Performing optical character recognition using spatial information of regions within a structured document
First Claim
1. A computer-implemented method for identifying information in an electronic document, comprising:
- obtaining a set of training documents for each template of a plurality of templates for the electronic document;
extracting a first set of spatial attributes for at least a first label region and at least a first corresponding value region from the set, the first set of spatial attributes representing a position of at least the first label region and at least the first value region within the electronic document;
training a classifier model based on the extracted first set of spatial attributes to generate a trained classifier model;
segmenting, an image of the electronic document to obtain a second set of spatial attributes of candidate regions in the image, each of the candidate regions corresponding to a label or a value;
identifying at least one candidate region from the candidate regions as a label to generate an identified label based on the obtained second set of spatial attributes using the trained classifier model without performing Optical Character Recognition (OCR);
designating at least one of the candidate regions that is not identified as a label, as a designated value region; and
performing OCR only on the designated value region to obtain at least one value corresponding to the identified label.
1 Assignment
0 Petitions
Accused Products
Abstract
Techniques are disclosed for facilitating optical character recognition (OCR) by identifying one or more regions in an electronic document to perform the OCR. For example a method for identifying information in an electronic document includes obtaining a set of training documents for each template of a plurality of templates for the electronic document, extracting spatial attributes for at least a first label region and at least a first corresponding value region from the set, and training a classifier model based on the extracted spatial attributes, wherein the classifier model is used to identify the information in the electronic document. The spatial attributes represent a position of at least the first label region and at least the first value region within the electronic document.
-
Citations
7 Claims
-
1. A computer-implemented method for identifying information in an electronic document, comprising:
-
obtaining a set of training documents for each template of a plurality of templates for the electronic document; extracting a first set of spatial attributes for at least a first label region and at least a first corresponding value region from the set, the first set of spatial attributes representing a position of at least the first label region and at least the first value region within the electronic document; training a classifier model based on the extracted first set of spatial attributes to generate a trained classifier model; segmenting, an image of the electronic document to obtain a second set of spatial attributes of candidate regions in the image, each of the candidate regions corresponding to a label or a value; identifying at least one candidate region from the candidate regions as a label to generate an identified label based on the obtained second set of spatial attributes using the trained classifier model without performing Optical Character Recognition (OCR); designating at least one of the candidate regions that is not identified as a label, as a designated value region; and performing OCR only on the designated value region to obtain at least one value corresponding to the identified label. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
Specification