Topics

(order may change depending on availability of tablets)
1: Introduction
2: Feature based recognition (Rubine)
3: Gathering Data: Students will gather data on which to test the algorithms to be studied later in the semester.
4: Recognizing primitives (breaking down strokes into lines, arcs, and ellipses)
5: Geometric algorithms
6: Vision based algorithms
7: Combining classifiers with Adaboost
8: Combining classifiers using other techniques from machine learning
9: User Interface Issues

pen-based computer

pen-based computer, computerthat uses pattern-recognition software to enable it to accept handwriting as a form of input. A stylus, which may contain special electronic circuitry, is used to write on the computer display or on a separate tablet. The earliest devices were limited to recognizing geometric shapes for computer graphics applications and neatly printed alphabetic characters. Pattern recognition has improved to the level where cursive input is now acceptable, especially in personal digital assistants, although such input is not always accurately interpreted by the software. Some software requires the use of a specially modified alphabet to enter data.

nteracting with computers using a pen, as opposed to a keyboard or mouse. A pen allows fluid handwriting, gestures, and sketching that are difficult with many other input devices, thus enabling a more expressive form of input. Pen-based interfaces are popular in PDAs because of the portability and convenience of a pen. Stroke recognition allows the computer to interpret handwriting and gestures in terms of text and commands.