Images
CMU algorithm matches sketches, paintings to photographs
10:42 December 7, 2011

Alexei Efros and his team of cunning robotics researchers at Carnegie Mellon University have developed an image matching algorithm with which computers can identify similar images regardless of medium. Like humans, the system can match sketches and paintings with photographs of similar subjects, and so perform tasks that have traditionally posed problems to machines, such as pairing a simple sketch of a car with a photograph of the same. Read More
Get some virtual culture with the Google Art Project
By Darren Quick
23:51 February 1, 2011

Google has announced a collaboration with 17 of the world’s most acclaimed art museums that lets people view over 1,000 high res artwork images and 17 "gigapixel" images while taking a virtual stroll through their galleries using “Street View” technology. While nothing can beat seeing a work of art in person, the Google Art Project could be the next best thing for those without the time and money to pop on a plane and trade elbows with crowds of tourists looking to catch a glimpse of what some of the best museums have on offer. Read More
New software processes hundred-billion-pixel photos in seconds
By Paul Ridden
17:59 October 31, 2010

Computer scientists from the University of Utah have developed computer software that allows editing of "extreme resolution" image files in a matter of seconds, a process that could previously have taken hours. Whereas existing editing suites require the full gigapixel image to be loaded into a computer's memory before manipulation can begin, the new development draws a lower resolution preview image from an externally-stored image into the editing screen. Users are said to benefit from being able to make image-wide modifications in seconds rather than hours and on devices normally not nearly powerful enough for such things. Read More
System automatically classifies images and video based on elements they contain
By Darren Quick
19:15 October 13, 2010

Currently, computer search and classification of images is based on the name of the file or folder or on features such as size and date. That’s fine if the name of the file reflects its content but isn’t much good when the file is given an abstract name that only holds meaning to the person providing it. This drawback means companies in the search business, such as Google and Microsoft, are extremely interested in giving computers the ability to automatically interpret the visual contents and video. A technique developed by the University of Granada does just that, allowing pictures to be classified automatically based on whether individuals or specific objects are present in the images. Read More
“Seeing” NeuFlow supercomputer based on the human visual system
By Darren Quick
23:30 September 15, 2010

The brain’s ability to quickly visually interpret our environment requires such an enormous number of computations it is pretty amazing that it accomplishes this feat so quickly and with seemingly little effort. Coming up with a computer-driven system that can mimic the human brain in visually recognizing objects, however, has proven difficult, but now Euginio Culurciello of Yale’s School of Engineering & Applied Sciences has developed a supercomputer based on the human visual system that operates more quickly and efficiently than ever before. Read More

There are many factors other than the megapixel count that affect the quality of images a digital camera will produce – sensor size, lens quality, organization of the pixels, etc. However, consumers often use the number of pixels each dollar buys as a basic measure of value for a digital camera and there has been a steady increase in the “pixels per dollar” for new cameras that roughly follows Moore’s Law. Depending on its cost and when it will hit the market, a new APS-H-size CMOS image sensor developed by Canon could put a bit of a dent in that line with its image resolution of approximately 120-megapixels. Read More
Online predators can determine where posted photos and videos were shot
By Ben Coxworth
17:02 July 25, 2010
Before you proudly go posting photos of your Ming vase online, you should be aware that computer-savvy burglars can likely use that photo to find out where you live. The same goes for photos or videos of your kids, yourself, or anything else that you don’t want strangers knowing how to locate. The practice of tracking people via their posted images is an example of “cybercasing”, and is possible because many digital cameras and smart phones, including the iPhone, automatically geotag their images by embedding the longitude and latitude at which they were taken. Even when uploaded to a website, the images still retain this information. By plugging the coordinates into a service like Google Street View, getting an address or an identifying landmark is entirely possible. Read More
Adobe Lightroom 3: New features introduced since the public beta
23:03 June 7, 2010

If you’re a fan of Adobe’s indispensable digital darkroom software, Lightroom then chances are you might have already had a nose around some of its new features and improvements in the beta. Although most of the major updates were introduced during this public pre-release we’re pleased to say a few more features have come to light in the final version announced today. Read More

We’ve all seen cards with images that move or provide a 3D effect without glasses when the viewing angle is moved. Although the technology has been around since the 1940s, its limitations in viewing distance and clarity has seen it largely remain a novelty for prizes in cereal boxes, collectible cards and the occasional movie poster. Now researchers have updated the technology for the 21st Century, enabling a much clearer 3D image on posters up to five meters in size which can also be viewed from a distance. Read More

All lenses have their little quirks, but anyone importing and processing huge stacks of shots at any one time will know what a pain it is to manually correct these nagging traits. Available now as a pre-release Adobe's Lens Profile Creator gives photographers the power to bulk correct lens distortions in images captured by a particular lens. Read More
Explore Gizmag