A rotation invariant retina identification algorithm using tessellation-based spectral feature

In this paper, a rotation-invariant retina identification algorithm based on tessellation of frequency spectrum is developed. In this algorithm, the proposed tessellation scheme provides rotation invariant, multi resolution and optimized features with low computational for our retina identification algorithm. The proposed algorithm is structured in two parts namely feature extraction and decision making. First step is forming feature vectors by applying proposed tessellation scheme on frequency spectrum of vessel skeleton of retinal image. Then, a specific scenario is defined based on energy spectrum of vessels to identify each individual. Finally, Euclidean distance criterion is used to evaluate the accuracy of proposed tessellation scheme. Experimental results show that the proposed algorithm obtains the accuracy rate of 99.29 % in presence of rotation and multi resolution samples.