[Colloq] PhD Thesis Defense by Mingyan Shao, Friday, Dec. 18

[Rachel Kalweit]

The College of Computer and Information Science presents:

PhD Thesis Defense: Mingyan Shao

Date: Friday, Dec.18
Time: 10:30am
Room: 366 West Village H

Title:  Diagrams: Feature Analysis and Classification

Abstract:

Diagrams are an important part of scientific articles because of the large
amount of information they carry, however most of the research on diagrams
concern about the relationship between diagrams and text in the documents.
Our research instead focuses on diagrams themselves, in particular, vector
diagrams that consist of a list of geometrical primitives such as lines
and rectangles, complementary to raster images that are represented in an
array of pixels. We approach the problem of diagrams from the perspectives
of feature analysis and classification.

One of our contributions is that we define and identify novel content
features of diagrams, graphemes: the elementary yet meaningful unit of
diagrams. Grapheme bridges the semantic gap in diagram research where only
low level content features. A variety of graphemes are defined and
extracted from diagrams and successfully distinguish five major diagram
classes.

The other contribution is that machine learning techniques are proved
capable of classifying and clustering diagrams. Moreover, suitable
algorithms are selected for our data domain. Our research allows to
achieve insights into diagrams from the point of view of machine learning,
and  builds a solid foundation for a diagram retrieval system which has
valuable potential in both research and commercial applications.





Committee:

Prof. Javed Aslam
Prof. Margrit Betke (Boston University)
Prof. Harriet Fell
Prof. Robert Futrelle (Advisor)
Prof. Ronald Williams