With the global demand for extra security systems, and the growing of human-machine interaction, facial analysis in unconstrained environments (in the wild) became a hot-topic in recent computer vision research. Unconstrained environments include surveillance footage, social media photos and live broadcasts. This type of images and videos include no control over illumination, position, size, occlusion, and facial expressions. Successful facial processing methods for controlled scenarios are unable to pledge with challenging circumstances. Consequently, methods tailored for handling those situations are indispensable for the face analysis research progress. This work presents a comprehensive review of state-of-the-art methods, drawing attention to the complications derived from in the wild scenarios and the behavior differences when applied to the controlled images.The main topics to be covered are: (1) face detection; (2) facial image quality; (3) head pose estimation; (4) face alignment; (5) 3D face reconstruction; (6) gender and age estimation; (7) facial expressions and emotions; and (8) face recognition. Finally, available code and applications for in the wild face analysis are presented, followed by a discussion on future directions.