Analyzing video is a powerful idea. But it contains naturally much more data. Penn State provides some new ideas.
New Algorithm May Help People Store More Pictures, Share Videos Faster
in Penn State News
By Matt Swayne
Researchers at Pennsylvania State University (Penn State) have developed an algorithm based on the human brain that could ease data bottlenecks that threaten the growth of the Internet by reducing the size of multimedia files and restoring them without losing much quality or information. The tool, which the researchers call an iterative refinement algorithm, features a recurrent neural network that compresses and restores the data. It is able to produce restored images that had better quality than the benchmarks selected for the study. Said Penn State’s David Miller, "The key advantage of recurrence in this image decoding context is that it exploits correlations over long spatial regions of the image than a conventional image decoder." .... '
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment