Biometric quality : from assessment to multibiometrics

Abstract

Quality is an attribute or a property of an item that quantitatively measures specific aspect or content. The definition and correct method of measurement of quality of a biometric modality that is usually represented by an image is currently unclear in the research community. While a biometric image’s quality is susceptible to degradation during capture and storage, it may also have low quality by its very nature. Quality of a biometric has several applications in popular research interests such as i) unconstrained biometric recognition ii) multibiometrics and iii) large-scale identity projects. This research aims to define and demystify quality in the field of biometrics. We present a comprehensive survey of current advancements in quality assessment, starting with a concise summary of the field of Biometrics and recent advances and applicability of quality in multibiometrics. In order to understand quality assessment in biometrics, we delve into related area of image quality assessment. Further, several applications and factors that influence biometric quality are analyzed. We also investigate popular methods of evaluating quality assessment algorithms in biometrics. Finally, we explore quality in face recognition, an area that is yet to receive proportionate attention from the research community. The complexity of the problem is multiplied by the lack of consensus in literature on the definition and constitution of facial features. However, initial experiments indicate that holistic image descriptors are able to successfully encode degradations in biometric images.