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

• Main Authors: Mohd Hanafi Ahmad Hijazi, Chuntao Jiang, Frans Coenen, Yalin Zheng
• Format: Conference or Workshop Item
• Language: English; English
• Published: 2011
• Subjects: QA1-43 General
• Online Access: https://eprints.ums.edu.my/id/eprint/31610/1/Image%20Classification%20for%20Age-related%20Macular%20Degeneration%20Screening%20Using%20Hierarchical%20Image%20Decompositions%20and%20Graph%20Mining.pdf1.pdf; https://eprints.ums.edu.my/id/eprint/31610/2/Image%20Classification%20for%20Age-related%20Macular%20Degeneration%20Screening%20Using%20Hierarchical%20Image%20Decompositions%20and%20Graph%20Mining.pdf; https://eprints.ums.edu.my/id/eprint/31610/; https://link.springer.com/chapter/10.1007%2F978-3-642-23783-6_5
• Institution: Universiti Malaysia Sabah

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.