Open Competition 1 - Information Technology

An Advanced Disruptive, Intelligent-Based Image Compression Technology

Sponsor: UtopiaCompression Corporation

• Project Performance Period: 2/1/2003 - 8/8/2006
• Total project (est.): $3,231,234.00
• Requested ATP funds: $2,000,000.00

Driven by advances in communication technology, explosive growth in Internet communication continues to strain networks. As demand for limited bandwidth escalates, networks suffer from delays, bottlenecks, and even paralysis in transmission and storage. Because imagery is more than 60 percent of the information transmitted (the rest is voice and text) and is predicted to increase in the years ahead, a powerful software solution that efficiently compresses imagery is crucial and more cost effective than expensive upgrades in network infrastructure. UtopiaCompression will develop an advanced intelligence-based image compression technology modeled after natural cognition, which comprehends an image as a unified and interrelated entity, instead of unrelated blocks of data. Compared to data-driven compression approaches, which break images into small units, thereby losing spatial relations and, thus, lowering the compression ratio, the UtopiaCompression paradigm simulates the cognitive process by compressing intricate networks of visual patterns. An adaptive filtering scheme partitions an image into complex but predictable structures, and unpredictable "noise-like" structures. Advanced algorithms using artificial intelligence techniques -- such as numeric decision trees, neural networks, genetic programming, and fuzzy classifiers -- efficiently capture high-quality images at superior compression ratios. This capability is achieved by training the system to recognize a repertoire of patterns common to images. UtopiaCompression's technology holds out the promise of compression ratios four times better than the competing data-driven approaches, such as those used in JPEG-2000 and MPEG-4. This will significantly reduce storage and transmission costs and dramatically increase transmission speed, as well as enhance image reconstruction quality. Although intrigued by the new compression concept, venture capital firms find the project at an early stage and disruptive in relation to existing standards-based compression and, therefore, are reluctant to fund. ATP funding is necessary to bring this infrastructural technology to market in a timely fashion. By making image transmission and storage much more efficient, this quantum-leap technology will rejuvenate the nation's telecommunication networks, on which billions of dollars already have been invested. The economy will be broadly stimulated by savings and revenues generated from applications in wireless communication, video conferencing, e-learning, telemedicine and digital photography, and media and entertainment including digital cinema and video-on-demand. In addition, an early application is expected to arise in surveillance and security for the transmission of larger numbers of higher quality data streams over existing communication channels.

For project information:

Dr. Jacob Yadegar, (310) 473-1500
jacob@utopiacompression.com

ATP Project Manager

Barbara Cuthill, (301) 975-3273
barbara.cuthill@nist.gov