The Analysis of Images of Mathematical and Chemical Formulas from Patent Documents

Currently, patent documents contain graphic images of device drawings, graphs, chemical and mathematical formulas, and the formulas often need to be recognized and brought to a unified standard. This work analyzes graphic images extracted from the descriptions of FIPS Rospatent patents. Thematic filtering of mathematical and chemical formulas contained in patent documents and their recognition is provided. The theoretical value lies in the developed patent parsing algorithms in the Yandex.Patents system; recognition of chemical and mathematical formulas among graphic patent images; converting graphic images of chemical formulas into SMILES format; converting graphic images of mathematical formulas into LaTeX format. The practical significance of the work lies in the developed software module for analyzing graphic images from patent documents. The scope of the developed module is the study of patents and the reduction of graphic images to a unified standard for solving patent examine problems.