IBM claims to have found a method to increase or decrease the size of digital images better than it is possible today with traditional techniques such as nearest neighbor, bilinear or bicubic resizing.
Even the most sophisticated image editing software does not provide perfect solutions to increase or decrease digital image sizes. Making images smaller results in loss of detail as pixels are eliminated; and an increase, which requires the addition of detail, relies on predictive methods that are rather crude today. With the nearest neighbor interpolation, the software simply adds pixels of the same color, which preserves detail, but impacts smooth shapes.
Bicubic resizing delivers much smoother lines, but quickly drifts into blurring and ugly artifacts. Much more elaborate methods, such as fractal analysis, require enormous computing resources that are generally not practical in consumer applications. In order to address these and other problems, the present invention provides a method and system for resizing a digital image.
According to IBM, there is another image analysis method that can deliver better results than current resizing techniques. The idea is to stretch or shrinks the image along the horizontal and vertical dimensions using two separately calculated scaling vectors, resulting in a scaling matrix.
IBM says that the technique delivers greater accuracy and quality than current methods as missing pixels are not just created from their neighboring pixels or interpolated, but predicted using spatial and frequency transformation of complete rows and complete columns that does not create jaggedness, artifacts or any other aliasing.
The patent did not mention any products this technology will be used in, but hopefully it won't be long before we see it.