Pattern recognition for in-game spell systems

• Thesis title in Czech: Rozpoznávání tvarů pro herní systémy kouzel
• Thesis title in English: Pattern recognition for in-game spell systems
• Key words: hry, rozpoznávání vzorů, neuronové sítě
• English key words: games, pattern recognition, neural networks
• Academic year of topic announcement: 2016/2017
• Thesis type: Bachelor's thesis
• Thesis language: angličtina
• Department: Department of Software Engineering (32-KSI)
• Supervisor: RNDr. Miroslav Kratochvíl, Ph.D.
• Author: hidden - assigned and confirmed by the Study Dept.
• Date of registration: 25.07.2017
• Date of assignment: 31.07.2017
• Confirmed by Study dept. on: 22.11.2017
• Date and time of defence: 06.09.2018 09:00
• Date of electronic submission: 20.07.2018
• Date of submission of printed version: 20.07.2018
• Date of proceeded defence: 06.09.2018
• Opponents: Mgr. Vít Šefl

Guidelines

For the purpose of improving systems of casting magic spells in computer games, the thesis aims to implement an algorithm that recognizes structured combinations (e.g. embeddings, agglomerations or convolutions) of magical symbols (e.g. runes, letters or simple shapes) and demonstrate its functionality by providing a comprehensive mapping of the recognized features to a spell system in a matching game environment.

Recognition will be implemented by a method chosen from the reviewed literature and modified to handle the combinations of the basic shapes. Algorithm should run in time negligible to the user, while recognizing sufficiently complex combinations of the shapes.

References

Bishop, Christopher M. Neural networks for pattern recognition. Oxford university press, 1995.

Seidl, Markus. Computational Analysis of Petroglyphs. Diss. Technische Universität Wien, 2016.

Petrakis, Euripides G. M., Aristeidis Diplaros, and Evangelos Milios. "Matching and retrieval of distorted and occluded shapes using dynamic programming." IEEE Transactions on Pattern Analysis and Machine Intelligence 24.11 (2002): 1501-1516.

Wu, Yi-Chao, Fei Yin, and Cheng-Lin Liu. "Improving handwritten Chinese text recognition using neural network language models and convolutional neural network shape models." Pattern Recognition 65 (2017): 251-264.