Applied Graph Theory in Computer Vision and Pattern Recognition

This book will serve as a foundation for a variety of useful applications of graph theory to computer vision, pattern recognition, and related areas. It covers a representative set of novel graph-theoretic methods for complex computer vision and pattern recognition tasks. The first part of the book presents the application of graph theory to low-level processing of digital images such as a new method for partitioning a given image into a hierarchy of homogeneous areas using graph pyramids, or a study of the relationship between graph theory and digital topology. Part II presents graph-theoretic learning algorithms for high-level computer vision and pattern recognition applications, including a survey of graph based methodologies for pattern recognition and computer vision, a presentation of a series of computationally efficient algorithms for testing graph isomorphism and related graph matching tasks in pattern recognition and a new graph distance measure to be used for solving graph matching problems. Finally, Part III provides detailed descriptions of several applications of graph-based methods to real-world pattern recognition tasks. It includes a critical review of the main graph-based and structural methods for fingerprint classification, a new method to visualize time series of graphs, and potential applications in computer network monitoring and abnormal event detection.

INVESTIGATION OF STRATEGIES TO PROMOTE EFFECTIVE TEACHER PROFESSIONAL DEVELOPMENT EXPERIENCES IN EARTH SCIENCE

This dissertation serves as a call to geoscientists to share responsibility with K-12 educators for increasing Earth science literacy. When partnerships are created among K-12 educators and geoscientists, the synergy created can promote Earth science literacy in students, teachers, and the broader community. The research described here resulted in development of tools that can support effective professional development for teachers. One tool is used during the planning stages to structure a professional development program, another set of tools supports measurement of the effectiveness of a development program, and the third tool supports sustainability of professional development programs. The Michigan Teacher Excellence Program (MiTEP), a Math/Science Partnership project funded by the National Science Foundation, served as the test bed for developing and testing these tools. The first tool, the planning tool, is the Earth Science Literacy Principles (ESLP). The ESLP served as a planning tool for the two-week summer field courses as part of the MiTEP program. The ESLP, published in 2009, clearly describe what an Earth science literate person should know. The ESLP consists of nine big ideas and their supporting fundamental concepts. Using the ESLP for planning a professional development program assisted both instructors and teacher-participants focus on important concepts throughout the professional development activity. The measurement tools were developed to measure change in teachers’ Earth science content-area knowledge and perceptions related to teaching and learning that result from participating in a professional development program. The first measurement tool, the Earth System Concept Inventory (ESCI), directly measures content-area knowledge through a succession of multiple-choice questions that are aligned with the content of the professional development experience. The second measurement, an exit survey, collects qualitative data from teachers regarding their impression of the professional development. Both the ESCI and the exit survey were tested for validity and reliability. Lesson study is discussed here as a strategy for sustaining professional development in a school or a district after the end of a professional development activity. Lesson study, as described here, was offered as a formal course. Teachers engaged in lesson study worked collaboratively to design and test lessons that improve the teachers’ classroom practices. Data regarding the impact of the lesson study activity were acquired through surveys, written documents, and group interviews. The data are interpreted to indicate that the lesson study process improved teacher quality and classroom practices. In the case described here, the lesson study process was adopted by the teachers’ district and currently serves as part of the district’s work in Professional Learning Communities, resulting in ongoing professional development throughout the district.

Back to the future in one week - implementing a Smalltalk VM in PyPy

We report on our experiences with the Spy project, including implementation details and benchmark results. Spy is a re-implementation of the Squeak (i.e., Smalltalk-80) VM using the PyPy toolchain. The PyPy project allows code written in RPython, a subset of Python, to be translated to a multitude of different backends and architectures. During the translation, many aspects of the implementation can be independently tuned, such as the garbage collection algorithm or threading implementation. In this way, a whole host of interpreters can be derived from one abstract interpreter definition. Spy aims to bring these benefits to Squeak, allowing for greater portability and, eventually, improved performance. The current Spy codebase is able to run a small set of benchmarks that demonstrate performance superior to many similar Smalltalk VMs, but which still run slower than in Squeak itself. Spy was built from scratch over the course of a week during a joint Squeak-PyPy Sprint in Bern last autumn.