A Comparison between Contrast Limited Adaptive Histogram Equalization and Gabor Filter Sclera Blood Vessel Enhancement Techniques
Eliza Gail Maxwell1, Tripti C2
1Eliza Gail Maxwell, Department of Computer Science and Engineering, Rajagiri School of Engineering and Technology, Cochin, India.
2Tripti C, Department of Computer Science and Engineering, Rajagiri School of Engineering and Technology, Cochin, India.
Manuscript received on August 04, 2013. | Revised Manuscript received on August 28, 2013. | Manuscript published on September 05, 2013. | PP: 22-25 | Volume-3, Issue-4, September 2013. | Retrieval Number: D1763093413/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The importance of the human sclera lies in the uniqueness of the blood vessel structure which can be easily obtained non-intrusively in visible wavelengths. The unique and persistent characteristic of the sclera vessel patterns makes it a suitable candidate for human identification (ID). The proper segmentation of the sclera region and obtaining the sclera vessel patterns are the main problems that this biometric has to deal with. Images of sclera vessel patterns are often defocused or blurry and, most importantly, the vessel structure in the sclera is multilayered and has complex nonlinear deformations. This paper compares two sclera vessel enhancement methods. The first method uses a contrast limited adaptive histogram equalization with region growing technique. The other technique uses a directional Gabor filter bank to enhance the sclera veins. Experimental results showed that the Gabor filter-enhancement method yields faster and better results as compared to the histogram equalization and region growing method.
Keywords: Gabor filter, histogram, region-growing, sclera vessel pattern.