Red eye moving method based on human face detection

Abstract

The red eye eliminating method based on human face detection in image treating technology includes three steps of: 1. human face detection with human face classifier obtained through computer learning algorithm training combined with skin color information to obtain the human face area from the picture; 2. red eye detection via dividing the detected area into typical red eye and wear red eye based on the red color distribution in the human face area; and 3. red eye correction via searching red eye area, color correction and edge smoothening to restore normal color of picture. The present invention adopts fast human face detecting algorithm to reduce red eye searching range and correction based on the color of pupils, and can detect precisely and correct red eye in digital picture in reasonable image processing speed even in condition of no attendance.

Description

technical field [0001] The invention relates to a method in the technical field of image processing, in particular to a method for removing red eyes based on face detection. Background technique [0002] The red-eye phenomenon is when the camera takes a portrait photo in flash mode, and there will be a red spot at the pupil of the person's eye in the photo. The reason for this is that the pupils of the human body will dilate when the ambient light is relatively dark. The strong light from the flashlight at close range passes through the dilated pupils and hits the microvascular tissue behind the retina, reflecting back red light, causing the actual imaged photos to appear "red-eye". . Red-eye is primarily affected by ambient brightness, subject age, the angle at which flash light bounces into the lens, and certain groups of people or ethnicities. Sometimes it occupies the entire pupil range and is reddish in color, and sometimes it only appears in a part of the pupil area ...

AI Technical Summary

Problems solved by technology

However, this patented technology performs red-eye removal processing on the basis of color information, and the effect of the method based on color information is not stable enough in practical applications, and red-eye is often missed for photos with poor lighting

Also doing the same treatment for all red-eye photos doesn't work well in some cases (especially if the red-eye is more golden)

Images