University of Rochester

Western New York Universities Collaborate to License Technologies

October 24, 2003

Illegible prescriptions scrawled on physicians' notepads could become a thing of the past, thanks to two complementary technologies developed at the University at Rochester and the University at Buffalo that are together being licensed by MobileLexis, a digital media company based in Salt Lake City, Utah.

The company plans to use the two technologies, which were marketed together through a new effort to commercialize research conducted at upstate New York institutions, to develop a secure electronic prescription system using digital paper.

"Since we focus on the healthcare, financial, and government markets, we needed to have both a reliable and robust means of translating the handwritten information from paper to computer and a powerful and proprietary method of securing that information for Internet transfer," said Rod Sheets, president of MobileLexis. "AuthentImage and Accuscript resolve both of these issues quite nicely and more than satisfy our data requirements," he says.

AuthentImage, a trademarked University of Rochester technology, is a digital authentication package that ensures both the security and integrity of documents. Accuscript, the University of Buffalo technology, allows for unmatched handwriting recognition.

The two technologies together provide MobileLexis with critical features for its MDScript product, which will process prescriptions in real-time through the transmission of penstroke information to a computer or server. The Accuscript technology will translate the handwritten information into digital data and the AuthentImage technology will then secure it for transmission to the pharmacy or healthcare insurance provider.

AuthentImage is a new way to hide information within an ordinary digital image and to extract it again without distorting the original image or the data. The new technique will solve a dilemma faced by digital image users, particularly in sensitive military, legal, and medical applications. Until now they have had to choose between an image that's been watermarked to establish its trustworthiness and one that isn't watermarked but preserves all the original information, allowing it to be enlarged or enhanced to show detail. When information is embedded using the new method, authorized users can do both.

"The technique will be widely applicable to situations requiring authentication of images with detection of changes, and it can also be used to encode information about the image itself, such as who took the picture, when or with what camera," says Murat Tekalp, professor of electrical engineering at the University of Rochester and co-creator of the technology.

"The greatest benefit is in determining if anyone has clandestinely altered an image. These days many commercial software systems can be used to manipulate digital images. By encoding data in this way we can be sure the image has not been tampered with, and then remove the data within it without harming the quality of the picture," he says.

Although the technique is currently implemented in software, it could be implemented in hardware or firmware in trusted devices where image integrity is critical to the application, the authors said. For instance, the technique could be used in a trusted digital camera used to gather forensic evidence to be later used at a trial. If information is embedded in the images captured with the camera using the new technique, any subsequent manipulations of the pictures could be detected and the area where they occurred pinpointed.

"We are pleased to contribute to the MobileLexis product. We think the AuthentImage technology has unique strengths and can have applications in many other fields for authenticating a digital photograph or digital document," says Jack Fraser from the University of Rochester's Office of Technology Transfer.

Accuscript is a software program ideally suited for instantly turning handwriting on digital paper into digital data, according to its principal developers, Venu Govindaraju, professor of computer science and engineering at the University of Buffalo and associate director of the Center of Excellence for Document Analysis and Recognition (CEDAR) and former University of Buffalo graduate student in computer science and engineering, Hanhong Xue, now an employee of IBM.

"Some handwriting recognition programs are designed to ignore the 'noise' that occurs when people write on paper, things like smudges or other marks that are not part of the letters themselves," explains Govindaraju. "That feature, which is critical in hard-copy applications, will not result in optimal performance in a digital paper application, Accuscript, on the other hand, works best with the perfectly clean images that result when users write on digital paper."

The ability to ignore handwritten "noise," Govindaraju says, is a function that must be built into a software package at its most fundamental level, so it is intrinsic to the way the package will function.

While most consumers are familiar with the use of the electronic pads they use to sign for packages or when they charge a purchase, Govindaraju said, those gadgets just capture data, they do not contain any handwriting recognition features.

"Most of these devices are just for signatures and nobody ever will read or recognize them unless there's a question about one of them," he says. "But with digital paper applications, the bar is much higher. The software has to be application-specific, so that a basic lexicon, or vocabulary, can be constructed, which guides the software program in recognizing words correctly."

Govindaraju pointed out that while Accuscript's first application may be in the medical information field, it can be easily customized to any application. MobileLexis is sponsoring the University of Buffalo research so that the software may be further customized.

The University of Rochester licensed AuthentImage to MobileLexis in July, and the University of Buffalo is in the process of finalizing the license of Accuscript to MobileLexis.

CEDAR is the largest research center in the world devoted to developing new technologies that can recognize and read handwriting. Over the past decade, CEDAR has worked with the U.S. Postal Service developing and refining handwriting recognition software for postal applications.