Image processing apparatus, image processing method and image processing program

Patent metadata

Field	Value
Publication number	US-9477885-B2
Application number	US-201414562888-A
Country	US
Kind code	B2
Filing date	Dec 8, 2014
Priority date	Jul 25, 2014
Publication date	Oct 25, 2016
Grant date	Oct 25, 2016

Abstract

An image processing apparatus according to one embodiment includes a first extraction unit, a second extraction unit, and a specifying unit. The first extraction unit performs stroke width transform on an image and thereby extracts a SWT region from the image. The second extraction unit performs clustering based on pixel values on the image and thereby extracts a single-color region from the image. The specifying unit specifies a pixel group included in a candidate text region based at least on the single-color region when a ratio of the number of pixels in an overlap part between the SWT region and the single-color region to the number of pixels in the single-color region is equal to or more than a first reference value, or more than the first reference value.

First claim

What is claimed is:

1. An image processing apparatus comprising:
at least one memory operable to store computer program code;
at least one processor operable to access said at least one memory and operate as instructed by said program code:
first extraction code configured to cause at least one of said at least one processor to perform stroke width transform (SWT) on an image and thereby extract a SWT region from the image, the SWT region being a region having a continuous edge and a stroke width within a set range;
second extraction code configured to cause at least one of said at least one processor to perform clustering based on pixel values on the image and thereby extract a single-color region from the image, the single-color region being a region composed of a plurality of pixels having pixel values within a set range and present continuously; and
specifying code configured to cause at least one of said at least one processor to specify a pixel group included in a candidate text region based at least on the single-color region when a ratio of the number of pixels in an overlap part between the SWT region and the single-color region to the number of pixels in the single-color region is equal to or more than a first reference value, or more than the first reference value.

2. The image processing apparatus according to claim 1 , wherein
the specifying code does not specify a candidate text region from the SWT region and the single-color region when the ratio is less than a second reference value.

3. The image processing apparatus according to claim 2 , wherein
the first reference value and the second reference value are the same, and
when the second extraction code extracts a plurality of single-color regions, the specifying code selects the single-color region having the maximum number of pixels in the overlap part with the SWT region, and when a ratio of the number of pixels in the overlap part between the SWT region and the selected single-color region to the number of pixels in the selected single-color region is equal to or more than the first reference value, the specifying code specifies a pixel group included in the candidate text region based on the SWT region and the selected single-color region, and when the ratio is less than the first reference value, the specifying code does not specify the candidate text region.

4. The image processing apparatus according to claim 1 , wherein
the second extraction code sets a part of the image as a clustering target region based on the SWT region extracted by the first extraction code, and extracts the single-color region from the clustering target region.

5. The image processing apparatus according to claim 1 , wherein
the specifying code specifies a pixel group included in the candidate text region by complementing a missing part of the SWT region with pixels of the single-color region.

6. The image processing apparatus according to claim 5 , wherein
the specifying code specifies a logical sum of the SWT region and the single-color region as a pixel group included in the candidate text region.

7. The image processing apparatus according to claim 5 , wherein
the specifying code complements the missing part without using pixels of the single-color region outside an edge of the SWT region, by using other pixels of the single-color region.

8. The image processing apparatus according to claim 7 , wherein
the first extraction code performs the stroke width transform using a first edge threshold, and
the specifying code performs the stroke width transform using a second edge threshold lower than the first edge threshold on a part of the single-color region not overlapping the SWT region and thereby searches for an additional edge, and enlarges the SWT region using the additional edge, and complements a missing part of the enlarged SWT region without using pixels of the single-color region outside an edge of the enlarged SWT region, by using other pixels of the single-color region.

9. The image processing apparatus according to claim 1 , wherein
the second extraction code extracts the single-color region by performing color clustering.

10. An image processing method performed by an image processing apparatus including at least one processor, comprising:
performing stroke width transform on an image and thereby extracting a SWT region from the image, the SWT region being a region having a continuous edge and a stroke width within a set range;
performing clustering based on pixel values on the image and thereby extracting a single-color region from the image, the single-color region being a region composed of a plurality of pixels having pixel values within a set range and present continuously; and
specifying a pixel group included in a candidate text region based at least on the single-color region when a ratio of the number of pixels in an overlap part between the SWT region and the single-color region to the number of pixels in the single-color region is equal to or more than a first reference value, or more than the first reference value.

11. A non-transitory computer readable medium storing an image processing program causing a computer comprising at least one processor operable to access said non-transitory computer readable medium to operate as instructed by said image processing program to implement:
first extraction code configured to cause at least one of said at least one processor to perform stroke width transform on an image and thereby extract a SWT region from the image, the SWT region being a region having a continuous edge and a stroke width within a set range;
second extraction code configured to cause at least one of said at least one processor to perform clustering based on pixel values on the image and thereby extract a single-color region from the image, the single-color region being a region composed of a plurality of pixels having pixel values within a set range and present continuously; and
specifying code configured to cause at least one of said at least one processor to specify a pixel group included in a candidate text region based at least on the single-color region when a ratio of the number of pixels in an overlap part between the SWT region and the single-color region to the number of pixels in the single-color region is equal to or more than a first reference value, or more than the first reference value.

Assignees

• Rakuten Inc

Inventors

• Chiba Naoki

Classifications

• G06V10/44

  Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components · CPC title

• G06V10/267

  by performing operations on regions, e.g. growing, shrinking or watersheds · CPC title

• G06K9/00416

  Physics · mapped topic

• G06K9/00456 Primary

  Physics · mapped topic

• G06K9/4604

  Physics · mapped topic