Dictionary learning for dark image enhancement

This paper proposes dark image enhancement algorithm based on dictionary learning(DL). When image is dark, many vision based robotic applications cannot work well. Existing dark image enhancement algorithms have defects. For example, histogram modification results in color information losses and gam...

Full description

Saved in:
Bibliographic Details
Main Authors: Jaesik Yoon, Yuna Seo, Jungyu Kang, Yoo, Chang D.
Format: Conference Proceeding
Language:English
Subjects:
Dark Image Enhancement
Dictionaries
Dictionary Learning
Dual Dictionary
Histogram Modification
Sparse Coding
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes dark image enhancement algorithm based on dictionary learning(DL). When image is dark, many vision based robotic applications cannot work well. Existing dark image enhancement algorithms have defects. For example, histogram modification results in color information losses and gamma correction makes degradation in dark area. Proposed algorithm preserves color information and provides high performances in extreme conditions. Experimental results compared with existing algorithms will be also presented.
DOI:10.1109/URAI.2012.6462941