Giovanni Seni · Motorola Human Interface Labs
TreadMill Ink -- Enabling Continuous Pen Input on Small Devices

Portable computing devices, often called personal digital assistants (PDAs), have increased in popularity during the past couple of years. A typical PDA is a limited function microcomputer with a touch-enabled LCD display for input and output. PDAs are evolving from simple agenda and address book electronic devices into multimedia terminals capable of wireless Internet communications. As the text data entry needs on these small devices shift from short address book or calendar items to longer notes or e-mail messages, the demand for natural, high-throughput text input methods increases.

PDAs currently use the following UI methods for text input: a unistroke character-based interface (e.g., Graffiti), where each character is written with a single pen trace; an on-screen keypad, a write-anywhere interface (e.g., Transcriber), or a plugin keyboard. Each of these methods is beset with problems and compromises. Text input using a unistroke alphabet is unnatural because it requires users to learn new character shapes; text input using an on-screen keypad is somewhat clumsy to use on small screens. In a write-anywhere interface, users can enter entire words or phrases anywhere on the screen, which increases text input throughput over character-based methods; however, such interfaces are problematic because it is difficult to differentiate whether the stylus is acting as a pointer or as an inking instrument for text entry. An expansion keyboard is impractical for on-the-go input.

In this talk I present a novel handwriting input user interface (UI) for small portable devices with a touch-enabled screen. This UI includes a writing area on the screen that behaves as a "treadmill" such that electronic ink input is immediately moved from right to left while it is being entered, giving the user the feeling of writing text on a virtual "ticker-tape". This method allows the user to write continuously without running out of writing space, and takes up very little screen real-estate to implement. The UI communicates with a recognition engine capable of recognizing continuously input handwritten text and that can buffer incomplete ink entries. The UI technique described, unlike prior interfaces in which space constraints limit the ability to continuously write on the device screen and thus slow text input, allows the full throughput benefit of continuous text input to be realized within a very small writing space.

Giovanni Seni is a Member of the Technical Staff at the Motorola Human Interface Labs in Mountain View, CA. He has worked extensively in the field of pen-based user interfaces and has published several articles in this area. Prior to joining Motorola Labs he was a Software Engineer with Lexicus, a Motorola-acquired startup company developing handwriting recognition software, where he worked on two generations of recognition systems. He received a M.S. and Ph.D. in Computer Science from State University of New York at Buffalo (SUNY at Buffalo) in 1996, where he studied on a Fulbright scholarship. His research was on the use of convolutional neural networks for recognizing on-line cursive words in a large vocabulary setting. In his spare time Giovanni likes to play with his children, read history books and play tennis.