Automatic Detection of Hard Exudates in Retinal Images Using Haar Wavelet Transform

Diabetic Retinopathy (DR) is a leading cause of vision loss, caused by the abnormalities in the retina due to insufficient insulin in the body. So that Diabetic patients require regular medical checkup for effective timing of sight saving treatment. A completely automated and robust screening system for the detection of Diabetic Retinopathy can effectively reduces the burden of the specialist and saves cost as well as time. Due to noise and other disturbances that occur during image acquisition, DR may lead to false detection and this is overcome by various image processing techniques. This paper presents an automated method for bright lesions i.e. hard exudates in retinal images. The Haar wavelets transform is used in the system for the hard exudates segmentation followed by k nearest neighbor classification method. We have used four databases of fundus images; among them we obtain sensitivity 37.14%, 21.87%, 12.50%, 25.47% for MISP, DB0, DB1 and STARE database respectively. And the specificity is 0% for MISP and 1% for remained databases.

[1]  P. Prentasic,et al.  Detection of Diabetic Retinopathy in Fundus Photographs , 2013 .

[2]  Gilberto Zamora,et al.  The effects of spatial resolution on an automated diabetic retinopathy screening system's performance in detecting microaneurysms for diabetic retinopathy , 2004, Proceedings. 17th IEEE Symposium on Computer-Based Medical Systems.

[3]  Til Aach,et al.  Advances in medical image processing , 2011, Computer Science - Research and Development.

[4]  Asoke K. Nandi,et al.  Automated detection of exudates in retinal images using a split-and-merge algorithm , 2010, 2010 18th European Signal Processing Conference.

[5]  Marios S. Pattichis,et al.  Detection of hard exudates and red lesions in the macula using a multiscale approach , 2012, 2012 IEEE Southwest Symposium on Image Analysis and Interpretation.

[6]  M. Mathurakani,et al.  IMAGE DENOISING USING DUAL TREE COMPLEX WAVELET TRANSFORM , 2014 .

[7]  L D Cromwell,et al.  Filtering noise from images with wavelet transforms , 1991, Magnetic resonance in medicine.

[8]  Roberto Hornero,et al.  Retinal image analysis based on mixture models to detect hard exudates , 2009, Medical Image Anal..

[9]  P. Sharp,et al.  Automated detection and quantification of retinal exudates , 1993, Graefe's Archive for Clinical and Experimental Ophthalmology.

[10]  A. Grossmann,et al.  DECOMPOSITION OF HARDY FUNCTIONS INTO SQUARE INTEGRABLE WAVELETS OF CONSTANT SHAPE , 1984 .

[11]  L. Aiello,et al.  Systemic considerations in the management of diabetic retinopathy. , 2001, American journal of ophthalmology.

[12]  Hossein Rabbani,et al.  Diabetic Retinopathy Grading by Digital Curvelet Transform , 2012, Comput. Math. Methods Medicine.

[13]  Prabhjot Kaur Kholi,et al.  Exact Detection of Optic Disc in Retinal Images Using Segmentation Based On Level Set Method and Morphological Operations , 2012 .

[14]  Atul Kumar,et al.  A Segment based Technique for Detecting Exudate from Retinal Fundus Image , 2012 .

[15]  S C Orphanoudakis,et al.  DIPE: a distributed environment for medical image processing. , 1997, Studies in health technology and informatics.