Yasunori Taguchi

Super-resolution with depth-adapted gain control for depth-feel enhancement of landscape image

A super-resolution method that enhances the depth-feel of images is proposed. Our method controls the gain of the super-resolution effect by using a depth map. The proposed method is effective for landscape images containing far objects and large difference of distance. The proposed method creates an image from which viewers derive a feeling of high realism by clearly perceiving the difference of distances of near and far objects.

Image denoising via nonlocal means with noise-robust similarity

We propose an effective image denoising method by revising the conventional “nonlocal means (NL-means)” method. Conventional NL-means replaces a noisy pixel by the weighted average of other reference pixels depending on the similarity between local neighborhoods of target pixel and reference pixels. Noise, however, reduces the similarity even within the same pattern blocks. This is due to the weighted average of dissimilar blocks of pixels, which makes the result image blurred or irregular. Hence, our proposal is to calculate the similarity with the combination of basis patterns correlated statistically with little noise through principal component analysis making use of local structures that have low correlation with incurred noise. The first step is to exclude the local structures of the given image whose statistical correlation with the original images is slight. The second step is to exclude basis patterns whose correlation with the target blocks is slight. Making use of the selected basis patterns, we can calculate the similarity robust to any noise. Consequently, high-quality images can be obtained. Comparing with other methods, our experiments show our method denoises effectively without causing any blur or irregularity.

An image interpolation method by projection satisfying reconstruction constraint

An image interpolation method is proposed. An input image can be considered to be a deteriorated one from an unknown original image with more pixels than it. The image interpolation can be treated as an underdetermined problem to reconstruct the original image from the input image. In the proposed method, an output image by an arbitrary method is moved closer to the original image by a projection satisfying a reconstruction constraint that the output image should coincide with the input image by an assumed deterioration. Experimental results showed the effectiveness of the proposed method.