Computer vision has been gaining increasing popularity in this age of automation and advancing technology. In particular, human detection has been looked into quite thoroughly in the recent years. Human detection is important in areas of surveillance, pedestrian detection, human-computer interaction etc where humans need to be detected very accurately. With accurate detection, postprocessing of human actions can then be done effectively. For accurate detection, it is necessary that the features and classification framework adopted are robust and effective. This book proposes several features that make use of gradient and/or texture information present in images and videos for representation and a non-linear classification framework for human detection. Existing features and classification frameworks of human detection are analyzed thoroughly and from their limitations, new features and a classification framework are derived. This development should help to advance human detection performance and should be especially useful to professionals in the Artificial Intelligence field or anyone developing a system for human detection.