17643227. ENHANCING MACHINE TRANSLATION OF HANDWRITTEN DOCUMENTS simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)

From WikiPatents
Jump to navigation Jump to search

ENHANCING MACHINE TRANSLATION OF HANDWRITTEN DOCUMENTS

Organization Name

INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor(s)

Barton Wayne Emanuel of Manassas VA (US)

Nadiya Kochura of Bolton MA (US)

Su Liu of Austin TX (US)

Tetsuya Shimada of Seattle WA (US)

ENHANCING MACHINE TRANSLATION OF HANDWRITTEN DOCUMENTS - A simplified explanation of the abstract

This abstract first appeared for US patent application 17643227 titled 'ENHANCING MACHINE TRANSLATION OF HANDWRITTEN DOCUMENTS

Simplified Explanation

The patent application describes a method, system, and computer program product for improving machine translation of a document. Here is a simplified explanation of the abstract:

  • The method involves capturing an image of a document that contains multiple characters arranged in a specific layout.
  • The image is classified based on the character layout to determine the document type.
  • A strategy for an intelligent character recognition (ICR) algorithm is determined based on the character layout of the image.
  • The ICR algorithm is then applied to the characters in the image using the determined strategy to generate a translated document.
  • The translated document maintains the original character layout and includes translated characters.

Potential applications of this technology:

  • Enhancing machine translation of documents with complex character layouts, such as legal contracts or technical manuals.
  • Improving the accuracy and efficiency of translating documents with non-standard character arrangements, such as handwritten or stylized fonts.

Problems solved by this technology:

  • Overcoming challenges in accurately translating documents with complex character layouts, which can be difficult for traditional machine translation methods.
  • Addressing the limitations of existing character recognition algorithms when dealing with non-standard character arrangements.

Benefits of this technology:

  • Improved accuracy in translating documents with complex character layouts, leading to more reliable and understandable translations.
  • Increased efficiency in the translation process by automating the recognition and translation of characters in the document.
  • Enhanced usability of machine translation systems for a wider range of document types and layouts.


Original Abstract Submitted

A computer-implemented method, a computer system and a computer program product enhance machine translation of a document. The method includes capturing an image of the document. The document includes a plurality of characters that are arranged in a character layout. The method also includes classifying the image by a document type based on the character layout. The method further includes determining a strategy for an intelligent character recognition (ICR) algorithm with the image based on the character layout of the image. Lastly, the method includes generating a translated document by applying the intelligent character recognition (ICR) algorithm to the plurality of characters in the image using the strategy. The translated document includes a plurality of translated characters that are arranged in the character layout.

Retrieved from "http://wikipatents.org/index.php?title=17643227._ENHANCING_MACHINE_TRANSLATION_OF_HANDWRITTEN_DOCUMENTS_simplified_abstract_(INTERNATIONAL_BUSINESS_MACHINES_CORPORATION)&oldid=25774"