Structure-adaptive anisotropic filter applied to fingerprints

The propose a modified structure-adaptive anisotropic filter, which uses local intensity orientation and an anisotropic measure to control the shape of the filter kernel, and apply it to fingerprints. The modification is made in the frequency domain by converting the common structure-adaptive anisotropic filter from a low-pass filter to a band-pass one. We show that the modified structure-adaptive anisotropic filter can be effectively applied to applications, such as fingerprint image enhancement, in which the oriented patterns in local neighborhood form a sinusoidal-shaped plane wave with a well-defined frequency and orientation. The performance of the proposed structure-adaptive anisotropic filter is compared to some other filters used for minutiae detection. The proposed filter shows some improvement in terms of computational time and efficient.