Biometric walk recognizer. Research and results on wearable sensor-based gait recognition

Gait is a biometric trait that can allow user authentication, though being classified as a "soft" one due to a certain lack in permanence, and to sensibility to specific conditions. The earliest research relies on computer vision-based approaches, especially applied in video surveillance. More recently, the spread of wearable sensors, especially those embedded in mobile devices, which are able to capture the dynamics of the walking pattern through simpler 1D signals, has spurred a different research line. This capture modality can avoid some problems related to computer vision-based techniques, but suffers from specific limitations. Related research is still in a less advanced phase with respect to other biometric traits. However, the promising results achieved so far, the increasing accuracy of sensors, the ubiquitous presence of mobile devices, and the low cost of related techniques, make this biometrics attractive and suggest to continue the investigations in this field. The first Chapters of this thesis deal with an introduction to biometrics, and more specifically to gait trait. A comprehensive review of technologies, approaches and strategies exploited by gait recognition proposals in the state-of-the-art is also provided. After such introduction, the contributions of this work are presented in details. Summarizing, it improves preceding result achieved during my Master Degree in Computer Science course of Biometrics and extended in my following Master Degree Thesis. The research deals with different strategies, including preprocessing and recognition techniques, applied to the gait biometrics, in order to allow both an automatic recognition and an improvement of the system accuracy.