Paper form data conversion system, OCR engine learning image generation device and image analysis device

摘要

An object of the present invention is to improve the accuracy of extracting character information from a form such as an invoice. A paper form data conversion system 10 for extracting character information from a target image obtained by scanning a form and outputting the character information to an external database includes an OCR unit 23, a structure analysis unit 25, and a mapping unit 26. The OCR unit 23 extracts character information from the target image using an OCR engine. The structure analysis unit 25 generates structured data in which the character information extracted by the OCR unit 23 is structured based on the position of the character information on the target image. The mapping unit 26 inputs structured data into the database using a mapping table indicating the correspondence between the structured data and the structure of the database. [Selected figure] Figure 1