Back to results
US 9,384,423 B2Granted
System and method for OCR output verification
AssigneeXerox Corporation
InventorsJose Antonio Rodriguez-Serrano, Florent C. Perronnin
Life of this patent
Estimating the term…
Abstract
A system and method for computing confidence in an output of a text recognition system includes performing character recognition on an input text image with a text recognition system to generate a candidate string of characters. A first representation is generated, based on the candidate string of characters, and a second representation is generated based on the input text image. A confidence in the candidate string of characters is computed based on a computed similarity between the first and second representations in a common embedding space.
Claims22
A method for computing confidence comprising:
- with a text recognition system, performing character recognition on an input text image to generate a candidate string of characters;
- generating a first representation based on the candidate string of characters, the generating of the first representation comprising partitioning the candidate character string into a plurality of regions and extracting a representation of each of the regions, the character string representation being derived by aggregating the region representations;
- generating a second representation based on the input text image;
- computing a confidence in the candidate string of characters based on a computed similarity between the first and second representations in a common embedding space, at least one of the first and second representations being projected into the common embedding space;
- and
- wherein at least one of the performing character recognition, generating the first representation, generating the second representation, and computing the confidence is performed with a computer processor.
3 more elements
A method, for computing confidence comprising:
- with a text recognition system, performing character recognition on an input text image to generate a candidate string of characters;
- generating a first representation based on the candidate string of characters comprising synthesizing a synthetic image of the candidate string of characters generated by the character recognition and computing a representation based on the synthetic image;
- generating a second representation based on the input text image;
- computing a confidence in the candidate string of characters based on a computed similarity between the first and second representations in a common embedding space, at least one of the first and second representations being projected into the common embedding space;
- and
- wherein at least one of the performing character recognition, generating the first representation, generating the second representation, and computing the confidence is performed with a computer processor.
3 more elements
A system for computing confidence comprising:
- a text image representation component which generates a text image representation based on features extracted from a text image;
- a text string representation component which receives a character string from an associated text recognition system as a candidate string for the text image,
- synthesizes a word image from the character text string using a computer-generated font and generates a character string representation based on features extracted from the synthesized word image, or
- partitions the character string into a plurality of regions, extracts a representation of each of the regions, and aggregates the region representations to generate a character string representation;
- a comparison component which computes a confidence in the character string based on a similarity between the text image representation and the character string representation in a learned embedding space;
- an information output component which outputs information based on the computed confidence;
- and
- a processor which implements the text image representation component, text string representation component, comparison component, and information output component.
5 more elements
A license plate recognition method comprising:
- performing optical character recognition on an image of a license plate to generate a character string as a candidate license plate number;
- computing a confidence in the candidate license plate number based on a function which embeds a representation of the license plate image and a representation of the candidate license plate number in an embedding space with a matrix of weights learned on an annotated set of license plate images;
- and
- where the confidence meets a threshold, outputting the character string as a recognized license plate number for the image of the license plate, otherwise initiating another process for license plate number recognition;
- wherein at least one of the performing, computing and outputting is performed with a processor.
2 more elements
Dependencies are inferred from the claim text.