YEDA Collaborates with Adobe for New Data Visualization Technique

YEDA Research and Development Company LTD., the commercial arm of the Weizmann Institute of Science, today announced it has entered into a license agreement with Adobe Systems Incorporated related to a bidirectional similarity measure to summarize visual data.

The bidirectional similarity method developed by Prof. Michal Irani and Drs. Denis Simakov, Yaron Caspi and Eli Shechtman of the Institute’s Computer Science and Applied Mathematics Department is a technique for summarizing visual data – both still images and video. Rather than cropping or scaling down an image to obtain a smaller thumbnail, or clipping a video segment, the method produces a complete and coherent visual summary: a smaller or shorter version of the original that retains the most relevant information. The bi-directionality of the method ensures that the resulting image is visually coherent: In addition to telling the same “story,” it is as visually pleasing as the original. As opposed to cropping or clipping, in which important information can be lost; or scaling down, in which resolution is lost, summarizing manages to maintain both relevant information and resolution details, despite the decrease in size.   

The method is based on eliminating redundant information from the image/video. Video summarization works in a similar way, only the program exploits redundancy in space-time. Gradual resizing and rechecking ensures that the final result is seamless and coherent.

In addition to summarizing images and videos, the method may have a number of other applications, including completing missing parts in images/videos; creating montages out of separate images; photo reshuffling (in which elements may be moved around the image/video); automatic cropping; image synthesis (in which an image might be expanded, rather than summarized); and image morphing (generating a video sequence displaying a smooth transition from one image to another, possibly unrelated, image).