing knowledge about a target object can be utilized in the recognition system to bias the attention from the top down? This thesis attempts to address these questions with a combination of how computational models can be adopted for artificial visual attention systems and how the bottom-up and top-down approaches can be studied empirically for various applications. The base of this research work is on the popular model by Koch and Ullman [60] which is based on the psychological work by Treisman [113] terme the feature-integration-theory. The model uses saliency maps in combination with a winner-take-all selection mechanism. Once a region has been selected for processing it is inhibited to enable other regions to compete for the available resources.
Pagination: xxii, 202p.
Appears in Departments:Amrita School of Engineering

Files in This Item:
File Description SizeFormat 
01_title.pdfAttached File10.66 kBAdobe PDFView/Open
02_contents.pdf91.56 kBAdobe PDFView/Open
03_acknowledgements.pdf10.79 kBAdobe PDFView/Open
04_list of figures.pdf102.26 kBAdobe PDFView/Open
05_list of tables.pdf40.29 kBAdobe PDFView/Open
06_list of abbreviations.pdf15.32 kBAdobe PDFView/Open
07_list of symbols.pdf50.11 kBAdobe PDFView/Open
08_abstract.pdf50.55 kBAdobe PDFView/Open
09_declaration.pdf28.65 kBAdobe PDFView/Open
10_certificate.pdf33.55 kBAdobe PDFView/Open
11_chapter 1.pdf75.65 kBAdobe PDFView/Open
12_chapter 2.pdf220.98 kBAdobe PDFView/Open
13_chapter 3.pdf530.81 kBAdobe PDFView/Open
14_chapter 4.pdf744.81 kBAdobe PDFView/Open
15_chapter 5.pdf476.49 kBAdobe PDFView/Open
16_chapter 6.pdf583.98 kBAdobe PDFView/Open
17_chapter 7.pdf416.45 kBAdobe PDFView/Open
18_chapter 8.pdf789.37 kBAdobe PDFView/Open
19_chapter 9.pdf70.56 kBAdobe PDFView/Open
20_reference.pdf203.41 kBAdobe PDFView/Open
21_appendix.pdf1.64 MBAdobe PDFView/Open

Items in Shodhganga are protected by copyright, with all rights reserved, unless otherwise indicated.

Altmetric Badge: