DocumentCode :
598229
Title :
Anti-ghost of differently exposed images with moving objects
Author :
Zhengguo Li ; Shiqian Wu ; Zijian Zhu ; Shoulie Xie ; Rahardja, Susanto
Author_Institution :
Signal Process. Dept., Inst. for Infocomm Res., Singapore, Singapore
fYear :
2012
fDate :
Sept. 30 2012-Oct. 3 2012
Firstpage :
2745
Lastpage :
2748
Abstract :
In a typical image synthesis where multiple differently exposed images are captured for processing, it is important to design an anti-ghost algorithm so as to prevent ghosting artifacts from appearing in the final image. An anti-ghost algorithm is usually composed of a detection module and a correction module. In this paper, a new detection module is proposed to detect non-consistent pixels of all input images without predefining any initial reference image. The proposed module is suitable when an interactive mode is desired. In addition, a bidirectional approach is introduced to correct the non-consistent pixels in the correction module. Compared with existing unidirectional correction methods, the proposed bidirectional correction approach uses information from two adjacent images of a detected image to correct its non-consistent pixels. This leads to a quality improvement in the final image.
Keywords :
natural scenes; object detection; antighost algorithm; bidirectional approach; bidirectional correction approach; correction module; detection module; differently exposed images; ghosting artifacts; image detection; image synthesis; images processing; initial reference image; interactive mode; moving objects; nonconsistent pixels; unidirectional correction methods; Dynamic range; Heuristic algorithms; Image reconstruction; Imaging; Indexes; Signal processing algorithms; Software algorithms;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2012 19th IEEE International Conference on
Conference_Location :
Orlando, FL
ISSN :
1522-4880
Print_ISBN :
978-1-4673-2534-9
Electronic_ISBN :
1522-4880
Type :
conf
DOI :
10.1109/ICIP.2012.6467467
Filename :
6467467
Link To Document :
بازگشت