Electronic apparatus, method, and program
AssigneeToshiba Client Solutions CO., LTD.
InventorChikashi Sugiura
Life of this patent
Estimating the term…
Abstract
According to one embodiment, an electronic apparatus performs a character recognition process, uses, if a stroke in a first area of the first handwritten document and a stroke in a second area are the same, a character recognition result of the first handwritten document, and performs, if a stroke in the first area and a stroke in the second area are different, the character recognition process for the second area including the different stroke.
Claims11
An electronic apparatus for performing a character recognition process for plural stroke data in a handwritten document including plural areas, the electronic apparatus comprising:
- one or more hardware processors configured to:
- store a first handwritten document and first hash values for the plural areas of the first handwritten document in at least a working memory, wherein the first handwritten document is obtained by performing a character recognition process for the handwritten document;
- calculate, at a character recognition process for a second handwritten document which is created by editing the first handwritten document, second hash values for the plural areas of the second handwritten document;
- compare the first hash values in the working memory and the second hash values to detect an area wherein the first hash value is different from the second hash value;
- use, for a first area wherein the first hash value is not different from the second hash value, at least a part of a character recognition result of the first areas of the first handwritten document;
- and
- use, for a second area wherein the first hash value is different from the second hash value, a result of the character recognition process for the handwritten document.
A method for performing a character recognition process for plural stroke data in a handwritten document including plural areas, the method comprising:
- storing a first handwritten document and first hash values for the plural areas of the first handwritten document in at least a working memory, wherein the first handwritten document is obtained by performing a character recognition process for the handwritten document;
- calculating, at a character recognition process for a second handwritten document which is created by editing the first handwritten document, second hash values for the plural areas of the second handwritten document;
- comparing the first hash values in the working memory and the second hash values to detect an area wherein the first hash value is different from the second hash value;
- using, for a first area wherein the first hash value is not different from the second hash value, at least a part of a character recognition result of the first handwritten document;
- and
- using, for a second area wherein the first hash value is different from the second hash value, a result of the character recognition process for the handwritten document.
A non-transitory computer-readable storage medium having stored thereon a computer program which performs a character recognition process for plural stroke data in a handwritten document including plural areas, and is executable by a computer, the computer program capable of causing the computer to execute functions of:
- storing a first handwritten document and first hash values for the plural areas of the first handwritten document in at least a working memory, wherein the first handwritten document is obtained by performing a character recognition process for the handwritten document;
- calculating, at a character recognition process for a second handwritten document which is created by editing the first handwritten document, second hash values for the plural areas of the second handwritten document;
- comparing the first hash values in the working memory and the second hash values to detect an area wherein the first hash value is different from the second hash value;
- using, for a first area wherein the first hash value is not different from the second hash value, at least a part of a character recognition result of the first handwritten document;
- and
- using, for a second area wherein the first hash value is different from the second hash value, a result of the character recognition process for the handwritten document.
Dependencies are inferred from the claim text.