• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
成果搜索

author:

Lan, Chengdong (Lan, Chengdong.) [1] (Scholars:兰诚栋) | Yang, Xiuzhi (Yang, Xiuzhi.) [2] (Scholars:杨秀芝) | Chen, Jian (Chen, Jian.) [3] (Scholars:陈建)

Indexed by:

EI Scopus PKU CSCD

Abstract:

To improve the consistency of the objective quality and the human eye perception of stereoscopic images, and enhance the visual experience of the stereoscopic content, we take into account the problem of differences existing in the attention of the different regions of stereoscopic images and stereoscopic sense of different depth values for the human eye, and propose a stereoscopic quality evaluation method based on visual perceptual characteristics. Firstly, it introduces a visual saliency model to select region of interest, and then generates a depth map for the region. Secondly, the perceptible range and the sensitivity factor of depth map pixels are determined in terms of the just noticeable difference in depth model. Finally, the stereoscopic objective quality scores are obtained by computing relative depth hierarchy. Experimental results show that the correlation coefficient between the proposed method and subjective quality is higher than 0.9, and the mean square error is less than 5.4. There is good consistency between the two, and the results are better than the state-of-the-art methods.

Keyword:

Image enhancement Image quality Image segmentation Mean square error Quality control Stereo image processing Vision

Community:

  • [ 1 ] [Lan, Chengdong]College of Physics and Information Engineering, Fuzhou University, Fuzhou; 350108, China
  • [ 2 ] [Yang, Xiuzhi]College of Physics and Information Engineering, Fuzhou University, Fuzhou; 350108, China
  • [ 3 ] [Chen, Jian]College of Physics and Information Engineering, Fuzhou University, Fuzhou; 350108, China

Reprint 's Address:

  • 兰诚栋

    [lan, chengdong]college of physics and information engineering, fuzhou university, fuzhou; 350108, china

Email:

Show more details

Version:

Related Keywords:

Related Article:

Source :

Journal of Computer-Aided Design and Computer Graphics

ISSN: 1003-9775

CN: 11-2925/TP

Year: 2014

Issue: 8

Volume: 26

Page: 1333-1338

Cited Count:

WoS CC Cited Count:

SCOPUS Cited Count:

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 2

Online/Total:362/9707629
Address:FZU Library(No.2 Xuyuan Road, Fuzhou, Fujian, PRC Post Code:350116) Contact Us:0591-22865326
Copyright:FZU Library Technical Support:Beijing Aegean Software Co., Ltd. 闽ICP备05005463号-1