Please use this identifier to cite or link to this item:
Title: Content-based image indexing and retrieval using soft computing
Authors: Syed Muhammad Ghazanfar Monir.
Keywords: DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
Issue Date: 2011
Abstract: Conventional interactive Content-based Image Retrieval (CBIR) systems restrict the user to binary labelling of feedback images, i.e. the user can mark the retrieved images either as relevant or irrelevant. This feedback process does not reflect the nature of user interpretation and understanding of images, which tends to be uncertain due to perceptual subjectivity. Hence, it is inappropriate to describe the feedback decision by binary logic without considering the degree of relevance. To overcome this problem, a fuzzy framework is implemented to integrate the users' imprecise interpretation of visual contents into relevance feedback. An efficient learning machine is developed with Fuzzy Radial Basis Function Network (FRBFN) whose parameters (weights, width, and centres) are tuned by a gradient-descent-based learning strategy. The system is tested for its effectiveness using a database of 10,000 images.
Description: 72 p.
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Theses

Files in This Item:
File Description SizeFormat 
  Restricted Access
6.96 MBAdobe PDFView/Open

Page view(s) 20

checked on Sep 25, 2020

Download(s) 20

checked on Sep 25, 2020

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.