System and method for identifying and labeling fields of text associated with scanned business documents
A system for electronically distilling information from a business document uses a network scanner to electronically scan a platen area, having a business document thereon, to create a bitmap. A network server carries out a segmentation process to segment the scan generated bitmap into a bitmap object, the bitmap object corresponding to the scanned business document; a bitmap to text conversion process to convert the bitmap object into a block of text; a semantic recognition process to generate a structured representation of semantic entities corresponding to the scanned business document; and a document generation process to convert the structured representation into a structure text file. The semantic recognition process includes the processes of generating, for each line of text having a keyword therein, a terminal symbol corresponding to the keyword therein; generating, for each line of text not having a keyword therein and absent of numeric characters, an alphabetic terminal symbol; generating, for each line of text not having a keyword therein and having a numeric character therein, an alphanumeric terminal symbol; generating a string of terminal symbols from the generated terminal symbols; determining a probable parsing of the generated string of terminal symbols; labeling each text line, according to a determined function, with non-terminal symbols; and parsing the business document information text into fields of business document information text based upon the non-terminal symbol of each text line and the determined probable parsing of the generated string of terminal symbols.
1. A method for parsing business card information text from electronically derived text representing an electronically scanned business card, comprising:
(a) electronically ordering, using an electronic device, lines of text linearly left-to-right, top-to-bottom;
(b) generating, for each line of text having a keyword therein, a terminal symbol corresponding to the keyword therein, the terminal symbol being a member of a pre-defined set of terminal symbols;
(c) generating, for each line of text not having a keyword therein and absent of numeric characters, an alphabetic terminal symbol;
(d) generating, for each line of text not having a keyword therein and having a numeric character therein, an alphanumeric terminal symbol;
(e) generating a string of terminal symbols from the generated terminal symbols;
(f) electronically determining, using an electronic device, a probable parsing of the generated string of terminal symbols;
(g) labeling each text line, according to a determined function, with non-terminal symbols; and
(h) electronically parsing, using an electronic device, the business card information text into fields of business card information text based upon the non-terminal symbol of each text line and the determined probable parsing of the generated string of terminal symbols.
2. The method as claimed in claim 1 , further comprising:
(i) inserting a terminal separator symbol between lines of text being labeled with different non-terminal symbols.
3. The method as claimed in claim 1 , further comprising:
(i) inserting a terminal separator symbol between lines of text being positioned spatially apart.
4. The method as claimed in claim 1 , further comprising:
(i) inserting a terminal separator symbol between lines of text being labeled with different non-terminal symbols; and
(j) inserting a terminal separator symbol between lines of text being positioned spatially apart.
5. The method as claimed in claim 1 , wherein each line of text includes font-size estimate information.
6. The method as claimed in claim 5 , wherein the font-size estimate information is normalized within the text representing an electronically scanned business card.
7. The method as claimed in claim 6 , wherein a terminal symbol is generated based upon the normalized font-size estimate information associated with the line of text.
8. The method as claimed in claim 1 , wherein the probable parsing of the generated string of terminal symbols is determined using a Cocke-Younger-Kasami algorithm and stochastic context free grammar.
9. The method as claimed in claim 1 , wherein the probable parsing of the generated string of terminal symbols is determined using a Cocke-Younger-Kasami algorithm and probabilistic context free grammar.
10. The method as claimed in claim 1 , wherein the pre-defined set of terminal symbols includes a terminal symbol representing voice line information, a terminal symbol representing fax line information, a terminal symbol representing mobile voice line information, a terminal symbol representing pager information, and a terminal symbol representing other voice line information.
11. The method as claimed in claim 1 , wherein the pre-defined set of terminal symbols includes a terminal symbol representing email address information.
12. The method as claimed in claim 1 , wherein the pre-defined set of terminal symbols includes a terminal symbol representing uniform resource locator information.
13. The method as claimed in claim 10 , wherein the pre-defined set of terminal symbols further includes a terminal symbol representing email address information and a terminal symbol representing uniform resource locator information.
14. The method as claimed in claim 1 , wherein the pre-defined set of terminal symbols includes a terminal symbol representing an emphasized line of text and a terminal symbol representing a huge font line of text.
15. The method as claimed in claim 13 , wherein the pre-defined set of terminal symbols includes a terminal symbol representing an emphasized line of text and a terminal symbol representing a huge font line of text.
16. The method as claimed in claim 1 , wherein a non-terminal symbol represents a name of an organization.
17. The method as claimed in claim 1 , wherein a non-terminal symbol represents a name and title of a person.
18. The method as claimed in claim 1 , wherein a non-terminal symbol represents phone numbers.
19. The method as claimed in claim 1 , wherein a non-terminal symbol represents internet information.
20. The method as claimed in claim 1 , wherein a non-terminal symbol represents comment information.