Content-based retinal image retrieval using dual-tree complex wavelet transform

Author

Baby, Christina George ; Chandy, D.A.

Author_Institution

Dept. of Electron. & Commun. Eng., Karunya Univ., Coimbatore, India

fYear

2013

fDate

7-8 Feb. 2013

Firstpage

195

Lastpage

199

Abstract

Content-based image retrieval methods aid physicians in diagnosing the early detection of diabetic retinopathy for preventing blindness. In this work, the combination of two dimensional dual-tree complex wavelet transform (DT-CWT) and generalized Gaussian density (GGD) model is used for feature extraction. Kull-back Leibler Divergence (KLD) computes the similarity measure between two feature set. Experimental dataset includes 1200 images from MESSIDOR database. The mean precision rates at five retrieved images are obtained as 78.23% and 53.70% for Macular Edema and Retinopathy classes, respectively. Results are promising and give an indication that the dual-tree complex wavelet transform is efficient for content-based retinal image retrieval problem.

Keywords

content-based retrieval; eye; image retrieval; medical image processing; patient diagnosis; trees (mathematics); visual databases; wavelet transforms; DT-CWT; GGD model; KLD; Kull-back Leibler divergence; MESSIDOR database; blindness prevention; content-based retinal image retrieval; diabetic retinopathy; dimensional dual-tree complex wavelet transform; feature extraction; generalized Gaussian density model; macular edema class; Adaptation models; Computational modeling; Continuous wavelet transforms; Feature extraction; Indexes; Lead; CBIR; Diabetic retinopathy; Kull-back Leibler Divergence; Macular Edema; dual-tree complex wavelet;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing Image Processing & Pattern Recognition (ICSIPR), 2013 International Conference on

Conference_Location

Coimbatore

Print_ISBN

978-1-4673-4861-4

Type

conf

DOI

10.1109/ICSIPR.2013.6497987

Filename

6497987