Advances in the detection & repair of flash-eye defects in digital images - a review of recent patents

Red-eye and flash-eye defects in still photography continue to cause problems for digital imaging devices. New variants of flash-eye defects have appeared as cameras and cameras sub-systems get smaller in size. This paper reviews a wide range of the more recently patented techniques that have been applied to solve various problems associated with red and non-red flash-eye, particularly solutions which are implemented in the camera. The use of incamera metadata, multiple images of the same scene and adaptation of image acquisition conditions to improve red-eye detection and correction are explained. Four principle categories of flash-eye defect are identified and techniques are outlined to deal with each of these. The use of face, eye and scene metadata obtained within the camera is also considered. In particular data obtained regarding indoor/outdoor scenes, partial face regions, eye orientation and gaze and pupil size can all assist with some difficult cases of flash-eye defect. Some advanced techniques to improve the correction and reconstruction of eye regions are also considered. Index Terms —redeye detection, redeye correction, flasheye defects, embedded image processing.

[1]  马骞,et al.  An image processing method and apparatus , 2013 .

[2]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[3]  리차드 스젤리스키,et al.  Digital photography with flash/no flash extension , 2005 .

[4]  Peter M. Corcoran,et al.  Hybrid video-frame pre-processing architecture for HD-video , 2011, 2011 IEEE International Conference on Consumer Electronics (ICCE).

[5]  에란 스테인버그,et al.  Two stage detection for photographic eye artifacts , 2008 .

[6]  Peter M. Corcoran,et al.  Smart cameras: 2D affine models for determining subject facial expressions , 2010, IEEE Transactions on Consumer Electronics.

[7]  Michael F. Cohen,et al.  Digital photography with flash and no-flash image pairs , 2004, ACM Trans. Graph..

[8]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  コーコラン,ピーター,et al.  Real-time Face Tracking in a digital image acquisition device , 2007 .

[10]  W. Marsden I and J , 2012 .

[11]  Giovanni Maria Farinella,et al.  Red-eyes removal through cluster based Linear Discriminant Analysis , 2010, 2010 IEEE International Conference on Image Processing.

[12]  山田类 Image processing method, image processing apparatus, and computer program used therewith , 2005 .

[13]  Kang Ryoung Park,et al.  Real-Time Facial and Eye Gaze Tracking System , 2005, IEICE Trans. Inf. Syst..

[14]  Kang Ryoung Park,et al.  Gaze tracking system at a distance for controlling IPTV , 2010, IEEE Transactions on Consumer Electronics.

[15]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[16]  Mingjing Li,et al.  Automated red-eye detection and correction in digital photographs , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[17]  치욱 미하이 Detecting redeye defects in digital images , 2008 .

[18]  Peter M. Corcoran,et al.  Automated in-camera detection of flash-eye defects , 2005, IEEE Transactions on Consumer Electronics.

[19]  Raimondo Schettini,et al.  A Review of Redeye Detection and Removal in Digital Images Through Patents , 2009 .

[20]  Giovanni Maria Farinella,et al.  Red-Eyes Removal through Cluster-Based Boosting on Gray Codes , 2010, EURASIP J. Image Video Process..

[21]  닉 자르만,et al.  Detection and correction of red-eye features in digital images , 2003 .

[22]  Raimondo Schettini,et al.  Automatic Redeye Removal for Smart Enhancement of Photos of Unknown Origin , 2005, VISUAL.

[23]  余横,et al.  Image processing method , 2011 .

[24]  Peter M. Corcoran,et al.  Statistical models of appearance for eye tracking and eye-blink detection and measurement , 2008, IEEE Transactions on Consumer Electronics.

[25]  Robert Ulichney,et al.  Automatic red-eye detection and correction , 2002, Proceedings. International Conference on Image Processing.

[26]  铜奔马 Digital Camera——数字照相机 , 1996 .