Image Magnification Based on the Properties of Human Visual Processing
ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks, Part III
Color Image Magnification: Geometrical Pattern Classification Approach
IVIC '09 Proceedings of the 1st International Visual Informatics Conference on Visual Informatics: Bridging Research and Practice
Hi-index | 0.00 |
The rapid growth in computer graphics and digital cameras has resulted in computer users being able to easily produce digital images. As a result, the need to display and print digital images has increased. Nowadays, high-resolution display and printing devices are available to users. Therefore, high-resolution images are needed in order to produce high quality displayed images and high quality prints. However, since high-resolution images are not usually provided, there is a need to magnify the original images. Previous methods on magnifying images have the disadvantage that either the sharpness of the edges cannot be preserved or that some distinct artifacts are produced in the magnified image. In this paper, we present a novel method for doubling the size of images in which the sharpness of the edges is preserved without introducing distinct artifacts in the magnified images. The proposed method consists of two steps, first generation of an initial magnified image and then progressively refining this image to produce a high quality magnified image. The experimental results show that with the proposed method it is possible to produce magnified images of comparable, and in some cases superior, visual quality to those produced using previous methods.