Wavelet transform algorithm for iris recognition
Guangshu Hu · Journal of Tsinghua University(Science and Technology) · 2003
Iris recognition algorithms based on wavelet transform zerocrossing are sensitive to the grey variation of the iris image texture. A new iris recognition algorithm was developed using the bandpass characteristic of wavelets and the wavelet transform principles for detecting singularities. The iris image texture is divided into eight bands with an appropriate scale wavelet used to filter each band for quantization to 256 byte iris feature codes. Then the Hamming distance is used to match two iris codes. Tests show that this method which is translation, rotation, and scaling invariant requires approximately 1s to complete recognition and achieves an identification rate of 97.04%, so it can be used in a personal identification system.