Information processing apparatus for obtaining a degree of similarity between elements

Patent metadata

Field	Value
Publication number	US-9818028-B2
Application number	US-201615016388-A
Country	US
Kind code	B2
Filing date	Feb 5, 2016
Priority date	Sep 30, 2015
Publication date	Nov 14, 2017
Grant date	Nov 14, 2017

Abstract

An information processing apparatus includes a first acquiring unit, an addition unit, a second acquiring unit, and an extraction unit. The first acquiring unit acquires a first group of elements included in a first image generated by reading a document. The addition unit generates multiple second images by adding noises that differ from each other to the first image. The second acquiring unit acquires second groups of elements included in the respective multiple second images. The extraction unit extracts an element representing characteristics of the document from the first group of elements in accordance with the degrees of similarity between elements included in the first group of elements and elements included in the multiple second groups of elements.

First claim

What is claimed is:

1. An information processing apparatus comprising:
a first acquiring unit that acquires a first group of elements included in a first image generated by reading a document;
an addition unit that generates a plurality of second images by adding noises that differ from each other to the first image;
a second acquiring unit that acquires second groups of elements included in the respective plurality of second images;
a comparing unit that compares the first group of elements from the first image with the second group of elements from each of the plurality of second images to obtain a degree of similarity; and
an extraction unit that extracts an element representing characteristics of the document from the first group of elements in accordance with the degrees of similarity between elements included in the first group of elements and elements included in the plurality of second groups of elements.

2. The information processing apparatus according to claim 1 ,
wherein the addition unit generates each of the plurality of second images by adding, to the first image, a certain noise that is a predetermined type of noise among the noises so that certain noises included in the plurality of respective second images differ from each other.

3. The information processing apparatus according to claim 1 ,
wherein the addition unit generates each of the plurality of second images by adding, to the first image, certain noises that are predetermined types of noise among the noises so that certain noises included in the plurality of respective second images differ from each other.

4. The information processing apparatus according to claim 1 , wherein the extraction unit extracts, as an element representing characteristics of the document, an element whose degree of similarity reaches a threshold.

5. The information processing apparatus according to claim 2 , wherein the extraction unit extracts, as an element representing characteristics of the document, an element whose degree of similarity reaches a threshold.

6. The information processing apparatus according to claim 3 , wherein the extraction unit extracts, as an element representing characteristics of the document, an element whose degree of similarity reaches a threshold.

7. The information processing apparatus according to claim 1 , wherein the extraction unit extracts, as an element representing characteristics of the document, an element whose degree of similarity is the highest.

8. The information processing apparatus according to claim 2 , wherein the extraction unit extracts, as an element representing characteristics of the document, an element whose degree of similarity is the highest.

9. The information processing apparatus according to claim 3 , wherein the extraction unit extracts, as an element representing characteristics of the document, an element whose degree of similarity is the highest.

10. The information processing apparatus according to claim 4 , wherein the extraction unit extracts, as an element representing characteristics of the document, an element whose degree of similarity is the highest.

11. The information processing apparatus according to claim 5 , wherein the extraction unit extracts, as an element representing characteristics of the document, an element whose degree of similarity is the highest.

12. The information processing apparatus according to claim 6 , wherein the extraction unit extracts, as an element representing characteristics of the document, an element whose degree of similarity is the highest.

13. An information processing method comprising:
acquiring a first group of elements included in a first image generated by reading a document;
generating a plurality of second images by adding noises that differ from each other to the first image;
acquiring second groups of elements included in the respective plurality of second images;
comparing the first group of elements from the first image with the second group of elements from each of the plurality of second images to obtain a degree of similarity; and
extracting an element representing characteristics of the document from the first group of elements in accordance with the degrees of similarity between elements included in the first group of elements and elements included in the plurality of second groups of elements.

14. A non-transitory computer readable medium storing a program causing a computer to execute a process, the process comprising:
acquiring a first group of elements included in a first image generated by reading a document;
generating a plurality of second images by adding noises that differ from each other to the first image;
acquiring second groups of elements included in the respective plurality of second images;
comparing the first group of elements from the first image with the second group of elements from each of the plurality of second images to obtain a degree of similarity; and
extracting an element representing characteristics of the document from the first group of elements in accordance with the degrees of similarity between elements included in the first group of elements and elements included in the plurality of second groups of elements.

Assignees

• Fuji Xerox Co Ltd

Inventors

• Shigeeda Nobuyuki
• Kashima Yozo

Classifications

• G06V30/1914 Primary

  Determining representative reference patterns, e.g. averaging or distorting patterns; Generating dictionaries, e.g. user dictionaries · CPC title

• G06V30/416

  Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors · CPC title

• G06F18/28

  Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries · CPC title

• G06V10/22

  by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition · CPC title

• G06V30/40 Primary

  Document-oriented image-based pattern recognition · CPC title