Patchwise scaling method for content-aware image resizing

  • Authors:

  • Yun Liang;Zhuo Su;Xiaonan Luo

  • Affiliations:

  • College of Informatics, South China Agricultural University, Guangzhou 510642, China and School of Information Science and Technology, Sun Yat-sen University, Guangzhou 510006, China and National ...;School of Information Science and Technology, Sun Yat-sen University, Guangzhou 510006, China and National Engineering Research Center of Digital Life, Guangzhou 510006, China;School of Information Science and Technology, Sun Yat-sen University, Guangzhou 510006, China and National Engineering Research Center of Digital Life, Guangzhou 510006, China

  • Venue:
  • Signal Processing
  • Year:
  • 2012

Quantified Score

Hi-index 0.08

Visualization

Abstract

Image resizing becomes more and more important in content-aware image displaying. This paper proposes a patchwise scaling method to resize an image to emphasize the important areas and preserve the globally visual effect (smoothness, coherence and integrity). This method for resizing image is based on optimizing the image distance presented in this paper. The image distance is defined based on so-called local bidirectional similarity measurement and smoothness measurement to quantify the quality of resizing outputs. The original image is divided into small important patches and unimportant patches based on an important map. The important map is generated automatically using a novel combination of image edge and saliency measurement. A scaling factor is computed for each small patch. The resized image is produced by iteratively optimizing, which is based on our image distance, the scaling factor for each small patch. Experiments of different type images demonstrate that our method can be effectively used in image processing applications to locally shrink and enlarge important areas while preserving image quality.