Title :
CNN-based algorithm for drusen identification
Author :
Checco, Paolo ; Corinto, Fernando
Author_Institution :
Dept. of Electron., Politecnico di Torino
Abstract :
Drusen characterize the age-related macular degeneration. Automatic procedures for their identification have been recently developed. In this paper a cellular neural network based algorithm for drusen identification in fundus photograph is proposed. The algorithm is composed by different image processing steps: noise reduction, histogram normalization and a novel procedure of adaptive segmentation. The algorithm has been validated by using images provided from an ophthalmic medical center
Keywords :
cellular neural nets; eye; image segmentation; medical image processing; CNN; adaptive segmentation; age related macular degeneration; cellular neural network; drusen identification; fundus photograph; histogram normalization; image processing; noise reduction; Biomedical imaging; Cellular neural networks; Colored noise; Histograms; Image color analysis; Image processing; Image segmentation; Medical diagnostic imaging; Noise reduction; Nonlinear filters;
Conference_Titel :
Circuits and Systems, 2006. ISCAS 2006. Proceedings. 2006 IEEE International Symposium on
Conference_Location :
Island of Kos
Print_ISBN :
0-7803-9389-9
DOI :
10.1109/ISCAS.2006.1693051
