Visible Results and Comparisons of A Near-linear Time Algorithm for Binarization of Fingerprint Images

Moayer and Fu [1] proposed an iterative algorithm using repeated convolution by a Laplacian operator and a pair of global dynamic thresholds that are progressively moved towards an unique value. The pair of global dynamic thresholds change with each iteration and control the convergence rate to the binary pattern. This method requiring repeated convolution operations is time consuming and the final result depends on the choice of the pair of dynamic thresholds and some other design parameters. As local information can not be dealt with well, there will always remain some impulsive noise needing further preprocessing.