Fingerprint local analysis for high-performance minutiae extraction

The paper presents a novel approach to identify the minutiae present in a fingerprint image based on the analysis of the local properties. The typical patterns of minutiae called ridge termination and bifurcation are identified by studying the intensity along squared paths in the image. The presented algorithm works both on grey-level image and binarized image and, despite its simplicity, it achieves good accuracy and it can be a good candidate to be implemented in hardware or executed on simple hardware architectures, for example in biometric systems embedded in portable applications such as cellular phones and smart cards.