Model of documents and method for automatically classifying a document
View Patent ↗A method for automatically creating a model of documents representing a class of documents. The method includes the steps of providing a plurality of documents separated into different classes; and determining at least one potential identifying tag within one document belonging to one class. The identifying tag may be defined by at least its graphical content, size and location within the document. The method also includes checking whether the potential identifying tag is included within at least a document of the class and creating a model of documents related to said one class, the model including the selected identifying tags.
1. A method for automatically creating a model of documents representing a class of documents, the method comprising the steps of:
a) providing a plurality of documents separated into different classes and selecting a first document from the plurality of documents, the first document belonging to a first class;
b) determining at least one potential identifying tag within the first document, said identifying tag being defined by at least a graphical content, a size and a location within the first document
c) correlating the at least one potential identifying tag within the first document with at least one potential identifying tag from a second document of the same first class as the first document, the second document selected from the plurality of documents; and
d) creating a model of documents related to the first class, wherein the model includes the at least one potential identifying tag within the first document having a correlation that is representative of the first class.
2. The method according to claim 1 , further comprising the steps of:
e) checking whether the at least one potential identifying tag within the first document is included within at least a document of another class; and
f) rejecting the at least one potential identifying tag within the first document and repeating steps b) and c).
3. The method according to claim 2 , wherein steps b) to f) are repeated for each class of documents provided in step a).
4. The method according to claim 3 , wherein step b) comprises the steps of:
b1) selecting a working window in the first document;
b2) calculating an object to surface ratio for said working window;
b3) if said ratio lies within predetermined values, selecting the region of said working window as a potential identifying tag.
5. The method according to claim 4 , wherein steps b1) to b3) are repeated by shifting the working window to scan the first document.
6. The method according to claim 2 , wherein steps c) and e) comprise the step of calculating a correlation function between the at least one potential identifying tag within the first document and a region of said second document corresponding to the size and location of the at least one potential identifying tag within the first document.
7. The method according to claim 1 , wherein a given portion of the first document is excluded from the searching of an identifying tag.
8. The method according to claim 1 for automatically classifying a document comprising the steps of:
a′) providing a plurality of models of documents, each model of documents being related to a different class;
b′) comparing a document to be classified with at least one model of documents; and
c′) assigning said document to be classified into a corresponding class when said document to be classified matches said one model of documents.
9. The method according to claim 8 , wherein step b′) includes the step of calculating a correlation function between at least one identifying tag of the model of documents and a region of the document to be classified corresponding to the size and location of said identifying tag.
10. The method according to claim 9 , wherein step c′) includes the steps of:
comparing the correlation function results for each model of documents provided at step a′); and
assigning the document to be classified to the class corresponding to the model of documents providing the correlation result closest to a predetermined value.
11. A computer system for creating a model of documents representing a class of documents comprising:
computer-implemented software means for accessing a plurality of documents separated into different classes
computer-implemented software means for determining at least one potential identifying tag within a first document belonging to a first class, said identifying tag being defined at least by a graphical content, a size and a location within the document;
computer-implemented software means for correlating the at least one potential identifying tag with a second document of the first class; and
computer-implemented software means for creating a model of documents related to said first class, the model including said selected identifying tag.
12. The computer system according to claim 11 , further comprising:
computer-implemented software means for checking whether said potential identifying tag is included within at least a document of another class; and
computer-implemented software for rejecting said preselected identifying tag when said potential identifying tag is included within the document of another class.