software

According to Fishbowl NY, the fashion magazine Marie Claire has contracted Pongr to provide image recognition technology for interactivity with the print edition. Users can take a picture of a magazine page with their phone and email the image to a website. When the image is recognized, additional content relating to the magazine picture is sent to the user. Pongr's technology was selected because it does not require running an app on the phone.

Researchers at the National Cheng Kung University in Taiwan have developed a tool to fuse images within other images. Using patterns of light and dark regions, an image is overlaid onto the background so that textures show through. The tool can be used generate CAPTCHA images for online authentication. More information and a video are available in a NewScientist web article

Researchers at University of Wisconsin at Madison (UWM), led by David J. Gagnon, are developing an open source tool that lets designers link text, images, video, and audio into a physical location. The tool, named ARIS (Augmented Reality and Interactive Storytelling), maps the real world to virtual objects that users can navigate with smartphones. More details is available in a press release.

Dr. Gary Bradski of Willow Garage disclosed at CVPR2010 that there are now five full time staff at Willow Garage working exclusively on OpenCV. Dr. Bradski also presented the status of the OpenCV software project at the Embedded Computer Vision Workshop and at the Open Source Vision Software tutorial. Dr. Radu Rusu and Dr. Vadim Pisarevsky, also from Willow Garage, presented the 3D Point Clouds Library and a hands-on tutorial.

Researchers at the University of Utah, Jens Krueger and Tom Fogal, have developed ImageVis3D, a software program that converts complex data sets into 3D images that can be viewed with an iPhone or iPad. According to Fogal, "the program enables users to manipulate a wide range of 3D images of medical, scientific, and engineering data". More information is available in a press release and a news story on KSL channel 5.

Submitted by Sek Chai

Researchers at Fraunhofer Institute for Digital Media Technology (IDMT) have developed a multimedia search engine that uses digital fingerprints to locate video and audio files. The fingerprints for video files are stored in MPEG-7 format and include information on scene change, camera movement, and image brightness. More information is available in a press release.

Submitted by Boaz Super

NASA Ames Intelligent Systems Division develops and maintains an open source C++ computer vision software library called Vision Workbench. Vision Workbench is not a full-featured computer vision library: it is focused on image stitching, multi-band blending, and 3D reconstruction from multiple images. According to NASA, in 2010 "Vision Workbench will be used as a test case for incorporating third-party (non-NASA) source code contributions." See the Vision Workbench download site for more information.

Submitted by Boaz Super

U.K. company Imsense Ltd. announced the release of an improved version of its photo enhancement software imphoto. In addition to improved image quality, the software now has export options specific to the iPad's display size, and to standard Facebook and Twitter image sizes.

Submitted by Boaz Super

Ramaprasanna Chellamuthu, an Indian developer, is showing off his hobbyist project on the sidelines of Microsoft's Tech Ed conference. His Buddy Home uses multiple computer vision and robotics capabilities to, for example, stir the food cooking on the stove, let him know if he is eating something unhealthy, pour cold water over his head if he sleeps through his alarm, recognize the magazine page he is reading and project related web sites on his wall, recognize gestures and facial expressions, recognize a credit card in his hand to make an online purchase, and detect intruders.

Buddy Home uses OpenCV, gesture recognition software, off-the-shelf robot parts, webcams, and a projection display.

OpenCV (The Open Source Computer Vision Library) has been accepted as a mentoring organization in Google's Summer of Code 2010 program. Potential topics of interest for student projects include, among others, augmented reality, photo stitching, motion analysis, GUI, parallelization, and implementing OpenCV on new platforms such as 64-bit OSX and Android. For more info, see Willow Garage's Summer of Code mentorship page for the OpenCV project.