Image interpolation by high dimensional projection based on subspace method
Image interpolation by high dimensional projection based on subspace method
复制标题
基于子空间法的高维投影图像插值
DOI：
10.1109/icpr.2004.1333860
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
Toshiyuki Amano
中科院分区：
文献类型：
--
作者：
Toshiyuki Amano
这项工作提出了一种新的图像插值技术，用于解决图像破裂（例如字幕字符遮挡或图像恶化）的问题。风景图片、纹理图案或其他自然场景都含有自相关图案的行为，建立了一种基于自相关图案的图像插值方法。该方法从一幅图像中提取许多局部区域，并由图像向量生成子空间。子空间通过图像向量空间中的超平面限制来限制局部区域的图像描述的自由度。本文解释了一种基于特征空间的图像插值方法，并解释了使用核非线性投影的扩展。
This work presents a new image interpolation technique for image cracking such as telop character occlusion or picture deterioration. The landscape picture and texture pattern or other natural scenes contain the behavior of the autocorrelation pattern, and a method of image interpolation based on the autocorrelation pattern has been established. This method extracts many local regions from a piece of image and generates a subspace by the image vectors. The subspace limits the freedom of the image description at the local region by the hyperplane restriction in the image vector space. This paper explains for an image interpolation method based on eigen-space and explains the expansion using kernel non-linear projection.