An automatic fingerprint classification technique based on global features

Fingerprint classification is an important stage in automatic fingerprint identification system (AFIS) because it significantly reduces the processing time to search and retrieve in a large-scale fingerprint database. However, its performance is heavily relied on image quality that comes in various forms such as low contrast, wet, dry, bruise, cuts, stains, etc. This paper proposed an automatic fingerprint classification scheme based on singular points and structural shape of orientation fields. It involves several steps, amongst others: firstly, fingerprint foreground is extracted and then noise patches in the foreground are detected and enhanced. Next, the orientation fields are estimated, and a corrective procedure is performed on the false ones. Afterward, an orientation image is created and singular points are detected. Based on the number of core and delta and their locations, an exclusive membership of the fingerprint can be discovered. Should it fail, the structural shape of the orientation fields neighboring the core or delta is analyzed. The performance of the proposed method is tested using 27,000 fingerprints of NIST Special Database 14. The results obtained are very encouraging with an accuracy rate of 89.31% that markedly outperformed the latest work.