The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON SIGNAL PROCESSING
Transactions ID Number: 53-420
Full Name: Kavitha Karthikeyan
Position: Assistant Professor
Age: ON
Sex: Female
Address: Department of ECE,Nandha Engineering College,Vaikkalmedu,Perundurai Road,Erode-638 052
Country: INDIA
Tel:
Tel prefix:
Fax:
E-mail address: gskkavitha@gmail.com
Other E-mails: skkn03@gmail.com
Title of the Paper: automatic detection of hard exudates in monocular fundus images using entropies of gray tone spatial dependency matrix and classification using anfis
Authors as they appear in the Paper:
Email addresses of all the authors:
Number of paper pages: 10
Abstract: Diabetic Retinopathy is one of the most significant factors contributing to blindness and so early diagnosis and timely treatment is particularly important to prevent visual loss. In this paper an automated classifier is developed based on Adaptive Neuro-Fuzzy Inference System (ANFIS) to differentiate between normal and nonproliferative eyes from the quantitative assessment of monocular fundus images. Feature extraction is performed on the preprocessed fundus images. Hard Exudates were detected using CIE Color channel transformation, Entropy Thresholding and connected component analysis from the preprocessed fundus images. Features like area of blood vessels, area occupied by Hard Exudates, and texture properties were given as input to ANFIS. ANFIS was trained with Back propagation in combination with the least squares method. Proposed method was evaluated on 200 real time images comprising 70 normal and 130 retinopathic eyes. Results are validated with hand draw!
n ground truths from expert ophthalmologists. Quantitative performance of the method detected exudates with an accuracy of 99.5%. Performance of the classifier was measured by the Receiver operating characteristic curve generated by ANFIS. ANFIS provides best classification with a mean square error of 0.005 and this method can be used as a screening tool in the analysis and diagnosis of retinal images.
Keywords: Monocular fundus, Entropy, CIE color space, Hard exudates, Anfis
EXTENSION of the file: .doc
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress: image processing,Fuzzy Systems ,Image analysis and segmentation
IP ADDRESS: 115.184.22.43
