Convolutional neural networks have been widely applied in many low level vision tasks. In
this paper, we propose a video super-resolution (SR) method named enhanced video SR …

摘要超分辨率重建技术可以提高图像质量, 使原图像具有更丰富的细节信息.
针对现有的超分辨率重建算法存在提取特征单一, 不利于对图像信息进一步提取的问题 …

By introducing a crater-shaped window (CSW) instead of the traditional square-shaped
window (SSW), an edge detector with low false positive rate is proposed to rapidly extract …

图像插值是数字图像处理领域中的一个基本问题, 利用插值技术可以实现图像的缩放和图像恢复
. 传统的插值方法易使边缘产生锯齿效应或使插值结果模糊不清. 该文提出一种基于角点保护的 …

In this letter, an antistretch edge detector has been proposed for synthetic aperture radar
(SAR) images. Traditional detectors using anisotropy edge detection filters often incur …

核磁共振高分辨率的图像可以提供更加丰富的病理信息, 起到辅助诊断的作用,
超分辨重建是利用低分辨率图像通过算法重建出高分辨率图像的技术. 本文研究了针对核磁共振 …

The system thermal drift is an uncertain factor in the scanning of the AFM image. Thermal
drift is difficult to be detected by using traditional sensor. Therefore, digital image method is …

Image interpolation is a basic issue in digital image processing, which can be used to
realize image magnification and restoration, etc.. Traditional interpolation methods are easy …

In order to solve the problems of single image super-resolution algorithm based on
convolutional neural network, such as shallow network structure, single feature extraction …