Image Enlargement Using Repetitive Component Multiplication

Efficient and effective image enlargement without distortion attracts numerous interests these days. This paper presents an image enlargement system for images with repetitive components. Based on repetitive components and seam filling, our system achieves distortion-free visual effect. Our system c...

Full description

Saved in:
Bibliographic Details
Published in2014 International Conference on Virtual Reality and Visualization pp. 333 - 338
Main Authors Zhengzhe Liu, Xiaojuan Qi, Bin Sheng, Wen Wu, Ping Li, Lizhuang Ma
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.08.2014
Subjects
Feature extraction
Image color analysis
Image resolution
Image segmentation
Lattices
Merging
Shape
Online AccessGet full text

Cover

More Information
Summary:Efficient and effective image enlargement without distortion attracts numerous interests these days. This paper presents an image enlargement system for images with repetitive components. Based on repetitive components and seam filling, our system achieves distortion-free visual effect. Our system captures and extracts the repetitive components by MSERs. After which, we got the repetitive component (RC) regions and non-repetitive component (NRC) regions. In order to deal with the different characteristics of these two regions, we intuitively incorporated two different algorithms: patch-based texture synthesis for RC regions and in painting for NRC regions. To achieve seamlessness filling, we lastly smooth the boundary between the filled regions and its surroundings by multi-resolution. Our system shows great success in enlarging image with repetitive components.
DOI:10.1109/ICVRV.2014.9