摘要
研究以离散余弦变换(DCT)基函数作为辅助函数,结合序列灰度图像构造动力系统,然后迭代得到轨迹点集合(近似的吸引子);使用该吸引子能够将视频图像的不同场景鉴别出来,用于视频分段裁剪等。使用多个DCT基函数矩阵,分别与一个图像构造动力系统,生成多个近似吸引子,这些吸引子可以作为图像的特征,用于图像识别,也可以重构原图像。
This paper used the discrete cosine transform( DCT) basis function as an auxiliary function together with the gray image of the sequence to construct the dynamic system,and then achieved the trajectory point set( approximate attractor) by iteration. This attractor can be used to distinguish the different scenes of the video image. It Used a number of DCT basis function to construct respectively with an image dynamic system to generate a number of approximate attractor. These attractors can be used as image features for image recognition,and can also be used to reconstruct the original image.
出处
《微型机与应用》
2016年第18期39-41,44,共4页
Microcomputer & Its Applications
基金
辽宁省自然科学基金(201602034)
关键词
图像数据
混沌吸引子
离散余弦变换基函数
image data
chaotic at tractor
discrete cosine transform basis function
