Scotopic Visual Image Mining Based On NR-IQAF

摘要：

In this paper, a new image mining method is proposed considering the contrast resolution limitation of human vision under scotopic visual environment. First, a valid gray distribution of an image is taken from scotopic vision condition. Second, the gray values of a target image pixels are computed from the original image via Zadeh-X transformation. Third, a no reference image quality assessment function (NRIQAF) is used to estimate the image after transformation. Experiments demonstrate that this method greatly improves the visual contrast and luminance of the image, so image quality and visual effects have been improved significantly after mining; in addition, the optimal quality image can be obtained by the NR-IQAF.

关键词： Scotopic vision image mining Zadeh-X transformation averaging contrast no reference image quality assessment

作者: Fengbo Tian Zhengxiang Xie Xiafu Lv Jiaji Cheng

作者单位: Chongqing University of Posts and telecommunications, Chongqing 400065, China Chongqing Medical University, Chongqing 400016, China

会议类型: 国际会议

会议名称: 2010 International Conference on Bio-inspried System and Signal Processing(2010 IEEE生物系统与信号处理国际会议 ICBSSP 2010)

会议地点: 厦门

会议语种:英文

页码: 35-38

在线出版日期: 2010-10-26（万方平台首次上网日期，不代表论文的发表时间）