Automatic Image Scaling is a feature that allows pixel-
mapped images to be enlarged or reduced to optimize their
size to the page. When combined with the printer’s auto-
matic image rotation feature, scaling allows images to be
printed as large as possible on the paper. You may print an
image either scaled or unscaled by selecting the appropriate
Logical Device, as you wish. Image scaling is also config-
urable, allowing you to choose between several advanced
algorithms, based on individual detail, clarity, and speed
requirements
www.codonics.com
"Neural Network Image Scaling Using Spatial Errors"
We propose a general method for gradient-based training of neural
network (NN) models to scale multi -dimensional signal data. In the
case of image data, the goal is to fit models that produce images of
high perceptual quality, as opposed to simply a high peak signal to
noise ratio (PSNR).
www.hpl.hp.com
"Interpolation algorithms for image scaling"
Nowadays, the tendency for image visualization is devises, which have determined
resolution, to be used more and more. Image resampling is essential for the purpose of correct image visualization. In this paper, parallel between different resampling algorithms is made, and as basis for this comparison are used three methods: Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR) and Subjective Evaluation (SE). In the present paper are given qualitative and quantitative results from the execution of the above algorithms upon special, designed for the purpose, vector graphics and selected photographs. The method offered is a useful tool for doing simple tests.
www.tu-sofia.bg
