Computer scientists have designed a new algorithm that incorporates artificial neural networks to simultaneously apply a wide range of fixes to corrupted digital images. The researchers tested their algorithm by taking high-quality, uncorrupted images, purposely introducing severe degradations, then using the algorithm to repair the damage. In many cases, the algorithm outperformed competitors’ techniques, very nearly returning the images to their original state.
From phone camera snapshots to lifesaving medical scans, digital images play an important role in the way humans communicate information. But digital images are subject to a range of imperfections such as blurriness, grainy noise, missing pixels and color corruption. The research team, which included members from the University of Bern in Switzerland, tested their algorithm by taking high-quality, uncorrupted images, purposely introducing severe degradations, then using the algorithm to repair the damage. In many cases, the algorithm outperformed competitors’ techniques, very nearly returning the images to their original state.
Zwicker and his colleagues can “train” their algorithm by exposing it to a large database of high-quality, uncorrupted images widely used for research with artificial neural networks. Because the algorithm can take in a large amount of data and extrapolate the complex parameters that define images — including variations in texture, color, light, shadows and edges — it is able to predict what an ideal, uncorrupted image should look like. Then, it can recognize and fix deviations from these ideal parameters in a new image.
Source (University of Maryland. “New algorithm repairs corrupted digital images in one step: Technique uses the power of artificial neural networks to address several types of flaws and degradations in a single image at once.” ScienceDaily. ScienceDaily, 5 December 2017.)
Original paper: He, L., Li, G. and Liu, J., 2015. Joint motion deblurring and superresolution from single blurry image. Mathematical Problems in Engineering, 2015.
