Proposal of a CBIR Framework for Retinal Images Using Fusion Edge Detection and Zernike Moments

详细信息    查看全文

• 关键词：Retinal blood vessels ; Diabetic retinopathy ; Edge detection ; Content based image retrieval ; Dempster ; Shafer fusion ; Zernike moments
• 刊名：Lecture Notes in Computer Science
• 出版年：2015
• 出版时间：2015
• 年：2015
• 卷：8947
• 期：1
• 页码：738-749
• 全文大小：2,068 KB
• 参考文献：1.Abràmoff, M.D., Garvin, M.K., Sonka, M.: Retinal imaging and image analysis. IEEE Rev. Biomed. Eng. 3, 169-08 (2010)View Article
  2.Kanski, J.J.: Clinical Ophthalmology: A Systemic Approach, 6th edn. Elsevier Health Sciences, London (2007). 952 pages
  3.Zheng, Y., He, M., Congdon, N.: The worldwide epidemic of diabetic retinopathy. Indian J. Ophthalmol. 60, 428-31 (2012)View Article
  4.Winder, R.J., Morrow, P.J., McRitchie, I.N., Bailie, J.R., Hart, P.M.: Algorithms for digital image processing in diabetic retinopathy. Comput. Med. Imaging Graph. 33, 608-22 (2009)View Article
  5.Yin, Y., Adel, M., Bourennane, S.: Automatic segmentation and measurement of vasculature in retinal fundus images using probabilistic formulation. Comput. Math. Methods Med. 2013, 1-6 (2013)MathSciNet View Article
  6.Fraz, M.M., Remagnino, P., Hoppe, A., Uyyanonvara, B., Rudnicka, A.R., Owen, C.G., Barman, S.A.: Blood vessel segmentation methodologies in retinal images - a survey. Comput. Methods Programs Biomed. 108, 407-33 (2012)View Article
  7.Li, X., Wee, W.G.: Retinal vessel detection and measurement for computer-aided medical diagnosis. J. Digit. Imaging 27, 120-32 (2014)View Article
  8.Karasulu, B.: Automatic extraction of retinal blood vessels: a software implementation. Eur. Sci. J. 8, 47-7 (2012)
  9.Sivakamasundari, J., Natrajan, V.: Analysis of human retinal vasculature for content based image retrieval applications. In: Panigrahi, B.K., Suganthan, P.N., Das, S., Dash, S.S. (eds.) SEMCCO 2013, Part II. LNCS, vol. 8298, pp. 606-16. Springer, Heidelberg (2013)View Article
  10.Sivakamasundari, J., Kavitha, G., Natarajan, V. Ramakrishnan, S.: Proposal of a content based retinal image retrieval system using kirsch template based edge detection. In: IEEE Conference on Informatics, Electronics & Vision, Dhaka, Bangladesh (2014)
  11.Zolfagharnasab, H., Naghsh-Nilchi, A.R.: Cauchy based matched filter for retinal vessels detection. J. Med. Sig. Sens. 4, 1- (2014)
  12.Goyal, A., Walia, E.: Variants of dense descriptors and Zernike moments as features for accurate shape-based image retrieval. SIViP 8, 1-7 (2013)
  13.Aich, S., Mamun, G.M.A.: An efficient supervised approach for retinal person identification using Zernike moments. Int. J. Comput. Appl. 81, 34-7 (2013)
  14.Tahmasbi, A., Saki, F., Shokouhi, S.B.: Classification of benign and malignant masses based on Zernike moments. Comput. Biol. Med. 41, 726-35 (2011)View Article
  15.Muller, H., Michoux, N., Bandon, D., Geissbuhler, A.: A review of content based image retrieval systems in medical applications -clinical benefits and future directions. Int. J. Med. Inf. 73, 1-3 (2004)View Article
  16.Mueen, A., Zainuddin, R., Sapiyan Baba, M.: MIARS: a medical image retrieval system. J. Med. Syst. 34, 859-64 (2010)View Article
  17.Ramamurthy, B., Chandran, K.R.: Content based image retrieval for medical images using canny edge detection algorithm. Int. J. Comput. Appl. 17, 32-7 (2011)
  18.Sivakamasundari, J., Kavitha, G., Natarajan, V., Ramakrishnan, S.: Content based human retinal image retrieval using vascular feature extraction. In: Pan, J.-S., Chen, S.-M., Nguyen, N.T. (eds.) ACIIDS 2012, Part II. LNCS, vol. 7197, pp. 468-76. Springer, Heidelberg (2012)View Article
  19.Xiang, F., Yong, H., Dandan, S., Jiexian, Z.: An image retrieval method based on Hu invariant moment and improved annular histogram. Elektronika IR Elektrotechnika 19, 114-18 (2013)
  20.Jadhav, D., Patil, M., Patil, A., Phalak, L.: A novel three stage CBIR using varying higher-order Zernike moments and its performance analysis. Int. J. Comput. Appl. 75, 33-8 (2013)
  21.Wei, C.H., Li, Y., Chau, W.Y., Li, C.T.: Trademark image retrieval using synthetic features for describing global shape and interior structure. Pattern Recogn. 42, 386-94 (2009)View Article
  22.K?hler, T., Budai, A., Kraus, M., Odstrcilik, J., Michelson, G., Hornegger, J.: Automatic no-reference quality assessment for retinal fundus images using vessel segmentation. In: IEEE International Symposium on Computer- Based Medical Systems, Porto, Portugal (2013)
  23.Shafer, G.: Perspectives on the theory and practice of belief functions. Int. J. Approx. Reason. 4, 323-62 (1990)MathSciNet View Article
  24.Lakshminarayanan, V., Fleck, A.: Zernike polynomials: a guide. J. Mod. Opt. 58, 545-61 (2011)View Article
  
• 作者单位：J. Sivakamasundari (16)
  V. Natarajan (16)
  
  16. Department of Instrumentation Engineering, Madras Institute of Technology, Anna University, Chennai, India
  
• 丛书名：Swarm, Evolutionary, and Memetic Computing
• ISBN：978-3-319-20294-5
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

Automated segmentation of blood vessels in retinal images is a critical component in the detection of diabetic retinopathy (DR). In this work, an attempt has been made to develop a Content Based Image Retrieval (CBIR) framework for retinal images. Various edge detection methods such as LoG, Canny, Sobel, Prewitt and Roberts are employed on preprocessed retinal fundus images to segment blood vessels. The output images of individual methods are integrated into four combinations such as LoG-Canny, Sobel-Canny, Sobel-Prewitt and Roberts-Prewitt using D-S fusion technique. The low and high-order invariant Zernike moments are extracted from the segmented blood vessels in four combinations and are analyzed. Results show that the D-S fusion based LoG-Canny edge detection provides continuous vessel map and higher vessel width than the other three combinations. The high-order Zernike moments of this group shows significant differentiation between normal and abnormal images. The retrieval performance such as precision and recall for D-S fusion based CBIR system is found to be 93?% and 81?% respectively. This CBIR system could be useful for automated diabetic retinopathy detection in mass screening.