Introduction to Computer Vision Tools for Modern Microscopy
8 lectures, March-April,2013, Mondays 10-11 am
4007 Genetic Medicine Building, 1 credit hour
room 4078 Genetic Medicine Building
Guest lecturer: Klaus Hahn
Registration deadline: January 8, 2013
For questions and registration, contact Kathy Justice.
This graduate-level course will introduce the basic principles of computer vision as a high-level image analysis tool, with an emphasis on its practical application to live-cell fluorescence microscopy. The course will start with an overview of the capabilities and limitations of modern microscopy for visualizing processes that occur at the cellular and molecular level. Next the course will cover two major computer vision approaches to automated content recognition: model-based analysis and supervised machine learning. Important topics and available techniques will be discussed and demonstrated using examples from current biomedical research, including live-cell imaging using biosensors and high-throughput screens. The last lecture will cover mathematical and statistical methods for quantifying image data. The course is designed as an introduction to computer vision applications for modern microscopy and will not be mathematically/statistically intensive. Therefore, there are no formal prerequisites required for this course.
This course will introduce computer vision methods for cell biology. Each topic will be motivated with an explanation of a computational challenge, followed by a discussion of available techniques to address the need and practical examples for how to apply the techniques. No prerequisites are required.
Course objectives (learning outcomes):
The objectives of this course are twofold. First, students will learn about the difficulties associated with automated image content recognition. An understanding of imaging issues from the perspective of quantitative image analysis will provide students with a balanced view of modern microscopy studies. Second, the course will cover a broad range of computer vision techniques and provide students with appropriate training to allow them to select and apply methods that are most relevant to their research.