Rozpoznání vzorů pro materiálový výzkum v jaderné energetice

• Thesis title in Czech: Rozpoznání vzorů pro materiálový výzkum v jaderné energetice
• Thesis title in English: Pattern recognition in material research in nuclear energetics
• Academic year of topic announcement: 2021/2022
• Thesis type: dissertation
• Thesis language: čeština
• Department: Department of Software and Computer Science Education (32-KSVI)
• Supervisor: RNDr. Jan Blažek, Ph.D.
• Author: hidden - assigned and confirmed by the Study Dept.
• Date of registration: 02.03.2022
• Date of assignment: 02.03.2022
• Confirmed by Study dept. on: 02.03.2022
• Advisors: doc. RNDr. Elena Šikudová, Ph.D.

Guidelines

During last few years deep learning became a main tool for image recognition of objects in human environment. However, the objects in nuclear environment are very different, but still human readable. In spite of the human environment the nuclear energetics is still out of the focus of researchers from image processing area. Recognition of particular structures and their comparison is the main tool for monitoring, measurement and error reporting in this area.

The main focus of the work is the selection of suitable algorithms for pattern recognition and development of new ones, which will be appropriate for automation of pattern recognition in the environment of nuclear energetics. The automation will enable pattern tracking and evolution during the time. The student will be able to improve the way of data collection and set up a desirable methodology for quality image-based records acquisition.

References

Gonzalez, R. C. & Woods, R. E. (2008), Digital image processing , Prentice Hall , Upper Saddle River, N.J. .
Goodfellow et. al. (2016), Deep Learning, MIT Press.