Abstract After highlighting vessel like structure by an appr opriate filter in Matched Filter (MF) technique, th resholding strategy is needed for the automated detection of b lood vessels in retinal images. For the purpose, we propose to use a new technique of entropic thresholding based on Gray Le vel Spatial Correlation (GLSC) histogram which take s into account the image local property. Results obtained show robustn ess and high accuracy detection of retinal vessel tree. An appropriate technique of thresholding allows significant improv ement of the retinal vessel detection method.

References

[1] Chaudhuri S., Detection of Blood Vessels in Retinal Images using Two9Dimensional Matched filters, IEEE Transaction on Medical Imaging , vol. 8, no. 3, pp. 2639269, 1989.

[2] Cree M., Cornforth D., and Jelinek H., Vessel Segmentation and Tracking using a Two9 Dimensional Model, in Proceedings of Image and Vision Computing Conference , Dunedin, New Zealand, pp. 3459350, 2005.

[3] Dodson P., Diabetic Retinopathy: Treatment and Prevention, Diabetes and Vascular Disease Research , vol. 4, no. 3, pp. 9911, 2007.

[4] Espona L., Carreira M., Penedo M., and Ortega M. , Retinal Vessel Tree Segmentation using a Deformable Contour Model, in Proceedings of the 19 th International Conference on Pattern Recognition , Florida, USA, pp. 194, 2008.

[5] Gardner G., Keating D., Williamson T., and Elliott A., Automatic Detection of Diabetic Retinopathy using an Artificial Neural Network: A Screening Tool, British Journal of Ophthalmology , vol. 80, no. 11, pp. 9409944. 1996.

[6] Hoover A. and Goldbaum M., Locating the Optic Nerve in a Retinal Image using the Fuzzy Convergence of the Blood Vessels, IEEE Transactions on Medical Imaging , vol. 22, no. 8, pp. 9519958, 2003.

[7] Hoover A., Goldbaum M., and Kouznetsova V., Locating Blood Vessels in Retinal Images by Piecewise Threshold Probing of a Matched Filter Response, IEEE Transaction on Medical Imaging , vol. 19, no. 3, pp. 2039210, 2000.

[8] Kabir H., Al9Wadud A., and Chae O., Brightness Preserving Image Contrast Enhancement using Weighted Mixture of Global and Local Transformation Functions, the International Arab Journal of Information Technology , vol. 7, no. 4, pp. 4039410, 2010.

[9] Lam B., Gao Y., and Liew A., General Retinal Vessel Segmentation using Regularization9Based Multiconcavity Modeling, IEEE Transactions on Medical Imaging , vol. 29, no. 7, pp. 1369981, 2010.

[10] Lee S., McCarty C., and Taylor H., Costs of Mobile Screening for Diabetic Retinopathy: A Practical Framework for Rural Populations, Australian Journal of Rural Health , vol. 9, no. 4, pp. 1869192, 2001.

[11] Niemeijer M., Comparative Study of Retinal Vessel Segmentation Methods on a New Publicly Available Database, in Proceedings of International Society for Optical Engineering in Medical Imaging , Florida, USA, pp. 6489656, 2004.

[12] Niki N., Kawata Y., Satoh H., and Kumazaki T., 3D Imaging of Blood Vessels using Xray Rotational Angiographic System, in Proceedings of International Conference Nuclear Science Symposium and Medical Imaging , California, USA, pp. 187391877. 1993.

[13] Rossant F., Badellino M., Chavillon A., Bloch I. and P ques M., A Morphological Approach for Vessel Segmentation in Eye Fundus Images with Quantitative Evaluation, the Journal of Medical Imaging and Health Informatics , vol. 1, no. 1, pp. 42949, 2011.

[14] Soares J., Leandro J., Cesar R., Jelinek F., and Cree M., Retinal Vessel Segmentation using the 29D Gabor Wavelet and Supervised Classification, IEEE Transactions on Medical Imaging , vol. 25, no. 9, pp. 121491222, 2006.

[15] Sofka M. and Stewar C., Retinal Vessel Centerline Extraction using Multiscale Matched Filters Confidence and Edge Measures, IEEE Transactions on Medical Imaging , vol. 25, no. 12, pp. 1531946, 2006.

[16] Staal J., Abramoff M., Niemeijer M., Viergever M., and Ginneken B., Ridge Based Vessel Segmentation in Color Images of the Retina, IEEE Transactions on Medical Imaging , vol. 23, no. 4, pp. 5019509, 2004.

[17] Vermeer K., Vos F., Lemij H., and Vossepoel M., A Model Based Method for Retinal Blood Vessel Detection, Computers in Biology and Medicine , vol. 34, no. 3, pp. 2099219, 2004.

[18] Walter T. and Klein J., Segmentation of Color Fundus Images of the Human Retina: Detection of the Optic Disc and the Vascular Tree using Morphological Techniques, in Proceedings of the 2 nd International Symposium on Medical Data Analysis , London, UK, pp. 2829287, 2001.

[19] Xiao Y., Cao Z., and Zhang T., Entropic Thresholding Based on Gray9level Spatial Correlation Histogram, in Proceedings of the 19 th International Conference on Pattern Recognition , Florida, USA, pp. 194, 2008.

[20] Zhang B., Zhang L., and Karray F., Retinal Vessel Extraction by Matched Filter with First9 Order Derivative of Gaussian, Computers in Biology and Medicine , vol. 40, no. 4, pp. 438945, 2010. Automated Retinal Vessel Segmentation using Entropic Thresholding Based Spatial Correlation 447 Soumia Belhadi is assistant professor at the University of Blida, she received the engineer diploma in electronic and her MS in image and sound processing from Blida University. Currently, she is member of the Image and Signal Processing Laboratory at the University of Blida. Her current research interests include: Medical image processin g, computer vision, diagnostic aid. Nadjia Benblidia is senior lecturer at the University of Blida since 1984, she received the engineer diploma in computer science from University of Science and Technology Houari Boumediene (USTHB) and her PhD degree in electrical engineering and image processing from Blida University. In 2007, s he obtained the PhD degree in space sciences at the University of Val de Marne (Paris XII). Currently, she is the director of the Research Laboratory for the Development of Computerized Systems at the University of Blida. She is a member of several scientific committees at the national and internati onal level. Her current research interests include: Imag e processing, computer vision, information retrieval, data mining and pattern recognition in various fields especially medical, satellite, security.