文章基本信息

标题：OPTIMIZATION OF COMPUTATIONAL BURDEN OF THE POINT INFORMATION GAIN
本地全文：下载
作者：Jan Urban ; Renata Rychtáriková ; Petr Macháček 等
期刊名称：Acta Polytechnica
印刷版ISSN：1210-2709
电子版ISSN：1805-2363
出版年度：2019
卷号：59
期号：6
页码：593-600
DOI：10.14311/AP.2019.59.0593
语种：English
出版社：Czech Technical University in Prague
摘要：We developed a method of image preprocessing based on the information entropy, namely, on the information contribution made by each individual pixel to the whole image or to image’s part (i.e., a Point Information Gain; PIG). An idea of the PIG calculation is that an image background remains informatively poor, whereas objects carry relevant information. In one calculation, this method preserves details, highlights edges, and decreases random noise. This paper describes optimization and implementation of the PIG calculation on graphical processing units (GPU) to overcome a high computational burden.
关键词：Pixel information contribution; entropy; image analysis; computation optimization.