Searching document images
AssigneeHewlett-Packard Development Company, L.P.
InventorsSuryaprakash KOMPALLI, Ashwin Gopakumar
Life of this patent
Estimating the term…
Abstract
Disclosed is a method of searching a digital image of a document for a predetermined keyword. The method identifies a word in the digital image, the word comprising one or more shapes. A test matrix comprising a difference vector for each character of the word is generated, and a template matrix comprising a difference vector for each shape of the keyword is also generated, wherein a difference vector represents the differences between the visual features of a respective shape and the visual features of a collection of reference shapes. A measure of similarity between the word and the keyword is generated by comparing the test matrix and the template matrix.
Claims15
A method of searching a digital image of a document for a predetermined keyword comprising one more keyword shapes, the method comprising the steps of:
- using a computer, identifying a word in the digital image, the word comprising one or more shapes;
- using a computer, generating a test matrix comprising a difference vector for each shape of the word, a difference vector representing the differences between the visual features of a respective shape and the visual features of a collection of reference shapes;
- using a computer, generating a template matrix comprising a difference vector for each keyword shape of the keyword;
- and
- using a computer, determining a measure of similarity between the word and the keyword by comparing the test matrix and the template matrix.
A computer program product comprising computer program code adapted, when executed on a computer, to cause the computer to implement the steps of:
- identifying a word in the digital image, the word comprising one or more shapes;
- generating a test matrix comprising a difference vector for each shape of the word, a difference vector representing the differences between the visual features of a respective shape and the visual features of a collection of reference shapes;
- generating a template matrix comprising a difference vector for each keyword shape of a keyword;
- and
- determining a measure of similarity between the word and the keyword by comparing the test matrix and the template matrix.
A computer-readable medium having computer-executable instructions stored thereon that, if executed by a computer, cause the computer to implement the steps of:
- identifying a word in the digital image, the word comprising one or more shapes;
- generating a test matrix comprising a difference vector for each shape of the word, a difference vector representing the differences between the visual features of a respective shape and the visual features of a collection of reference shapes;
- generating a template matrix comprising a difference vector for each keyword shape of a keyword;
- and
- determining a measure of similarity between the word and the keyword by comparing the test matrix and the template matrix.
Dependencies are inferred from the claim text.