Experts has a new look! Let us know what you think of the updates.

Provide feedback
Home
Scholarly Works
Learning-Based Restoration of Backlit Images
Journal article

Learning-Based Restoration of Backlit Images

Abstract

Backlighting is a commonly encountered ill illumination condition that can cause serious degradation of image quality. In this paper, we propose a learning-based spatially adaptive technique of optimal tone mapping to restore backlit images. Object surfaces illuminated from behind in a scene are detected by a soft binary classifier that is constructed via supervised learning. Two optimal tone mapping functions, one for backlit regions and the …

Authors

Li Z; Wu X

Journal

IEEE Transactions on Image Processing, Vol. 27, No. 2, pp. 976–986

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Publication Date

February 2018

DOI

10.1109/tip.2017.2771142

ISSN

1057-7149