Review of Preprocessing Techniques for Fundus Image Analysis

Review of Preprocessing Techniques for Fundus Image Analysis

Shilpa Joshi P.T. Karule

Y.C.C.E., Hingna, Nagpur 441110, India

Corresponding Author Email: 
ssjd10@gmail.com, ptkarule@gmail.com
Page: 
593-612
|
DOI: 
https://doi.org/10.18280/ama_b.600306
Received: 
26 December 2017
| |
Accepted: 
8 January 2018
| | Citation

OPEN ACCESS

Abstract: 

The principal target of preprocessing is to get more appropriate resultant image than its original for further additional analysis. Enhancement of retinal images creates several challenges. The main obstacle is to develop a technique to accommodate the wide variation in contrast inside the image. Necessity of preprocessing methods are for image normalization and to increase the contrast for achieving accurate analysis. This work examined literature in the prior process of digital imaging, in the field of the analysis of fundus image to extract normal and pathologic retinal traits within the context of diabetic retinopathy (DR).

Keywords: 

Color Space Conversion, Filtering, Contrast Enhancement, Shade Correction

1. Introduction
2. Related Work
3. Color Space Conversion and Normalization
4. Shade Correction
5. Adaptive Contrast Enhancement
6. Background Exclusion
7. Filtering
8. Morphological Processing
9. Mask Generation
10. Conclusion
  References

[1] A. Sopharak, A. Uyyanonvara, S. Barmanb, Williamson, Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods, 2008, Computerized Medical Imaging and Graphics, pp. 720–727.

[2] A. Sopharak, A. Uyyanonvara, Automatic Exudates Detection from Non-Dilated Diabetic Retinopathy Retinal Images using Fuzzy C-means Clustering, 2009, Sensors, pp. 2148-2161.

[3] M. Iqbal, A. Aibinu, Detection of Vascular intersection in retinal fundus Image using Modified Cross point number and NN Technique, 2008, Int. Conf. Comp. Comm. Engg, pp. 241 - 246.

[4] D. Usher, Dumskyi, Wiiamson, Nussey, Automated detection of diabetic retinopathy in digital retinal images: Tool for diabetic retinopathy screening, 2004, Diabet Med Engg, 21, pp 84-90.

[5] G. Nayomi, R. Ranamuka, N. Gayan, Meegama, Detection of hard exudates from diabetic retinopathy images using fuzzy logic, 2013, IET Image Processing, Vol. 7, 2, pp. 121–130.

[6] P. R. Asha, S. Karpagavalli, Diabetic Retinal Exudates Detection Using Extreme Learning Machine, 2015, Emerging ICT for Bridging the Future, pp. 1-5.

[7] J. P. Bae, K. G. Kim, H. C. Kang, C.B. Jeong, K. Park, A study on Hemorrhages detection using Hybrid method in fundus Images, 2010, Journal of Digital Imaging, pp. 394-404.

[8] C. Sanchez, A. Mayo, M Garcia, A. Hornero, Automatic Image Processing Algorithm to Detect Hard Exudates based on Mixture Models, 2006, IEEE EMBS Annual Int. Conf, pp. 4453-4456.

[9] H. Yazid, H. Arof, N. Mokhtar, Edge Sharpening for Diabetic Retinopathy Detection, 2010 IEEE Conf. on Cybernetics and Intelligent Systems, pp. 41 - 44.

[10] C.I. Sanchez, Poza, Retinal Image Analysis to Detect and Quantify Lesions Associated with Diabetic Retinopathy, 2004, Int. Conf. on Eng. in Medicine and Biology, pp. 1624–1627.

[11] M. Lotankar, K. Noronha, J. Koti, Detection of Optic Disc and Cup from Color Retinal Images for Automated Diagnosis of Glaucoma, 2015, UPCON, pp.1-6.

[12] S. Kavitha, K. Duraiswamy, Automatic Detection of Hard and Soft Exudates in Fundus Images Using Color Histogram Thresholding, 2011, European J. of Scientific Research, pp.493-504.

[13] K. Goatman, A. Whitwam, A. Manivannan, J. Olson, A. Sharp, Color normalization of retinal images, 2003, Int. Proceeding medical image understanding and analysis, pp. 149-152.

[14] A. Osareh, M. Mirmehdi, B. Thomas, R. Markham, Automated identification of diabetic retinal exudates in digital color images, British Journal of Ophthalmology, 2003, no. 87, pp. 1220–1223.

[15] A. Osareh, M. Mirmehdi, B. Thomas, Markham, Classification and localization of diabetic-related eye disease,2002, 7th European Conference on Computer Vision, pp. 502-516.

[16] A. Osareh, Automated Identification of Diabetic Retinal Exudates and the Optic Disc, PhD thesis, Department of Computer Science, University of Bristol, 2004.

[17] S. Lee, Y. Wang, Computer algorithm for detection and quantification of microaneurysms and hemorrhages in color retinal images, 1999, Int. Conf. Image Perception Performance, pp.61-71.

[18] M. Cree, E. Ganble, D. Cornforth, Color normalization to reduce inter-patient and intra-patient variability in microaneurysms detection in color retinal images, 2005, WDIC ARPS workshop on digital image computing Brisbane, Australia, pp.163-168.

[19] H. Hipwell, Strachan, Olson, McHardy, Sharp, Automated detection of microaneurysms in digital red-free photographs: a diabetic retinopathy screening tool,2000, Diabetic. Med, pp. 588-594. 

[20] B. Dupas, T. Walter, A. Erginay, et al., Evaluation of automated fundus photograph analysis algorithms for detecting microaneurysms, HEs and exudates and of a computer-assisted diagnostic system for grading diabetic retinopathy, Diabetic. Metab, 2010, vol.36, pp.213-220.

[21] V. Shanmugam, W. Banu, Retinal blood vessel segmentation using an extreme learning machine approach, IEEE 2013, Point-of-Care Healthcare Technologies, pp. 318 –321.

[22] P. Badea, D. Dnciu, Preliminary rules on using extension of gradient method for detection red lesions on fundus photographs, Aut. quality testing robotics, IEEE 2008, Int. Conf. pp 43-48.

[23] V. Mane, D. Jadhav, Ramish, Preprocessing in Early Stage Detection of Diabetic Retinopathy Using Fundus Images, 2015, Adv. of Med. Electronics, Lecture Notes Bioengg, pp. 27-38.

[24] R. C. Ganzalez and R. E. Woods, Digital image processing, Second edition. Prentice Hall: New Jersey, 2001.

[25] K. Zuiderveld, Contrast limited adaptive histogram equalization,1994, Graphics Gems, vol. 4, pp. 474–485.

[26] T. Yamuna and S. Maheswari, Detection of abnormalities in retinal images, ICECCN IEEE 2013, pp. 236-240.

[27] C. Sinthanayothin, Boyce, Williamson, Automated localization of the optic disk, fovea and retinal blood vessels from digital color fundus images, 1999, British Journal Opth. 902–910.

[28] C Sinthanayothin, K. Viravud, P. Suthee, S. Apichart, Automated screening system for diabetic retinopathy, 2003, International Symp. on Image and Signal Processing Analysis, pp. 915–920.

[29] G. Yang, S. Wang, I. Gagnon, Boucher, Algorithm for detecting microaneurysms in low resolution color retinal images, 2001, In Proc. Vision Interface 21, pp. 139-142.

[30] A. Youssif, Ghoneim, Comparative study of contrast enhancement and illumination equalization methods for retinal vasculature segmentation, 2006, Int. Biomed. Engg. Conf., pp.21-24.

[31] U. Akram, A. Tariq, S. Nasir, Automated Retinal Images: Noise Segmentation, IEEE 2008, Int. Multitopic Conference, pp. 23-24.

[32] X. Zhang, O. Chutatape, S. Nemeth, P. Soliz, Detection and classification of bright lesions in color fundus images, 2004, Int., Conf. on image processing, vol. 1, 53(6), pp. 139-142.

[33] M. H. Goldbaum, N. P. Katz, S. Chaudhuri, M. Nelson, P. Kube, Digital image processing for ocular fundus images, 1990, Ophthalmology, Clinical North American, vol. 3, pp. 756–760.

[34] S. Lee, E. Lee, Y. Wang, Comparison of diagnosis of early retinal lesions of DR between computer system and human experts, 2001, Gra. Arch. Clin. Exp. Opht. vol. 119, pp. 509- 515.

[35] H. Wang, W. Hsu, K. Goh, M. L. Lee, An effective approach to detect lesions in color retinal images, 2000, IEEE CVPR, pp. 181-187.

[36] D. Wu, M. Zhang, J. Liu, W. Bauman, On the adaptive detection of blood vessels in retinal images, 2006, IEEE Transaction on Biomedical Engineering, vol.53, no. 2, pp. 341–343.

[37] A. Osareh, M. Mirmehdi, Automatic recognition of exudative maculopathy using FCM and neural networks, 2001, Medical Image Understanding and Analysis, pp. 49–52.

[38] T. Walter, J. Klein, Automatic detection of microaneurysms in color fundus images of human retina by means of the bounding box closing, 2002, Lecture Notes in Comp. Sci pp.210-220.

[39] T. Walter, P. Massin, A. Arginay, R. Ordonez, C. Jeulin, J. Klein, Automatic detection of microaneurysms in color fundus images, 2007, Med. Image Anal., vol. 11, pp. 555–566.

[40] F. Haar, Automatic localization of the optic disc in digital color images of the human retina, 2005, M.S. Thesis, Utrecht University.

[41] M. Himaga, D. Usher, Retinal Blood Vessel extraction by using multi-resolution matched filtering and directional region growing segmentation, 2002, IAPR machine vision appl., pp. 529–51.

[42] V. Raman, P. Then, P. Sumari, Automatic Hemmorrhages detection based on fundus images, 2016, 7th IEEE Conf., on information technology and electrical Engg., pp 253-258.

[43] J. Nayak, P. Subbanna, Bhat, R. Acharya, C. M. Lim, M. Kagath, Automated Identification of Diabetic Retinopathy Stages Using Digital Fundus Images, 2007. 

[44] K Saranya, B Ramasubramanian, S. Mohideen, A novel approach for the detection of new vessels in the retinal images for screening diabetic retinopathy, 2012, ICCSP, pp. 57–61. 

[45] J. Dash, N Bhoi, A Survey on Blood Vessel Detection Methodologies in Retinal Images, Int. Conf. on Computational Intelligence and Networks, 2015, 2375-5822/15 IEEE.

[46] E. Grisan, A. Giani, Ceseracciu, Ruggeri, Model-based illumination correction in retinal images, 2006, Int. Symposium on Biomedical Imaging: Nano to Macro 984–987.

[47] A. Pandey, R. Chandra, M. Datta, R. burget, J. Minar, Automatic Detection of Red Lesions in Diabetic Retinopathy using Shape based Extraction Technique in fundus image, IEEE 2016, 39th Int. Conference on Telecommunications and Signal Processing TSP, pp. 756–760.

[48] M. Foracchia, E. Grisan, A. Ruggeri, Luminosity and contrast normalization in retinal images, 2005, IEEE Transaction on Medical Imaging. Analysis, no. 9, pp. 179–190. 

[49] D. Zhang, X. Li, X Shang, Y Yi, Y Wang, Robust Hemorrhage detection in diabetic retinopathy image, IEEE (2012), pattern Recognition ACPR, pp. 756–760.

[50] M. Garcia, I. Sancheza, M. Lopezb, D Abasoloa, R. Horneroa, Neural network based detection of hard exudates in retinal images,2009, Comp methods and prog. in biomedicine, pp.9–19. 

[51] M. J. Cree, J. A. Olson, P. Sharp, V. J. Forrester, The preprocessing of the retinal image for the detection of fluorescein leakage, 1999, Physics in Medicine and Biology, pp. 293.

[52] M. Foracchia, E. Grisan, A. Ruggeri, Detection of optic disc in retinal images by means of a geometrical model of vessel structure, 2004, IEEE Trans. on Medical Imaging, pp. 1189-1195 

[53] N. Mukherjee, H. Dutta, A New Approach for Color Distorted Region Removal in Diabetic Retinopathy Detection, 2015, Adv. of Medical Electronics, Lecture Notes in Bioengineering.

[54] J. Sivakamasundari, V. Natarajan, Proposal of a CBIR Framework for Retinal Images Using Fusion Edge Detection and Zernike Moments,2015, SEMCCO, LNCS 8947, pp. 738–749.

[55] M. Fadzil, L. Izhar, H. Nugroho, Determination off avascular zone in diabetic retinopathy digital fundus images, 2010, Computers in Biology and Medicine 40, pp. 657–664.

[56] K. Ram, G. Joshi, and J. Sivaswam, A Successive Clutter-Rejection based Approach for Early Detection of Diabetic Retinopathy, 2011, IEEE Trans. on Biomedical Engineering, pp. 1-9. 

[57] D. Marwan, C. Eswaran, A Mueen, An Automated Blood Vessel Segmentation Algorithm Using Histogram Equalization and Automatic Threshold Selection,2010, J. of Digital Imaging 

[58] K. Oktoeberza, H. Nugroho, T. Adji, Optic Disc Segmentation Based on Red Channel Retinal Fundus Images, 2015 ICSIIT, CCIS 516, pp. 348–359.

[59] B. Zhang, X. Wu, J. You, Q. Li, F. Karray, Detection of microaneurysms using multi-scale correlation coefficients, 2010, Pattern Recognition, vol. 43, no. 6, pp. 2237–2248.

[60] J. Anitha, D. Selvathi, D. Jude, Hemanth, Neural Computing Based Abnormality Detection in Retinal Optical Images, IEEE 2009, Int. Advance Computing. Conf. pp. 6-7.

[61] I. Lazar, A. Hajdu, Microaneurysms detection in retinal images using a rotating cross-section based model, 2011, Proc. IEEE Int. Symposium Biomedical Imaging, pp. 1405–1409.

[62] A. Fleming, S. Philip, Goatman, Automated microaneurysms detection using local contrast normalization and local vessel detection, 2006, IEEE Trans on Med. Imaging, pp. 1223–1232.

[63] S. Abdelazeem, Microaneurysms detection using vessel removal and circular Hough transform, 2002, National Radio Science, Conf. pp.421– 426.

[64] H-SNam, J. M. Hwang, H. Chung, J-M Seo, Automated measurement of retinal vessel diameters on digital fundus photographs, WC 2009, IFMBE Proc, pp.277-280.

[65] E Grisan, Thesis, Automatic Analysis of Retinal Images: Retinopathy Detection and Grading.

[66] T. Spencer, Olson, K. C. McHardy, Sharp, J. V. Forrester, An image-processing strategy for the segmentation and quantification of microaneurysms in fluorescein angiograms of the ocular fundus, 1996, Computer Biomed. Res., vol. 29, pp. 284–302.

[67] A. Frame, Undrill, Cree, Olson, McHardy, P. Sharp, Forrester, A comparison of computer based classification methods applied to the detection of microaneurysms in ophthalmic fluorescein angiograms, 1998, Computers in Bio. and Med, pp. 225 238.

[68] I Lazar, R. Hajdu, R. Quareshi, Retinal microaneurysms detection based on intensity profile analysis, 2010, 8th International Conference on Applied Informatics, pp.1405 – 1409.

[69] M. Tamilarasi, K Duraiswamy, Genetic based fuzzy seeded region growing segmentation for diabetic retinopathy images, 2013, ICCCI International Conference on. IEEE, pp.1–5.

[70] M. Akram, S. Khalid, S. Khan, Identification and classification of microaneurysms for early detection of diabetic retinopathy, 2012, Pattern recognition, pp. 1–10.

[71] G. Urcid, Lara-R L.D, Lopez-M E., Pathologies Segmentation in Eye Fundus Images Based on Frequency Domain Filters. WCECS 2015, Transactions on Engg. Technologies, pp. 137-151.

[72] N. Ward, S. Tomlinson, C. Taylor. Image analysis of fundus photographs. 1989, Ophthalmology, 96, pp. 80–86.

[73] R. Phillips, F. John, P. Sharp. Automated detection and quantification of retinal exudates, 1993, Graefe’s Archive for Clinical and Experimental Ophthalmology, vol. 231, pp. 90–94. 

[74] S. Sreng, N. Maneerat, I. Don, Automatic hemorrhages detection based on fundus images, 2015, ICITEE, pp. 253 – 257.

[75] M. Paing, C. Somsak, R. Yodprom, Detection of lesions and Classification of Diabetic Retinopathy using Fundus Images, IEEE 2016, Bio Med. Int. Conf., pp: 573 – 577.

[76] M. Preethi., R. Vanithamani, Review of Retinal Blood Vessel Detection Methods for Automated Diagnosis of Diabetic Retinopathy, IEEE- 2012, conf. ICAESM -2012, pp. 262 – 265.

[77] S. Kumar, Madheswran, Extraction of Blood Vascular Network for development of Automated Diabetic Retinopathy Screening, IEEE 2009 comp. tech. and development, vol. 2, pp. 360-64.

[78] A. Akram, A. Tariq, S Nasir, S Khan, Gabor Wavelet based vessel segmentation in Retinal Images, 2009, IEEE Symp. on Computational Intelligence for Image Processing, pp. 116 – 119.

[79]  M. Niemeijer, B. Ginneken, Russell, Abramoff, Automated detection and differentiation of drusen exudates and cotton wool spots in digital color fundus photographs for diabetic retinopathy diagnosis, 2007, Investigative Ophthalmology Visual Science, pp. 2260-2267.

[80] S. Mukhopadhyay, B. Chanda, Multiscale morphological approach to local contrast enhancement, 2000, Signal Processing, vol. 80, no.4, pp.685–696.

[81] A. Mendonca, A. Campilho, Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction, 2006, IEEE Transaction on Medical Imaging vol.25, no.9, pp.1200–1213.

[82] P. Tang, H. Liu, K. Sun, Enhancement of coronary angiogram by estimation of local background in Medical Imaging, Parallel Processing of Images, and Optimization Techniques Proc. SPIE 6789, MIPPR 2007.

[83]  X. Bai, F. Zhou, B. Xue, Image enhancement using multi scale image features extracted by top-hat transform, Optics & Laser Technology, 2012, vol. 44, Issue 2, pp. 328–336.

[84] X. Bai, Mineral image enhancement based on sequential combination of toggle and top-hat based contrast operator, 2013, Micron, vol.44, pp.193–201.

[85] T. Walter, J. Klein, Segmentation of color fundus images of the human retina, 2001, 2nd Int. Symposium on Medical Data Analysis, pp. 282–287. 

[86] D Marin, A. Aquino, M. Arias, J. Manuel Bravo, A new supervised method for blood vessel segmentation in retinal images by using gray-level and moment invariants-based features, 2011, IEEE Transactions on Medical Imaging, vol. 30, no. 1, pp. 146–158.

[87] K. Sun, Z. Chen, Y. Wang, Morphological multiscale enhancement, fuzzy filter and watershed for vascular tree extraction in angiogram, 2011, Journal of med. systems, vol. 35,5, pp. 811-24.

[88] L. Giancardo, Y. Li, K. Tobin, E. Chaum, Automatic retina exudates segmentation without a manually labelled training set, 2011, Biomed Imaging Nano to Macro, IEEE pp. 1396–1400.

[89] S. Ravishankar, A. Jain, A. Mittal, Automated feature extraction for early detection of diabetic retinopathy in fundus images, 2009, IEEE Conf. Comput. Vision Pattern Recog, pp. 210–217.

[90] G. Hassana, N. Bendary, A. Hassanien, A. Fahmy, A. Shoeba, V. Snasel, Retinal blood vessel segmentation approach based on mathematical morphology, 2015, ICCMIT vol.65,pp. 612-622

[91] D. Youssef, N. Sollouma A. El-dib, New feature based detection of Blood Vessels and Exudates in fundus Image, Image Processing Theory, tools and Application, 2010, IEEE pp. 294-299.

[92] S. Fahimuddin, A. Sharma, S. Ahmed, Hybrid model for analysis of abnormalities in diabetic cardiomyopathy and diabetic retinopathy related images, 2016, Springer Plus 20165:507. 

[93] Y. Wong, U. Acharya, Y. Venkatesh, C. Caroline, Identification of different stages of diabetic retinopathy using retinal optical images, 2008, Information Sciences 178, pp.106-121.

[94] A. Gonzalez, D. Kaba, Y. Li, X. Liu, Segmentation of the Blood Vessels and Optic Disk in Retinal Images, 2014 IEEE Journal of Biomed. And Health Info. Vol. 18, 4, pp. 1874-1886.

[95] A. Elbalaoui, M.Fakir, K.Taifi, Merbouha, Automatic Detection of Blood Vessel in Retinal Images, IEEE 2016, 13th Int. Conf. Comp. Graphics, Imaging and Visualization.

[96] L. Gagnon, M. Lalonde, M. Beaulieu, M. Boucher, Procedure to detect anatomical structures in optical fundus images, 2001, SPIE Conf. on Medical Imaging pp. 1218–1225. 

[97] K. Englmeier, K. Schmid, M. Maurino, M. Porta, Bek, O. Larsen, Hejlesen, Multi-resolution retinal vessel tracker based on directional smoothing, 2002, 3(21): 230–237.

[98] 98. Santha Kumar, Rajkumar, Tandur, Novel method for Automatic generation of Fundus Mask, 2016, Image Info. Processing Conf. IEEE, pp. 147 – 151. 

[99] 99. F. Hashim, N. Salem, A. F. Seddik, Preprocessing of Color Retinal Fundus Images, 2014, JEC-ECC IEEE, pp.190 – 193.

[100] 100. P. Porwal, M. Kokare, A novel Method to remove Bright Artifacts for Enhancing Lesion Detection in Retinal Images, 2017, Icon, SIP IEEE pp. 1–5.

[101] 101. A. Youssif, A. Ghalwash, Optic Disc detection from Normalized Digital Fundus Image by Means of Vessel’s Detection Match Filter, 2008, IEEE Trans on Med Imaging, pp. 11-18.

[102] 102. P. Manjiri, M. Ramesh, R. Yogesh, S. Manoj, Automated Localization of Optic Disk, Detection of Microaneurysms and Extraction of Blood Vessels to Bypass Angiography, 2014, FICTA, Adv. in Intelligent System and Computing, pp. 579-587.

[103] 103. R. Chon, J. C. Suniel, Histogram-Based Masking Technique for Retinal Fundus Images, 2015, Ubiquitous Computing App. Wireless Sensor, Lect. Notes Electrical Engg pp. 561-567. 

[104] 104. Y. Zheng, Daniel, An Automated drusen detection for classifying age related macular degeneration with color fundus photograph, 2013, IEEE Symp. Biomed. Imag., pp. 1448-51. 

[105] 105. R. Welikala, M. Fraz, J. Dehmeshki, A. Hoppea, V. Tahb, S. Mannc, Genetic algorithm based feature selection combined with dual classification for the automated detection of proliferative diabetic retinopathy, 2015, Computerized Medical Imaging and Graphics, vol 43, pp. 64-77.

[106] 106. A. Hoover, Kouznetzova, Goldbaum, Locating blood vessels in retinal images by piece-wise threshold probing of matched filter response, 2000, IEEE Trans. Med. Imag. 19(3): 203–210.

[107] 107. J. Leandro, Jr Cesar, Jelinek, Blood vessels segmentation in retina: Preliminary assessment of the mathematical morphology and the wavelet transform techniques, 2001, SIBGRAPI Brazilian Symp. on computer graphics and Image Processing, pp. 84–90.

[108] 108. D. Ye, L. Zheng, Fundus image processing and feature classification based on mathematical morphology, 2000, Canadian Med. and Bio. Engg. Conf., Vol. 2, pp. 1015–16.

[109] 109. D. Shin, R. Kaiser, M. Lee, J. Berger, Fundus image change analysis: Geometric and radiometric normalization, 1999, SPIE Conf. on Ophthalmic Technologies, pp. 129–136.

[110] 110. S. Lee, Identifying retinal vessel networks in ocular fundus images, Master’s thesis, 1992, The University of New Mexico.

[111] 111. C. Agurto, V. Murray, H. Yu, Wigdahl, M. Pattichis, S. Nemeth, E. Barriga, P. Soliz, A Multiscale Optimization Approach to Detect Exudates in the Macula, 2014, IEEE Journal of Biomed Health Info. Vol. 18, No. 4, pp. 1328-1336.

[112] 112. A. Budai, R. Bock, A. Maier, J. Hornegger, Robust Vessel Segmentation in Fundus Images, 2013, Hindawi Pub. Corp. Int. Journal of Biomed. Imaging, Article ID 154860, pp. 11.

[113] 113. B. Ege, O. Hejlesen, O. Larsen, Møller, B. Jennings, Kerr, D. Cavan, Screening for diabetic retinopathy using computer based image analysis and statistical classification Comp. Methods and Programs in Biomedicine, 2000, 62(3),165–175.

[114] 114. D. Marwan, C. Eswaran, An automated blood vessel extraction algorithm in fundus images, 2012, Int. conference on Bioinformatics and Biomedicine, pp. 482-486. 

[115] 115. G. Finlayson, S. Hordley, Improving gamut mapping color constancy, 2000, IEEE Transaction Image Processing, pp.1774–1783. 

[116] 116. D. Jobson, Z. Rahman, and G. A. Woodell, Properties and performance of a center/surround retinex, 1997, IEEE Transaction Image Processing, vol. 6, no. 3, pp. 451–462.

[117] 117. T. A. Soomro, J. Gao, Study of the Noise Level in the Color Fundus Images, ICDS 2015, LNCS 9208, Data Science, pp. 159-168.

[118] 118. M. J. Carlotto, Nonlinear background estimation and changed election for wide area search, 2000, Opt. Eng., vol.39, no.5, pp.1223–1229.

[119] 119. S. Rahim, V. Palade, C. Jayne, Holzinge, Detection of Diabetic Retinopathy and Maculopathy in Eye Fundus Images Using Fuzzy Image Processing, BIH 2015, LNAI, pp. 379–388.

[120] 120. S Rahim, V Palade1, S. James, C Jayne, Automatic Detection of Microaneurysms for Diabetic Retinopathy Screening Using Fuzzy Image Processing, 2015, EANN CCIS pp. 69–79.

[121] 121. D. Toth, T. Aach, V. Metzler, Illumination-invariant change detection, 2000, IEEE Southwest Symp. Image Analysis Interpretation, pp 667-676.

[122] 122. Guillemaud, Uniformity correction with homomorphic filtering on region of interest, 1998, IEEE Conf. Image Processing, pp. 872–875.

[123] 123. B. Brinkmann, A. Manduca, R. Robb, Optimized homomorphic unsharp masking for MR grayscale inhomogeneity correction, 1998, IEEE Trans. Med. Imaging, vol. 17, 2, pp. 161-71. 

[124] 124. J. Lou, H. Yang, W. Hu, T. Tan, 2002, An illumination invariant change detection algorithm, 5th Asian Conf. Computer Vision, Melbourne, Australia, pp. 1-6.

[125] 125. R. Jain, K. Skifstad, Illumination independent change detection from real world image sequences, 1989, Computer Vis. Graph. Image Processing, vol. 46, pp. 387–399. 

[126] 126. Y. Plotnikov, N. Rajic, W. P. Winfree, Means of eliminating background effects for defect detection and visualization in infrared thermography, 2000, Opt. Eng., vol. 39, no. 4,pp.89-96.

[127] 127. J. Hajer, H. Kamel, E. Noureddine, Localization of the optic disk in retinal image using the “watersnake”, 2008, Int. Conf. on Computer and Communication Engineering, pp. 947 – 951.

[128] 128. A. Criminisi, P. Perez, K. Toyama, Object removal by exemplar based inpainting, 2003, in Proc. IEEE Conf. Computer Vision Pattern Recognition, vol. 2, pp. 721–728.

[129] 129. K. Narasimhan, V. Neha, K. Vijayarekha, An efficient automated system for detection of diabetic retinopathy from fundus images using support vector machine and Bayesian classifiers, 2012, Int. Conference ICCEET, IEEE, pp. 964–969.

[130] 130. K. Goatman, A. Fleming, S. Philip, G. J Williams, J. A Olson, P. Sharp, Detection of new vessels on the optic disc using retinal photographs, 2011, IEEE Trans. on Med. Imaging, pp. 972–979.

[131] 131. K.G. Goh, W. Hsu, Li Lee, H. Wang, ADRIS: Automatic Diabetic Retinal Image Screening system. 2001, In Medical data mining and knowledge discovery, pp. 181-210.

[132] 132. J. Lee, BCY Zee, Q. Li, Detection of neovascularization based on fractal and texture analysis with interaction effects in diabetic retinopathy, 2013, PLoS ONE journal. pone.

[133] 133. D. Selvathi, N. Balagopal, Detection of Retinal Blood Vessels Using Curvelet Transform, 2012, International Conference on Devices, Circuits and Systems, pp. 325 – 329.

[134] 134. A. Narang, G. Narang, S. Singh, Detection of Hard Exudates in Color Retinal Fundus Images Using Support Vector Machine Classifier, 2013, Int. Congress on Image and Signal Processing, 6th International Congress on Image and Signal Processing, vol. 2, pp. 964 – 968.

[135] 135. M. Jahiruzzaman, A. Hossain, Detection and classification of diabetic retinopathy using K-means clustering fuzzy logic, 2015, Int. Conf. Comp. Info. Tech. IEEE, pp. 534 – 538.

[136] 136. H. Narasimha-Iyer, Roysam, Stewart, Tanenbaum, Robust detection and classification of longitudinal changes in color retinal fundus images for monitoring diabetic retinopathy, 2006, IEEE Transaction Biomed Engineering, 53(6), pp. 1084-98.

[137] 137. H. Narasimha-Iyer, A. Roysam, C. Stewart, et al., Integrated analysis of vascular and non-vascular changes from color fundus images, 2007, IEEE Tran. Biomed Engg, 54(8), pp. 1436-45.

[138] 138. J. Soares, J. Leandro, R. Cesar, Retinal Vessel Segmentation using the 2D Gabor wavelet and supervised Classification, 2006, IEEE Trans. Med Img. Vol. 25, 9, pp. 1214 – 1222.

[139] 139. N. Ian, M. Patricia, R. Winder, Image registration and subtraction for visualization of change in diabetic retinopathy screening, 2006, Comp. Med. Imaging and Graphics 139–145.

[140] 140. S. Morales, V. Naranjo, J. Angulo, A. Mariano, Automatic Detection of Optic Disc Based on PCA and Mathematical Morphology, 2013, IEEE Tran. Med. Imaging. vol. 32, 4, pp. 786-796.