Structure-Preserving Image Retargeting With Compression Assessment and Adaptive Registration
R.Nishanthi1, Pon L.T.Thai2, K.John Peter3

1R.Nishanthi, Computer Science, Vins Christian College of Engineering, Anna University,Nagercoil, India,
2Pon L.T.Thai, Computer Science, Vins Christian College of Engineering, Anna University,Nagercoil, India,
3K.John Peter, Information Technology, Vins Christian College of Engineering, Anna University, Nagercoil, India.

Manuscript received on July 01, 2012. | Revised Manuscript received on July 04, 2012. | Manuscript published on July 05, 2012. | PP: 333-338 | Volume-2, Issue-3, July 2012. | Retrieval Number: C0754062312 /2012©BEIESP
Open Access | Ethics and Policies | Cite 
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: A number of algorithms have been proposed for image retargeting with image content retained as much as possible. But, they usually suffer from some artifacts in the results, such as ridge or structure twists. In this paper, a structure and content preserving image retargeting technique is used that preserves the content and image structure as best as possible. The image content saliency is estimated from the structure of the content using saliency map. A block structure energy is used for structure preservation along x and y directions. Block structure energy uses top-down strategy to constrain the image structure uniformly. However, the flexibilities of retargeting are different for different images. To overcome this problem, compression assessment scheme is used by combining the entropies of image gradient magnitude and orientation distributions. Finally, adaptive registration algorithm is applied. Adaptive registration is used to increase the PSNR ratio. Thus, the resized image is produced to preserve the structure and image content as best as possible. The global image structure is preserved and structure distortions are avoided.

Keywords: Compressibility estimation, image retargeting, structure-preserving.