Noise-reduced Example-Based Image/Video Enlarging

To enlarge an image, bi-linear interpolation and bi-cubic interpolation are two common and simple methods, but they always generate unacceptable zigzag or blurry results. Some image processing methods are provided to reduce the zigzag or blurry effects by enhancing the edges and textureness or deblurring the images, and some example-based methods used some training high resolution images to provide the missing high frequency part for the enlarged input low resolution image. Although it is possible to record the relationship between the high resolution and low resolution samples of some natural training images and transfer the relationship to enhance the enlarged input low resolution image by using the example-based methods, the noise embedded in the input image is also amplified and makes the enhanced enlarged image looks noisy. Due to the noise, the example-based methods cannot be used to produce a satisfying result when applying to video frames directly. In this paper, we present an improved example-based approach that records the relationship of the middle and high frequency data of some training images, since the low frequency data is not needed for reconstructing the high frequency one. When enlarging an image, we only use the middle frequency data to estimate the missing high frequency one and transfer it to enhance the textureness of the enlarged input image. Since our approach can reduce the noise while enhancing the enlarged image, it can also be used for enlarging the video frames directly.