Detection of Hard Exudates in Fundus Images Based on SVM

Abstract

Abstract:

Abstract: To overcome the difficulties of the detection of hard exudates(HEs) such as uneven illumination, low contrast and the interference of soft exudates, a method based on SVM is proposed. Firstly we use morphological and thresholding methods to coarsely segment the candidate HEs regions in fundus images, then extract features on the candidate regions and import the AMFM features, finally we use a SVM classifier to classify the HEs and nonHEs. The experiment is based on the public diabetic retinopathy database DIARETDB1, we achieve a sensitivity of 91.1% and a specificity of 94.7%. The experimental results indicate that our method can conduct reliable detection of HEs.



Key words:

, Key words: , diabetic retinopathy； fundus images； hard exudates； SVM； AMFM

CLC Number:

TP391.41

PAN Yanhong, PAN Lin. Detection of Hard Exudates in Fundus Images Based on SVM[J]. Computer and Modernization, 2014, 0(4): 33-37.

References

［1］

Watkins P J. ABC of diabetes: Retinopathy［J］. BMJ: British Medical Journal, 2003,326(7395):924926.

［2］ Phillips R, Forrester J, Sharp P. Automated detection and quantification of retinal exudates［J］. Graefe’s Archive for Clinical and Experimental Ophthalmology, 1993,231(2):9094.

［3］ Sinthanayothin C, Boyce J F, Cook H L, et al. Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images［J］. British Journal of Ophthalmology, 1999,83(8):902910.

［4］ Walter T, Klein J C, Massin P, et al. A contribution of image processing to the diagnosis of diabetic retinopathydetection of exudates in color fundus images of the human retina［J］. IEEE Transactions on Medical Imaging, 2002,21(10):12361243.

［5］ Osareh A, Shadgar B, Markham R. A computationalintelligencebased approach for detection of exudates in diabetic retinopathy images［J］. IEEE Transactions on Information Technology in Biomedicine, 2009,13(4):535545.

［6］ Adarsh P, Jeyakumari D. Multiclass SVMbased automated diagnosis of diabetic retinopathy ［C］// IEEE 2013 International Conference on Communications and Signal Processing (ICCSP). 2013:206210.

［7］ Osareh A. Automated Identification of Diabetic Retinal Exudates and the Optic Disc［D］. University of Bristol, 2004.

［8］ Garcia M, Sanchez C I, Poza J, et al. Detection of hard exudates in retinal images using a radial basis function classifier［J］. Annals of Biomedical Engineering, 2009,37(7):14481463.

［9］ Havlicek J P, Harding D S, Bovik A C. The multicomponent AMFM image representation［J］. IEEE Transactions on Image Processing, 1996,5(6):10941100.

［10］Murray V, Psttichis M, Soliz P. New AMFM analysis methods for retinal image characterization［C］// IEEE 2008 the 42nd Asilomar Conference on Signals, Systems and Computers. 2008:664668.

［11］Tomi Kauppi, Valentina Kalesnykiene, JoniKristian Kamarainen, et al. DIARETDB1Standard Diabetic Retinopathy Database ［DB/OL］. http://www2.it.lut.fi/project/imageret/diaretdb1/, 20070619.

［12］British Academic Association. Retinal Photography Screening for Diabetic Eye Disease［R］. London: British Academic Association, 1997.

［13］Hsu C W, Chang C C, Lin C J. A Practical Guide to Support Vector Classification［R］. University of National Taiwan, Department of Computer Science and Information Engineering, 2003.

[1]	WAN Yuwen， HUANG Linying， GAN Dengwen. A New Weightbased Association Rules Mining Algorithm [J]. Computer and Modernization, 2014, 0(4): 73-76.
[2]	WANG Shangchao, TANG Xiaochun. A Prioritybased Faulttolerant Task Scheduling Algorithm on Heterogeneous Clusters [J]. Computer and Modernization, 2014, 0(4): 69-72.
[3]	CHEN Huijie, XIE Yixiong. Human Posture Recognition Method Based on Multiple Classifiers [J]. Computer and Modernization, 2014, 0(4): 64-68.
[4]	CAO Jie, YU Xin. Congestion Control Algorithm for WSN in Traffic Information Collection [J]. Computer and Modernization, 2014, 0(4): 59-63.
[5]	LIU Minghui. Multiparty Quantum Secret Sharing Protocol Using Bell Particle [J]. Computer and Modernization, 2014, 0(4): 55-58.
[6]	ZHANG Zhong. Methods of Hooking IAT with Injection DLL into Remote Process [J]. Computer and Modernization, 2014, 0(4): 51-54.
[7]	CHEN Si1， LI Huafeng1， TU Qinghua1， TANG Dongyang2. Nonlocal Disaster Recovery System of Digitized Campus [J]. Computer and Modernization, 2014, 0(4): 47-50.
[8]	XING Yiliang， MA Liang， HAN Baoru， FU Shi. Image Fundamental Motion Scrambling Method in Uniform Velocity  Based on Knighttour Transformation [J]. Computer and Modernization, 2014, 0(4): 41-46.
[9]	CHEN Xiao, WANG Min， TAO Mingyang. Image Geometric Segmentation Method Based on 3D Context [J]. Computer and Modernization, 2014, 0(4): 38-40.
[10]	WU Zhenju. Extraction for Vehicles Contour Based on Stransformation Coupled Canny Operator [J]. Computer and Modernization, 2014, 0(4): 29-32.
[11]	FANG Xue, YU Ruixing. Gridbased Statistical Model for 3D Object Recognition [J]. Computer and Modernization, 2014, 0(4): 24-28.
[12]	YIN Shile， ZENG Zhiyong. An Improved Nystrom Spectral Clustering for Image Segmentation [J]. Computer and Modernization, 2014, 0(4): 20-23.
[13]	WU Ning, GUAN Shengqi, XU Shuaihua. Fabric Defect Detection Based on Periodicity and Local Directivity of Texture Edge [J]. Computer and Modernization, 2014, 0(4): 16-19.
[14]	GONG Dingxi, CAO Changrong. Plant Leaf Classification Based on CNN [J]. Computer and Modernization, 2014, 0(4): 12-15.
[15]	LING Shen， CHEN Guang， HAN Xiuling. Mobile Communication Virtual Experiment Based on 3D MAX and Virtools [J]. Computer and Modernization, 2014, 0(4): 8-11.