Iris location algorithm by vector field convolution

In order to improve the precision and accuracy of iris location, and furthermore enhance the recognition rate of the iris recognition system, a iris location algorithm based on Vector Field Convolution (VFC) was proposed to locate the iris inner boundary accurately. Firstly, minimum grey value method was used to determine initialization contour of VFC model automatically, so that the iris inner boundary could be located precisely under the internal and external force of active contour, then the improved Daugman algorithm was adopted to locate the iris outer boundary. Performed abundant experiments make use of several iris image databases, and also compared with common several kinds of iris localization methods. The experimental results show that the location accuracy of this method is higher, the iris inner edge location is much closer to the real boundary, and the result of location have been improved significantly.