Image Classification for Age-related Macular Degeneration Screening Using Hierarchical Image Decompositions and Graph Mining

Mohd Hanafi Ahmad Hijazi and Chuntao Jiang and Frans Coenen and Yalin Zheng (2011) Image Classification for Age-related Macular Degeneration Screening Using Hierarchical Image Decompositions and Graph Mining. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, September 5-9, 2011, European Conference, ECML PKDD 2011, Athens, Greece.

[img] Text
Image Classification for Age-related Macular Degeneration Screening Using Hierarchical Image Decompositions and Graph Mining.pdf1.pdf

Download (35kB)
[img] Text
Image Classification for Age-related Macular Degeneration Screening Using Hierarchical Image Decompositions and Graph Mining.pdf
Restricted to Registered users only

Download (448kB) | Request a copy

Abstract

Age-related Macular Degeneration (AMD) is the most common cause of adult blindness in the developed world. This paper describes a new image mining technique to perform automated detection of AMD from color fundus photographs. The technique comprises a novel hierarchical image decomposition mechanism founded on a circular and angular partitioning. The resulting decomposition is then stored in a tree structure to which a weighted frequent sub-tree mining algorithm is applied. The identified sub-graphs are then incorporated into a feature vector representation (one vector per image) to which classification techniques can be applied. The results show that the proposed approach performs both efficiently and accurately.

Item Type: Conference or Workshop Item (Paper)
Keyword: Hierarchical image decomposition , Weighted graph mining , Image partitioning , Image classification
Subjects: Q Science > QA Mathematics > QA1-939 Mathematics > QA1-43 General
Department: SCHOOL > School of Engineering and Information Technology
Depositing User: SITI AZIZAH BINTI IDRIS -
Date Deposited: 17 Jan 2022 08:38
Last Modified: 17 Jan 2022 08:38
URI: https://eprints.ums.edu.my/id/eprint/31610

Actions (login required)

View Item View Item