Guided Facial Skin Color Correction

This paper proposes an automatic image correction method for portrait photographs, which promotes consistency of facial skin color by suppressing changes due to background colors. In is often distorted the lighting environment (e.g., light reflected from a colored wall and over-exposure camera strobe). distortion emphasized when artificially synthesized with another color, appearance becomes unnatural. our framework, we, first, roughly extract face region rectify distribution in space. Then, we perform brightness around original achieve proper balance image, not affected luminance Our process attains natural results using guide unlike conventional algorithms. particular, guided filtering does require perfectly-aligned required proposed He et al. Experimental show that generates more than methods on only headshot photographs but also scene photographs. We yearbook style photo generation as application.