A Survey on Face and Body Based Human Recognition Robust to Image Blurring and Low Illumination

Many studies have been actively conducted on human recognition in indoor and outdoor environments. This is because methods such environments are closely related to everyday life situations. Besides, these can be applied for finding missing children identifying criminals. Methods classified into three categories: face-, body-, gait-based methods. There various factors that hinder recognition, example, blurring of captured images, cutoff images due the camera angle, poor acquired low-illumination Previous solve problems focused facial only. face typically assumed contain more important information than body. However, when a by distant small, or even impossible identify with naked eye, body’s help recognition. For this reason, survey paper reviews both face- body-based In previous surveys, low-resolution were reviewed. papers blurred not comprehensive. Therefore, paper, we review image restoration detail classifying them based whether deep learning was used body combined. Although covered as well, they excluded survey, also include details deep-learning-based We aim researchers who will study fields future.