Optical character recognition of documents having non-coplanar regions
AssigneeABBYY Development LLC
InventorAleksey Kalyuzhny
Life of this patent
Estimating the term…
Abstract
Systems and methods for performing OCR of an image depicting text symbols and imaging a document having a plurality of planar regions are disclosed. An example method comprises: receiving a first image of a document having a plurality of planar regions and one or more second images of the document; identifying a plurality of coordinate transformations corresponding to each of the planar regions of the first image of the document; identifying, using the plurality of coordinate transformations, a cluster of symbol sequences of the text in the first image and in the one or more second images; and producing a resulting OCR text comprising a median symbol sequence for the cluster of symbol sequences.
Claims20
A method, comprising:
- obtaining, by a processing device, a first image comprising a first part depicting a first region of a document and a second part depicting a second region of the document, wherein the first region of the document and the second region of the document, as depicted in the first image, are mutually non-coplanar;
- obtaining, by the processing device, a second image of the document;
- identifying, by the processing device and using a first set of reference points of the document, a first transformation associating the first part of the first image with a first part of the second image, wherein the first part of the second image depicts the first region of the document;
- identifying, by the processing device and using a second set of reference points of the document, a second transformation associating the second part of the first image with a second part of the second image, wherein the second part of the second image depicts the second region of the document;
- identifying, by the processing device and using the first transformation and the second transformation, a first symbol sequence depicted in the first image and a corresponding second symbol sequence depicted in the second image;
- and
- performing optical character recognition (OCR) of a text in the document using the first symbol sequence and the second symbol sequence.
A system comprising:
- a memory that stores instructions;
- and
- a processing device, communicatively coupled to the memory, to execute the instructions to:
- obtain a first image comprising a first part depicting a first region of a document and a second part depicting a second region of the document, wherein the first region of the document and the second region of the document, as depicted in the first image, are mutually non-coplanar;
- obtain a second image of the document;
- identify, using a first set of reference points of the document, a first transformation associating the first part of the first image with a first part of the second image, wherein the first part of the second image depicts the first region of the document;
- identify, using a second set of reference points of the document, a second transformation associating the second part of the first image with a second part of the second image, wherein the second part of the second image depicts the second region of the document;
- identify, using the first transformation and the second transformation, a first symbol sequence depicted in the first image and a corresponding second symbol sequence depicted in the second image;
- and
- perform optical character recognition (OCR) of a text in the document using the first symbol sequence and the second symbol sequence.
A non-transitory computer-readable medium having instructions stored thereon that, when executed by a processing device, cause the processing device to perform operations comprising:
- obtaining a first image comprising a first part depicting a first region of a document and a second part depicting a second region of the document, wherein the first region of the document and the second region of the document, as depicted in the first document, are mutually non-coplanar;
- obtaining a second image of the document;
- identifying, using a first set of reference points of the document, a first transformation associating the first part of the first image with a first part of the second image, wherein the first part of the second image depicts the first region of the document;
- identifying, using a second set of reference points of the document, a second transformation associating the second part of the first image with a second part of the second image, wherein the second part of the second image depicts the second region of the document;
- identifying, using the first transformation and the second transformation, a first symbol sequence depicted in the first image and a corresponding second symbol sequence depicted in the second image;
- and
- performing optical character recognition (OCR) of a text in the document using the first symbol sequence and the second symbol sequence.
Dependencies are inferred from the claim text.