Automatic correction of amateur photos damaged by backlighting
Ilia V. Safonov · 2006
In this paper we consider a problem of enhancement of amateur photos damaged by backlighting for printing. The purpose of correction is to make photos more pleasant for an observer. Photos with exposure problems and with poorly distinguishable details in dark areas are main subject of our research. Our approach is based on contrast stretching and alpha-blending of both brightness of the initial image and estimations of reflectance. For obtaining reflectance estimation a simplified illumination model is used. The luminance is estimated using bilateral filter. Reflectance is estimated using heuristic functions of ratio between brightness of the initial image and estimation of luminance. The correction parameters are chosen adaptively based on histogram analysis. Noise suppression and some sharpening occur during correction. Also the time and memory optimization issues are considered. Recursive separable bilateral filter is applied to speed up the algorithm. The quality of the algorithm is evaluated by surveying of observer’s opinions and by comparisons with already existing software and hardware solutions for local shadow correction.