公制(单位)
GSM演进的增强数据速率
图像(数学)
计算机视觉
计算机科学
人工智能
数学
经济
运营管理
出处
期刊:The Journal of Information and Computational Science
[Binary Information Press]
日期:2014-07-01
卷期号:11 (10): 3411-3422
被引量:1
标识
DOI:10.12733/jics20104006
摘要
Aiming at the inaccurate locating problem of the boundary while retrieving edge width by the edge extension and inaccurate blur measure problem of a blurred image due to the dependence on the gradient direction, this paper presents a novel blur measure method, which applies the edge width obtained by a multi-scale filtering to model the blurriness of Gaussian-blurred image. The proposed method first construct the gradient line of Gaussian-blurred image according to its gradient magnitude edge and models the relationship between the edge and the gradient line, and then using LOG (Laplace of Gaussian)filter detects the edge to determine the edge width. The experimental results show that the average width determined by the proposed method can measure the blurriness of Gaussian-blurred images and the blur measure based on the edge width is stable for images with different content.
科研通智能强力驱动
Strongly Powered by AbleSci AI