An Efficient ELM Approach for Blood Vessel Segmentation in Retinal Images
Journal Title: Bonfring International Journal of Man Machine Interface - Year 2012, Vol 1, Issue 1
Abstract
Diabetic Retinopathy (DR) is one of the most important ophthalmic pathological reasons of blindness among people of working age. Previous techniques for blood vessel detection in retinal images can be categorized into rule-based and supervised methods. This research presents a new supervised technique for blood vessel detection in digital retinal images. This novel approach uses an Extreme Learning Machine (ELM) approach for pixel classification and calculates a 7-D vector comprises of gray-level and moment invariants-based features for pixel representation. The approach is based on pixel classification using a 7-D feature vector obtained from preprocessed retinal images and given as input to a ELM. Classification results (real values between 0 and 1) are thresholded to categorize each pixel into two classes namely vessel and nonvessel. Ultimately, a post processing fills pixel gaps in detected blood vessels and eliminates falsely-detected isolated vessel pixels. The technique was assessed on the publicly available DRIVE and STARE databases, widely used for this purpose, as they comprises of retinal images where the vascular structure has been precisely marked by experts. Method performance on both sets of test images is better than other existing solutions in literature. The approach proves particularly accurate for vessel detection in STARE images. Its efficiency and strength with different image conditions, along with its simplicity and fast implementation, make this blood vessel segmentation proposal appropriate for retinal image computer analyses such as automated screening for early diabetic retinopathy detection.
Authors and Affiliations
Merlin Sheeba X, Vasanthi S
Keywords
Related Articles
- EP ID EP98427
- DOI 10.9756/BIJMMI.1004
- Views 118
- Downloads 0
Effect of Dimension & Material Composition on Transmission Coefficient and Tunneling Current of Double Quantum Barrier Structure with Band Nonparabolicity
Transmission coefficient, eigen states and tunneling current density of a potentially symmetric quantum double barrier structure has been numerically computed using transfer matrix technique for qualitative analysis of r...
An Efficient ELM Approach for Blood Vessel Segmentation in Retinal Images
Diabetic Retinopathy (DR) is one of the most important ophthalmic pathological reasons of blindness among people of working age. Previous techniques for blood vessel detection in retinal images can be categorized into ru...
Implementation of Advanced Solar Tracking and Cleaning to Improve Efficiency
Solar energy is the most abundant source of energy for all forms of life. The sunlight is not used to the maximum extent in an ordinary solar power system and in order to take the highest potential of the system, Solar t...
Implementation of Wireless Underground Sensors Network
This paper instructs about Wireless Underground Sensor Networks (WUSNs) which constitute one of the promising application areas of the recently developed wireless sensor networking techniques. WUSN is a specialized kind...
Logical Design of Quaternary Signed Digit Conversion Circuit and its Effectuation using Operational Amplifier
In binary number system carry is a major problem in arithmetical operation. We have to suffer O(n) carry propagation delay in n-bit binary operation. To overcome this problem signed digit is required for carry free arith...