RESEARCH OF POSSIBILITIES OF APPLICATION INFTYREADER OCR-SYSTEMS IN PATTERN RECOGNITION PROBLEMS OF GRAPHICAL OBJECTS OF SCIENTIFIC AND TECHNICAL DOCUMENTATION
Keywords:
OCR, image recognition containing mathematical formulas, TeX, transformation of paper materials in digital formatAbstract
We investigate a method of rapid and qualitative recognition of scientific and technical documentation containing the object information in the form of formulas, digital images, various types of graphs. The method is based on the use of software InftyReader OCR-system developed by laboratory staff Masakazu Suzuki at the University mathematics graduate of Kyushu and the research group on mathematical processing InftyProject data [1-6]. This method makes it possible to recognize monochrome images 400-600 dpi, and quickly and accurately convert various types of graphical information in the text required a custom format.
