Adobe Systems in association with Massachusetts Institute of Technology and Stanford University have developed a new technology which cuts down bandwidth usage by 98% during mobile image processing. This new technique will also help in lowering the power consumption of mobile.
With smart phone usage increasing day by day, users are hoping to indulge in more innovation driven activities. For instance, though the gadgets are helping users to capture images in a smart way, the image processing activity still needs a lot of innovation.
In generalized terms, most image processing applications suffer from very intensive computing and often prove as heavy on battery power. The solutions proposed so far involved sending image files to a central server. But if the file is too large, or is taken from a high MP camera, the cost of data usage is always pretty high and delays incurred are quite significant.
The new method proposed by MIT-Stanford researchers’ works out a way where image style is altered such as deleting a certain figure or changing background with a new fill color.
To reduce the load on bandwidth usage, the system sends a low-quality JPEG file to the server and the real magic happens at the server side where the image is processed. The system introduces high frequency noise to the image so that its resolution becomes considerably higher; an effect that prevents the system from relying too much on the consistency of colors in particular section of the image. Next the system manipulates the image for better contrast, color spectrum shifting, sharpening edges etc. Once that’s done and dealt with, the image is broken down in smaller chunks using a certain machine learning algorithm to characterize using 25 basic parameters. When the image is finally sent back to the mobile device from the server, the system locally performs the modifications on the high-resolution copy of the image.
In their experiments, the researchers found that they could have time savings of about 50-70 percent and power savings of up to 50-85 percent. They are now working on optimizing their technique so that its suits every single mobile platform.
But still a lot of questions remain unanswered in this research and so will have to wait till a white paper in order to get to a conclusion.