The FPGA prototyping of iris recognition for biometric identification employing neural network
Faisal Mohd-Yasin, Aijiao Tan, Mamun Bin Ibne Reaz · 2005
In this paper, we present the realization of iris recognition for biometric identification employing neural network on Altera FLEX10 K FPGA device that allows for efficient hardware implementation. This method consists of two main parts, which are image processing and recognition. Image processing is implemented by using MATLAB and backpropagation method was used for recognition. The iris recognition neural network architecture is comprised of three layers: input layer with three neurons, hidden layer with two neurons and output layer with one neuron. Sigmoid transfer function is used for both hidden layer and output layer neurons. The timing analysis for the validation, functionality and performance of the model is performed using Aldec active HDL and the logic synthesis was performed using Synplify. Iris vector from captured human iris has been used to validate the effectiveness of the model. Test on the sample of 100 data showed an accuracy of 88.6% in recognizing the sample of irises.