Earticle

초록

영어

Image cropping is a technique to help people improve their taken photos’ quality by discarding unnecessary parts of a photo. A novel method is presented for Image cropping by patches dissimilarities. In this paper, we propose a novel patches dissimilarities algorithm. Firstly, representing the image patches and reducing dimensionality. Then we extract the visual saliency map of these photos based on the patches dissimilarities. Finally, by the saliency map and face priors, we find a cropped region that can be best found. The experimental results demonstrate that our technique is applicable to a wide range of photos and produce more agreeable resulting photos.

목차

Abstract
 1. Introduction
 2. Related Works
  2.1. Image Cropping
  2.2. Saliency Detection
 3. Image cropping via patches dissimilarity
  3.1. Representing the Image Patches
  3.2. Reducing Dimensionality
  3.3. Patches Dissimilarity
  3.4. Image Cropping
 4. Experimental Results
  4.1. Image Cropping Results
  4.2. User Studies
  4.3. Comparison with Related Work
 5. Conclusions
 References
 Acknowledgements

키워드

저자

• Shangbing Gao [ Faculty of Computer Engineering, Huaiyin Institute of Technology, Huai’an, China, The Key Laboratory for traffic and transportation security of Jiangsu Province, Huai’an, China ]
• Youdong Zhang [ Faculty of Computer Engineering, Huaiyin Institute of Technology, Huai’an, China ]
• Wanli Feng [ Faculty of Computer Engineering, Huaiyin Institute of Technology, Huai’an, China ]
• Dashan Chen [ The Key Laboratory for traffic and transportation security of Jiangsu Province, Huai’an, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Signal Processing, Image Processing and Pattern Recognition

• 간기

  격월간

• pISSN

  2005-4254

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605