Title :
Study of fully-automatic red-eye removal algorithm
Author :
YueLi Cui ; Zhigang Chen ; AiHua Chen
Author_Institution :
Coll. of Phys. & Electron. Eng., Taizhou Univ., Taizhou, China
Abstract :
“Red-eye effect” is a phenomenon that when a flashgun is used, the center of pupils appears unnaturally reddish. The automatic red-eye removal system can detect and correct red-eye automatically without manual intervention. First, faces are detected using Face Detection based on AdaBoost Algorithm, then the red-eyes are located using kinds of image processing method. At last the located red-eyes are finished corrected. The experimental results indicate that, the system can remove the red-eye automatically and effectively in the digital photo and has good robustness and rapidity.
Keywords :
face recognition; learning (artificial intelligence); AdaBoost algorithm; face detection; flashgun; fully automatic red eye removal algorithm; image processing; red eye effect; Classification algorithms; Equations; Face detection; Image color analysis; Pixel; Robustness; AdaBoost algorithm; Face detection; Red-eye location; Red-eye removal;
Conference_Titel :
Image and Signal Processing (CISP), 2010 3rd International Congress on
Conference_Location :
Yantai
Print_ISBN :
978-1-4244-6513-2
DOI :
10.1109/CISP.2010.5648115
