Adaptive Iris Recognition Method Based on the Marr Wavelet Transform Coefficients

This paper presents an adaptive iris recognition method based on the Marr wavelet transform coefficients. Firstly, it locates the iris and fits the contour of lower eyelid, then makes normalization to the iris image and gets 512 columns multiplying 64 rows rectangular iris image that ensures the effective iris area adaptively. Secondly, it makes one dimension Marr wavelet transform row by row to the iris image in the effective iris area, and gets a series of wavelet transform coefficients of different scales and gets the distribution figure of these coefficients of different scales. Thirdly, it makes binary codes to the iris image according to the coefficients of different scales and figures the iris pattern by iris codes. Finally, it sorts the different iris patterns by auto accommodated pattern matching method and gives the recognition results. Many experiments show the recognition rates of this method can reach 99.704% that can meet the demand of iris recognition.