From phone camera snapshots to life-saving 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.
A new algorithm incorporates artificial neural networks to simultaneously apply a wide range of fixes to corrupted digital images. Because the algorithm can be “trained” to recognize what an ideal, uncorrupted image should look like, it is able to address multiple flaws in a single image. The algorithm was tested by taking high-quality, uncorrupted images; purposely introducing severe degradations; and then using the algorithm to repair the damage. In many cases, the algorithm very nearly returned the images to their original state.
Traditional tools address each problem with an image separately. Each of these uses intuitive assumptions of what a good image looks like, but these assumptions have to be hand-coded into the algorithms. Artificial neural networks have been applied to address problems one by one; the new algorithm goes a step further to address a wide variety of problems at the same time.
Artificial neural networks are a type of artificial intelligence algorithm inspired by the structure of the human brain. They can assemble patterns of behavior based on input data in a process that resembles the way a human brain learns new information; for example, human brains can learn a new language through repeated exposure to words and sentences in specific contexts.
The new algorithm can be “trained” 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.
When other algorithms are tasked with only removing noise (or graininess) from an image, they would automatically address many of the other imperfections as well. But with a noisy image, it is randomly shifted or jittered away from a high-quality image in all possible dimensions. Other degradations, such as blurring, diverge from the ideal only in a subset of dimensions.
While the new algorithm is powerful, it works well for fixing easily recognizable “low-level” structures in images, such as sharp edges. Researchers hope to push the algorithm to recognize and repair “high-level” features, including complex textures such as hair and water.