PAGE ANALYSIS SYSTEM

• US 20010012400A1
• Filed: 11/18/1996
• Published: 08/09/2001
• Est. Priority Date: 11/18/1996
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: NIKI, TORU, WANG, SHIN-YWAN
• Granted Patent: US 6,512,848 B2
• Time in Patent Office: Days
• US Class Current: 382/181
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables

Abstract

A method for increasing the accuracy of image data classification in a page analysis system for analyzing image data of a document page. The method includes inputting image data of a document page as pixel data, analyzing the pixel data in order to locate all connected pixels, rectangularizing connected pixel data into blocks, analyzing each of the blocks of pixel data in order to determine the type of image data contained in the block, outputting an attribute corresponding to the type of image data determined in the analyzing step, and performing optical character recognition to attempt to recognize a character of the block of image data in the case that the analyzing step cannot determine the type of image data contained in the block.

Claims

1. In a page analysis system for analyzing image data of a document page, a method for increasing the accuracy of image data classification, the method comprising the steps of:

inputting image data of a document page as pixel data;

a first analyzing step for analyzing the pixel data in order to locate all connected pixels;

rectangularizing connected pixel data into blocks;

a second analyzing step for analyzing each block of pixel data in order to determine type of image data contained in each block;

outputting an attribute corresponding to the type of image data within the block determined in the second analyzing step; and

performing optical character recognition so as to recognize image data in a block in the case that the second analyzing step cannot determine a type of image data contained in the block.

2. A method according to

claim 1

, wherein, in the second analyzing step, the pixel data is analyzed for text data or non-text data and wherein, in the outputting step, in the case that the block of image data is determined to be text data, a text data attribute is output, or, if the data is determined to be non-text data, a non-text data attribute is output.

3. In a page analysis system for analyzing image data of a document page, a method for accurately classifying image data, the method comprising the steps of:

inputting image data of a document page as pixel data;

combining and rectangularizing connected pixel data into blocks of image data; and

analyzing and classifying the data as a type of data;

wherein, in the case that a block of image data is classified as text data and the size of the text data is not equal to a preset size threshold, performing optical character recognition on the text data.

4. A method according to

claim 3

, further comprising outputting a picture data attribute in the case that blocked image data is recognized in the performing step.

5. A method according to

claim 3

, further comprising outputting an unknown data attribute in the case that the blocked image data cannot be recognized in the performing step.

6. A method according to

claim 3

, wherein optical character recognition is performed on the text data only in the case that a size of text data in the block is-greater than the preset size threshold.

7. A method according to

claim 3

, wherein optical character recognition is performed on the text data only in the case that a size of the text data in the block is less than the preset size threshold.

8. A method according to

claim 3

, wherein the size threshold is based on an average size of pixel data in the analyzed document page.

9. Computer-executable process steps stored in a computer-readable medium, the process steps for use in a page analysis system for analyzing image data of a document page, the process steps to increase the accuracy of image data classification, the process steps comprising:

an inputting step to input image data of a document page as pixel data;

a first analyzing step to analyze the pixel data in order to locate all connected pixels;

a rectangularizing step to rectangularize connected pixel data into blocks;

a second analyzing step to analyze each block of pixel data in order to determine type of image data contained in each block;

an outputting step to output an attribute corresponding to the type of image data within the block determined in the second analyzing step; and

a performing step to perform optical character recognition so as to recognize image data of a block in the case that the second analyzing step cannot determine a type of image data contained in the block.

10. Computer-executable process steps according to

claim 9

, wherein, in the second analyzing step, the pixel data is analyzed for text data or non-text data and wherein, in the outputting step, in the case that the block of image data is determined to be text data, a text data attribute is output, or, if the data is determined to be non-text data, a non-text data attribute is output.

11. Computer-executable process steps for analyzing image data of a document page, the steps comprising:

an inputting step to input image data of a document page as pixel data;

a combining and rectangularizing step to combine and rectangularize connected pixel data into blocks of image data; and

an analyzing and classifying step to analyze and classify the data as a type of data;

wherein, in the case that a block of image data is classified as text data and the size of the text data is not equal to a preset size threshold, performing optical character recognition on the text data.

12. Computer-executable process steps according to

claim 11

, further comprising an outputting step to output a picture data attribute in the case that blocked image data is recognized in the performing step.

13. Computer-executable process steps according to

claim 11

, further comprising an outputting step to output an unknown data attribute in the case that the blocked image data cannot be recognized in the performing step.

14. Computer-executable process steps according to

claim 11

, wherein optical character recognition is performed on the text data only in the case that a size of text data in the block is greater than the preset size threshold.

15. Computer-executable process steps according to

claim 11

, wherein optical character recognition is performed on the text data only in the case that a size of the text data in the block is less than the preset size threshold.

16. Computer-executable process steps according to

claim 11

, wherein the size threshold is based on an average size of pixel data in the analyzed document page.

17. An apparatus for performing page analysis of a document page, the apparatus comprising:

a memory which stores page analysis process steps executable by a processor and an image of a document page; and

a processor which executes the page analysis process steps stored in the memory (1) to input image data of a document page as pixel data, (2) to analyze the pixel data in order to locate all connected pixels, (3) to rectangularize connected pixel data into blocks, (4) to analyze each block of pixel data in order to determine a type of image data contained in each block, (5) to output an attribute corresponding to the type of image data within a block analyzed by the processor, and (6) to perform optical character recognition to attempt to recognize a character of the block of image data in a case that the processor cannot determine a type of image data contained in the block.

18. An apparatus according to

claim 17

, wherein the processor analyzes each block of pixel data in order to determine a type of image data contained in each block by analyzing the pixel data for text data or non-text data;

and

wherein the processor outputs (1) a text data attribute in a case that the block of image data is determined to be text data, or (2) a non-text data attribute in a case that the data is determined to be non-text data.

19. An apparatus for analyzing image data of a document page, the apparatus comprising:

a memory which stores page analysis process steps executable by a processor and an image of a document page; and

a processor which executes the page analysis process steps stored in the memory (1) to input image data of a document page as pixel data, (2) to combine and rectangularize pixel data into blocks of image data, (3) to analyze and classify the data as a type of data, and (4) to perform optical character recognition on text data in a case that a block of image data is classified as text data and the size of the text data is not equal to a preset size threshold.

20. An apparatus according to

claim 19

, wherein the processor executes process steps stored in the memory to output a picture data attribute in a case that blocked image data is recognized.

21. An apparatus according to

claim 19

, wherein the processor outputs an unknown data attribute in a case that the blocked image data cannot be recognized.

22. An apparatus according to

claim 19

, wherein the processor performs optical character recognition on the text data only in a case that a size of text data in the block is greater than the preset size threshold.

23. An apparatus according to

claim 19

, wherein the processor performs optical character recognition on the text data only in a case that a size of the text data in the block is less than the preset size threshold.

24. An apparatus according to

claim 19

, wherein the size threshold is based on an average size of pixel data in the analyzed document page.