Date: | November 11, 2010 |
---|---|
Location: | DC 1331 |
Time: | 10:30 |
Chair: | Jamie Ruiz |
Date: | November 18, 2010 | November 25, 2010 | December 2, 2010 | December 9, 2010 |
---|---|---|---|---|
Location: | DC 1331 10:30 | DC 1331 10:30 | CGL Lab | DC 1331 10:30 |
Chair: | Mike Terry |
Matthew Thorne |
Cherry Zhang |
Zainab AlMeraj |
Technical Presentation: | Alex Pytel |
Jamie Ruiz |
Mike Terry |
Matthew Thorne |
Ed Lank |
Title : Analyzing Sketch Content Using In-Air Packet Information
Abstract: Recognizing hand drawn mathematical matrices on tablet computers has proven particularly challenging. While individual expression recognition can be simplified by assuming the entire content is a single semantic construct, a single math expression, a matrix is composed of multiple expressions arranged in rows and columns. These expressions must first be segmented into matrix elements, and then each individual matrix element expression must be recognized. In this work, we show how a simple algorithm on in-air (i.e. non-inking) strokes can be used to analyze the drawing order of a matrix to determine whether the matrix is written in row-major, column-major, or mixed-order. Once the drawing order is recognized, we show how outlier analysis on in-air packets gives rapid, reliable segmentation of matrix elements. Once recognized, individual matrix elements can be parsed by a standard recognizer, and complex matrix operations can be performed on hand drawn content. This work demonstrates the power inherent in using non-obvious electronic stylus data, in this case in-air packets, to enhance the recognition of hand drawn content. |
---|
Also see other Math and CS postings.