In this thesis, we deal with online recognition of handwritten chemical formulas and equations. First, we explain and point out some methods used, and present existing solutions. We examine the properties of the chemical structures. Then we describe our own solution consisting of detection of symbols on the basis of the spacial relations of strokes and their recognition provided by an existing third party library. After that the complex structure of the chemical formula or equation is examined using formal grammar, which we designed. The work also includes implementation of solutions in the form of web application and its experimental evaluation on our own collected set of test data. Powered by TCPDF (www.tcpdf.org)
Identifer | oai:union.ndltd.org:nusl.cz/oai:invenio.nusl.cz:347576 |
Date | January 2016 |
Creators | Nevolová, Kateřina |
Contributors | Průša, Daniel, Stria, Jan |
Source Sets | Czech ETDs |
Language | Czech |
Detected Language | English |
Type | info:eu-repo/semantics/masterThesis |
Rights | info:eu-repo/semantics/restrictedAccess |
Page generated in 0.0019 seconds