Selected quality metrics for digital passport photographs
This thesis deals with the development of metrics for the automated determination of the quality and grade of acceptance of digital passport photographs without having any reference image available. Different kinds of algorithms were implemented to determine values for image attributes and to detect the face features. No priority for the evaluation of attributes was given in the documents of the international standards. For that reason an international online and on-site survey was developed to explore the opinion of user experts whose work is related to passport photographs. Three different metrics, expressed by the Photograph/ Image and Biometric Attributes Quality Indexes (PAQI, IAQI, BAQI) have been developed to obtain reference values for the quality determination of a passport photograph. Another metric developed is called "Non-Conformance Quality Index'' which is based on the representation of the quality information in the minimum unit of information storage: the byte. The nonconformance of a quality attribute is stored in a bit. For a digital passport photograph the representation of the quality attributes is defined by four bytes. Every byte has eight bits and every bit represents an attribute.
Zugl.: Darmstadt, TU, Diss., 2007