Image processing apparatus, program and recording medium for document registration

• US 7,920,742 B2
• Filed: 07/31/2006
• Issued: 04/05/2011
• Est. Priority Date: 03/06/2006
• Status: Expired due to Fees

• Current Assignee: Fuji Xerox
• Original Assignee: Fuji Xerox Company Limited (Fujifilm Holdings Corporation)
• Inventors: Kato, Masahiro
• Primary Examiner(s): Wu; Jingge
• Assistant Examiner(s): Thomas; Mia M
• Application Number:
  US11/495,635
• Publication Number:
  US 20070206883A1
• Time in Patent Office: 1,709 Days
• Field of Search: 382137-140, 382/176, 382/178, 382/182, 382/190, 382/199, 382/195, 382/186
• US Class Current: 382/195
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1448 based on markings or identifiers characterising the document or the area

Abstract

An image processing apparatus includes a document input unit that inputs document data of a document, a first identifying unit that identifies a position of a string included in the document, a second identifying unit that identifies a range of a mark given in the document based on an orientation of the string, and a string extracting unit that extracts a string subject to the mark, based on the position of the string identified by the first identifying unit and the range of the mark identified by the second identifying unit.

Claims

1. An image processing apparatus, comprising:

a document input unit that inputs document data of a document;

a first identifying unit that identifies a position of a string in the document;

a second identifying unit that identifies a mark handwritten from a highlighter and is non-textual, the mark being separate from the string, in the document; and

an orientation detection unit that detects an orientation of the mark,

wherein the mark is defined by a range from a start position and an end position based on the detected orientation; and

a character string extracting unit that extracts a new string, based on the position of the string identified by the first identifying unit, and the mark identified by the second identifying unit and defined based on the detected orientation.

2. The image processing apparatus according to claim 1, further comprising a registering unit that registers the string extracted by the character string extracting unit as attribute information of the document data.

3. The image processing apparatus according to claim 1, wherein the character string extracting unit extracts the string from a plurality of strings identified by the first identifying unit, based on the position of the string identified by the first identifying unit and the mark identified by the second identifying unit.

4. The image processing apparatus according to claim 1, wherein:

when at least one of the start position and the end position of the mark, which defines the mark is identified by the second identifying unit, is less than a beginning of the position of the string or an end of the position of the string, the character string extracting unit determines whether or not the string identified by the first identifying unit is to be extracted based on a extraction condition that is preset.

5. The image processing apparatus according to claim 4, wherein the extraction condition is based on a ratio between a part that the string from the plurality of strings overlaps the mark and a part that the given string does not overlap the mark.

6. The image processing apparatus according to claim 4, wherein the extraction condition is based on a type of word represented by the given string.

7. The image processing apparatus according to claim 1, wherein the second identifying unit having:

a connected pixel area extracting unit that extracts range of a connected pixel area in which pixels representing the mark given in the document are connected; and

an end-of-mark identifying unit that identifies a beginning and an end of the mark based on the orientation of the mark identified by the orientation identifying unit and the range of the connected pixel area extracted by the connected pixel area extracting unit.

8. The image processing apparatus according to claim 7, wherein the end-of-mark identifying unit identifies, as the beginning and end of the mark, one end and the other end of the connected pixel area extracted by the connected pixel area extracting unit along the orientation of the mark identified by the orientation identifying unit.

9. The image processing apparatus of claim 1, wherein the character string extracting unit extracts the string based on the position of the string identified by the first identifying unit and whether the string overlaps the mark identified by the second identifying unit.

10. A non-transitory computer readable medium that records an image processing program that causes a computer to perform processing comprising:

inputting document data of a document;

identifying a position of a string in the document;

identifying a mark handwritten from a highlighter and is non-textual, the mark being separate from the string, given in the document;

detecting an orientation of the mark,

wherein the mark is defined by a range from a start position and an end position based on the detected orientation, and

extracting a new character string based on the position of the identified string and the identified mark, and the mark identified and defined based on the detected orientation.

11. The non-transitory computer readable medium of claim 10, further comprising:

extracting the string based on the identified position and whether the string overlaps the identified mark.

12. An image processing method to enable a computer to perform a process for document registration processing, the process comprising:

inputting document data of a document;

identifying a position of a string in the document;

identifying a mark handwritten from a highlighter and is non-textual, the mark being separate from the string, given in the document; and

detecting an orientation of the mark,

wherein the mark is defined by a range from a start position and an end position based on the detected orientation, and

extracting a new character string based on the position of the identified string and the identified mark, and the mark identified and defined based on the detected orientation.

13. The image processing method of claim 12, further comprising:

extracting the string based on the identified position and whether the string overlaps the identified mark.