Image processing method, image processing apparatus, image reading apparatus, image forming apparatus, and recording medium

• US 8,144,994 B2
• Filed: 11/09/2007
• Issued: 03/27/2012
• Est. Priority Date: 11/13/2006
• Status: Active Grant

• Current Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Original Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Inventors: Konishi, Yohsuke
• Primary Examiner(s): Desire, Gregory M
• Application Number:
  US11/938,107
• Publication Number:
  US 20080187249A1
• Time in Patent Office: 1,600 Days
• Field of Search: 382/209, 382/306, 707/1, 707/100
• US Class Current: 382/209
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1444 Selective acquisition, locating or processing of specific regions, e.g. highlighted text, fiducial marks or predetermined fields
• CPC Class Codes: G06V 30/18076 by analysing connectivity, e.g. edge linking, connected component analysis or slices

Abstract

A plurality of type identifiers are stored that contains one or a plurality of image identifiers each for identifying each of a plurality of reference images and thereby identifies a type of a document. Then, it is determined whether each of a plurality of obtained document images is similar to a reference image. When a document image is determined as being similar to a reference image, an image identifier that identifies the reference image is selected from among a plurality of image identifiers. Then, a type identifier is identified that contains the selected image identifier. Then, document images each similar to a reference image are classified for each identified type identifier.

Claims

1. An image processing method performed by an image processing apparatus, comprising:

storing, to a storage section, a plurality of type identifiers each of which contains one or a plurality of image identifiers each for identifying each of a plurality of reference images and thereby identifies a type of a document;

generating, by the image processing apparatus, a hash table indicative of a relationship between hash values and the plurality of image identifiers for each of the plurality of reference images;

determining, by a controller, whether each of a plurality of obtained document images is similar to a reference image based on the hash values;

when a document image is determined as being similar to the reference image, selecting, by the controller, an image identifier that identifies said reference image, from among the plurality of image identifiers;

identifying, by the controller, a type identifier that contains the selected image identifier;

classifying, by the controller, document images each similar to the reference image, for each identified type identifier, wherein document images in the number of image identifiers contained in a type identifier are classified for each type identifier;

at each time when a document image is determined as being similar to a reference image, the controller counting up the number of document images determined as being similar;

determining, by the controller, whether the counted number of document images is equal to the number of image identifiers contained in the type identifier;

when said number of document images is determined as being equal to the number of image identifiers, the controller determining that said document image is the last document image to be classified to said type identifier, and

outputting the classified document images to an image output apparatus.

2. The image processing method according to claim 1, further comprising:

controlling output processing for the document images is performed separately for each type identifier.

3. An image processing method performed by an image processing apparatus, comprising:

storing, to a storing section, a plurality of type identifiers each of which contains one or a plurality of image identifiers each for identifying each of a plurality of reference images and thereby identifies a type of a document;

generating, by the image processing apparatus, a hash table indicative of a relationship between hash values and the plurality of image identifiers for each of the plurality of reference images;

determining, by a controller, whether each of a plurality of obtained document images is similar to a reference image based on the hash values;

when a document image is determined as being similar to the reference image, the controller selecting an image identifier that identifies said reference image, from among the plurality of image identifiers;

identifying, by the controller, a type identifier that contains the selected image identifier,

classifying, by the controller, document images each similar to the reference image, for each identified type identifier, wherein document images in the number of image identifiers contained in a type identifier are classified for each type identifier;

at each time when a document image is determined as being similar to a reference image, the controller, counting up the number of document images determined as being similar;

storing, to the storage section, the counted number of document images, as associating with the type identifier;

determining, by the controller, whether the number of stored document images is equal to to the number of image identifiers contained in said type identifier;

when said number of document images is determined as being equal to the number of image identifiers, the controller determining that said document image is the last document image to be classified to said type identifier, and

outputting the classified document images to an image output apparatus.

4. An image processing method performed by an image processing apparatus, comprising:

storing, to a storage section, a plurality of type identifiers each of which contains one or a plurality of image identifiers each for identifying each of a plurality of reference images and thereby identifies a type of a document;

generating, by the image processing apparatus, a hash table indicative of a relationship between hash values and the plurality of image identifiers for each of the plurality of reference images;

determining, by a controller, whether each of a plurality of obtained document images is similar to a reference image based on the hash values;

when a document image is determined as being similar to the reference image, the controller selecting an image identifier that identifies said reference image, from among the plurality of image identifiers;

identifying, by the controller, a type identifier that contains the selected image identifier,

classifying, by the controller, document images each similar to the reference image, for each identified type identifier,

storing, to the storage section, features and image identifiers of the reference images as being associated with each other;

extracting, by the controller, features of a document image;

identifying, by the controller, an image identifier on the basis of the extracted features and the stored features of a reference image;

determining, by the controller, that said document image is similar to a reference image identified by said image identifier; and

outputting the classified document images to an image output apparatus.

5. An image processing method performed by an image processing apparatus, comprising:

storing, to a storage section, a plurality of type identifiers each of which contains one or a plurality of image identifiers each for identifying each of a plurality of reference images and thereby identifies a type of a document;

generating, by the image processing apparatus, a hash table indicative of a relationship between hash values and the plurality of image identifiers for each of the plurality of reference images;

determining, by a controller, whether each of a plurality of obtained document images is similar to a reference image based on the hash values;

when a document image is determined as being similar to the reference image, the controller selecting an image identifier that identifies said reference image, from among the plurality of image identifiers;

identifying, by the controller, a type identifier that contains the selected image identifier;

classifying, by the controller, document images each similar to the reference image, for each identified type identifier,

receiving, by the controller, an instruction for storing a reference image;

setting up, by the controller, an image identifier that identifies one or a plurality of the reference images having been inputted;

setting up, by the controller, a type identifier that contains the set-up image identifier;

extracting, by the controller, features of said reference image;

storing, in the storage section, the type identifier and the image identifier having been set up as well as the extracted features, as associating with each other, and

outputting the classified document images to an image output apparatus.

6. An image processing apparatus comprising:

a storage section for storing a plurality of type identifiers each of which contains one or a plurality of image identifiers each for identifying each of a plurality of reference images and thereby identifies a type of a document; and

a hash table indicative of a relationship between hash values and the plurality of image identifiers for each of the plurality of reference images;

a controller configured to perform operations of;

determining whether each of a plurality of obtained document images is similar to a reference image based on the hash values;

when a document image is determined as being similar to the reference image, selecting an image identifier that identifies said reference image, from among the plurality of image identifiers;

identifying a type identifier that contains the selected image identifier;

classifying document images each similar to the reference image, for each identified type identifier, wherein document images in the number of image identifiers contained in a type identifier are classified for each type identifier;

at each time when a document image is determined as being similar to a reference image, counting up the number of document images determined as being similar;

determining whether the counted number of document images is equal to the number of image identifiers contained in the type identifier; and

when said number of document images is determined as being equal to the number of image identifiers, determining that said document image is the last document image to be classified to said type identifier.

7. The image processing apparatus according to claim 6, wherein said controller is further configured to control output processing for the document images separately for each type identifier.

8. An image reading apparatus comprising:

an image reading section for reading an image; and

an image processing apparatus according to claim 6;

wherein

the image read by said image reading apparatus is processed by said image processing apparatus.

9. An image forming apparatus comprising:

an image processing apparatus according to claim 6; and

an image forming section for forming an output image on the basis of the image processed by the image processing apparatus.

10. An image processing apparatus comprising:

a storage section for storing a plurality of type identifiers each of which contains one or a plurality of image identifiers each for identifying each of a plurality of reference images and thereby identifies a type of a document; and

a hash table indicative of a relationship between hash values and the plurality of image identifiers for each of the plurality of reference images,

a controller configured to perform capable of performing operations of;

determining whether each of a plurality of obtained document images is similar to a reference image based on the hash values;

when a document image is determined as being similar to the reference a reference image, selecting an image identifier that identifies said reference image, from among the plurality a plurality of image identifiers;

identifying a type identifier that contains the selected image identifier; and

classifying document images each similar to the reference a reference image, for each identified type identifier, wherein document images in the number of image identifiers contained in a type identifier are classified for each type identifier,

wherein said controller is further configured to perform operations of;

at each time when a document image is determined as being similar to a reference image, counting up the number of document images determined as being similar;

storing the counted number of document images, as associating with the type identifier;

determining whether the number of stored document images is equal to the number of image identifiers contained in said type identifier; and

when said number of document images is determined as being equal to the number of image identifiers, determining that said document image is the last document image to be classified to said type identifier.

11. An image processing apparatus comprising:

a storage section for storing a plurality of type identifiers each of which contains one or a plurality of image identifiers each for identifying each of a plurality of reference images and thereby identifies a type of a document; and

a hash table indicative of a relationship between hash values and the plurality of image identifiers for each of the plurality of reference images;

a controller configured to perform capable of performing operations of;

determining whether each of a plurality of obtained document images is similar to a reference image based on the hash values;

when a document image is determined as being similar to the reference a reference image, selecting an image identifier that identifies said reference image, from among the plurality a plurality of image identifiers;

identifying a type identifier that contains the selected image identifier; and

classifying document images each similar to the reference a reference image, for each identified type identifier, wherein

features and image identifiers of the reference images are stored as being associated with each other in the storage section; and

said controller is further configured to perform operations of;

extracting features of a document image;

identifying an image identifier on the basis of the extracted features and the stored features of a reference image; and

determining that said document image is similar to a reference image identified by said image identifier.

12. An image processing apparatus comprising:

a storage section for storing a plurality of type identifiers each of which contains one or a plurality of image identifiers each for identifying each of a plurality of reference images and thereby identifies a type of a document; and

a hash table indicative of a relationship between hash values and the plurality of image identifiers for each of the plurality of reference images;

a controller configured to perform capable of performing operations of;

determining whether each of a plurality of obtained document images is similar to a reference image based on the hash values;

when a document image is determined as being similar to the reference a reference image, selecting an image identifier that identifies said reference image, from among the plurality a plurality of image identifiers;

identifying a type identifier that contains the selected image identifier; and

classifying document images each similar to the reference a reference image, for each identified type identifier,

wherein said controller is further configured to perform capable of performing operations of;

receiving an instruction for storing a reference image;

when the instruction is received, setting up an image identifier that identifies one or a plurality of the reference images having been inputted;

setting up a type identifier that contains the set-up image identifier;

extracting features of said reference image; and

storing into the storage section the type identifier and the image identifier having been set up as well as the extracted features, as associating with each other.

13. A non-transitory computer-readable medium storing thereon a computer program executable to perform the steps of:

determining whether each of a plurality of inputted document images is similar to any one of reference images based on a hash table indicative of a relationship between hash values and a plurality of image identifiers for each of the reference images;

when the document image is determined as being similar to a reference image, selecting an image identifier that identifies said reference image from among a plurality of image identifiers each for identifying the reference image;

identifying a type identifier that contains the selected image identifier, from among a plurality of type identifiers that contains one or the plurality of image identifiers and identifies a type of a document; and

classifying document images each similar to the reference image, for each identified type identifier, wherein document images in the number of image identifiers contained in a type identifier are classified for each type identifier;

at each time when a document image is determined as being similar to a reference image, counting up the number of document images determined as being similar,

determining whether the counted number of document images is equal to the number of image identifiers contained in the type identifier; and

when said number of document images is determined as being equal to the number of image identifiers, determining that said document image is the last document image to be classified to said type identifier.