Jinghua Wang finished his Master thesis “Finger Image Quality Based on Singular Point Localization” after working with da/sec and CASED in the period of February 2013 to July 2013.
Finger image quality assessment is a crucial task in the fingerprint-based biometric systems, and plenty of publications state that singular points have the profound influence on the biometric performance. The aim of the thesis is to analyze whether the singular points are significant and what is the degree of importance on the biometric performance.
Existing approaches of orientation field estimation and singular point localization are discussed in this work, and the most accurate and robust of them are applied. Five pattern-based filters are proposed to reduce the detected spurious singular points. One segmentation algorithm is proposed using morphological image processing.
Seven singular point localization-based global Quality Measurement Algorithms are proposed to systematically analyze the effect of singular points on the biometric performance by measuring the finger sample displacement and rotation. Experimental results establish the property of singular points does have influence on biometric performance although not better than the analysis of fine level characteristics (e.g., ridgeline and frequency). Four local Quality Measurement Algorithms are proposed to give the quality score by analyzing the coherence of the ridgeline. Acceptable results are achieved with excellent execution time.