The main novel contributions of this paper are as follow: 1. Difference merged image algorithm based on CNN is presented.
本文的主要研究贡献有:1。提出基于CNN差分图象合并的视频分割算法。
With the aid of fuzzy membership degree of image, characteristic degree of short crack included in a pixel was proposed, and fuzzy analysis was carried out based on merged images.
借助图像模糊隶属度,对合并图像中像素点具有短裂纹特征的程度进行模糊分析。
Aim at video sequences with static background, the difference merged image algorithm based on CNN is presented. In order to realize the algorithm, five CNN templates are constructed.
针对背景相对静止的视频序列,提出了基于CNN差分图象合并的视频分割算法,并构建了与该算法相关的五个CNN模板。
应用推荐