Image processing apparatus, method, and storage medium

US9807280B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-9807280-B2
Application numberUS-201414571833-A
CountryUS
Kind codeB2
Filing dateDec 16, 2014
Priority dateDec 19, 2013
Publication dateOct 31, 2017
Grant dateOct 31, 2017

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

A binary image of an input image is generated, and a character region within the binary image and a region surrounding each character are acquired as character segmentation rectangle information. A thinning process is executed on a region within the binary image which is identified based on the character segmentation rectangle information to acquire a thinned image. An edge detected image of the region identified based on the character segmentation rectangle information is acquired. Whether each character identified based on the character segmentation rectangle information is a character to be separated from a background by the binarization process or not is determined based on a result of a logical AND of the thinned image and the edge detected image.

First claim

Opening claim text (preview).

What is claimed is: 1. An image processing apparatus comprising: a binarizing unit configured to generate a binary image by executing a binarization process on an input image; a first determining unit configured to determine a character region within the binary image; a character segmenting unit configured to acquire a region surrounding a character contained in the character region as character segmentation rectangle information; a thinning unit configured to acquire a thinned image by executing a thinning process on a region within the binary image, the region being identified based on the character segmentation rectangle information; an edge detecting unit configured to acquire an edge detected image by executing an edge detection process on the region identified based on the character segmentation rectangle information; a logical operation unit configured to take a logical AND of the thinned image and the edge detected image; a second determining unit configured to determine, based on a result of the logical AND performed by the logical operation unit, whether the character identified based on the character segmentation rectangle information is a character to be separated from a background by the binarization process or not; and an image processing unit configured to perform a predetermined image process for a character on the region being identified based on the character segmentation rectangle information based on determination of the second determining unit that the character identified based on the character segmentation rectangle information is a character to be separated from a background by the binarization process, wherein the image processing unit does not perform the predetermined image process for a character on the region being identified based on the character segmentation rectangle information based on determination of the second determining unit that the character identified based on the character segmentation rectangle information is not a character to be separated from a background by the binarization process, wherein the units are implemented by one or more processors, a circuitry, or a combination thereof. 2. The image processing apparatus according to claim 1 , further comprising: a first compression unit configured to execute a binary reversible compression process on a character determined by the second determining unit as a character to be separated from a background by the binarization process; and a second compression unit configured to execute a multi-valued non-reversible compression on a character determined by the second determining unit as a character not to be separated from the background by the binarization process, wherein the first compression unit and the second compression unit are implemented by one or more processors, a circuitry or a combination thereof. 3. The image processing apparatus according to claim 2 , further comprising a color extracting unit configured to extract a character color of the character determined by the second determining unit as a character to be separated from the background by the binarization process, wherein the color extracting unit is implemented by one or more processors, a circuitry or a combination thereof. 4. The image processing apparatus according to claim 1 , further comprising a reducing unit configured to acquire a reduced multi-valued image by reducing the input image, wherein the edge detecting unit acquires the edge detected image by executing an edge detection process on the region identified based on the character segmentation rectangle information in the reduced multi-valued image, wherein the reducing unit is implemented by one or more processors, a circuitry or a combination thereof. 5. The image processing apparatus according to claim 1 , wherein the edge detecting unit acquires the edge detected image by executing an edge detection process on a region identified based on the character segmentation rectangle information in the input image. 6. The image processing apparatus according to claim 1 , wherein the logical operation unit generates a logical AND image by taking a logical AND of the thinned image and the edge detected image; and the second determining unit determines whether a character identified based on the character segmentation rectangle information is a character to be separated from a background by the binarization process or not based on a number of black pixels contained in the logical AND image generated by the logical operation unit. 7. The image processing apparatus according to claim 1 , further comprising a re-binarizing unit configured to execute a re-binarization process on a character determined by the second determining unit as a character not to be separated from a background by the binarization process. 8. The image processing apparatus according to claim 1 , wherein the thinning unit changes an amount of reduction of the thinning process in accordance with a size of a region identified based on the character segmentation rectangle information. 9. An image processing method executed by at least one processor, the image processing method comprising: generating a binary image by executing a binarization process on an input image; determining a character region within the binary image; acquiring a region surrounding a character contained in the character region as character segmentation rectangle information; acquiring a thinned image by executing a thinning process on a region within the binary image, the region being identified based on the character segmentation rectangle information; acquiring an edge detected image by executing an edge detection process on the region identified based on the character segmentation rectangle information; taking a logical AND of the thinned image and the edge detected image; determining, based on a result of the logical AND performed by the taking, whether the character identified based on the character segmentation rectangle information is a character to be separated from a background by the binarization process or not; and performing a predetermined image process for a character on the region being identified based on the character segmentation rectangle information based on determination of the determining that the character identified based on the character segmentation rectangle information is a character to be separated from a background by the binarization process, wherein the performing does not perform the predetermined image process for a character on the region being identified based on the character segmentation rectangle information based on determination of the determining that the character identified based on the character segmentation rectangle information is not a character to be separated from a background by the binarization process.

Assignees

Inventors

Classifications

  • Smoothing or thinning of the pattern; Skeletonisation · CPC title

  • Cutting or merging image elements, e.g. region growing, watershed or clustering-based techniques · CPC title

  • Character recognition · CPC title

  • H04N1/403Primary

    Discrimination between the two tones in the picture signal of a two-tone original · CPC title

  • from scanner, fax or copier · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US9807280B2 cover?
A binary image of an input image is generated, and a character region within the binary image and a region surrounding each character are acquired as character segmentation rectangle information. A thinning process is executed on a region within the binary image which is identified based on the character segmentation rectangle information to acquire a thinned image. An edge detected image of th…
Who is the assignee on this patent?
Canon Kk
What technology area does this patent fall under?
Primary CPC classification H04N1/403. Mapped technology areas include Electricity.
When was this patent published?
Publication date Tue Oct 31 2017 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 8 related publications on this page (citations in our corpus or others sharing the same primary CPC).