Character extracting apparatus, method, and program

• US 8,036,463 B2
• Filed: 09/13/2007
• Issued: 10/11/2011
• Est. Priority Date: 09/13/2006
• Status: Expired due to Fees

• Current Assignee: Keyence Corporation (Keyence)
• Original Assignee: Keyence Corporation (Keyence)
• Inventors: Shimodaira, Masato
• Primary Examiner(s): CARTER, AARON W
• Application Number:
  US11/898,628
• Publication Number:
  US 20080063273A1
• Time in Patent Office: 1,489 Days
• Field of Search: 382168-189
• US Class Current: 382/176
• CPC Class Codes: G06F 18/40 Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor
• CPC Class Codes: G06V 10/945 User interactive design; Environments; Toolboxes
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/158 using character size, text spacings or pitch estimation

Abstract

The present invention provides a technique of accurately extracting areas of characters included in a captured image. A character extracting device of the present invention extracts each character in an image with compensated pixel values. In more detail, the character extracting device integrates pixel values at each coordinate position in the image along a character extracting direction. Then, the character extracting device predicts the background area in the image based on the integrated pixel value. The compensated pixel values are compensated based on integrated pixel values at the predicted background area from integrated pixel values at each coordinate position.

Claims

1. An apparatus for extracting each of a plurality of characters from a character string having the plurality of characters arranged in a first direction and included in an image, comprising:

an integrating device integrating a plurality of pixel values along a second direction orthogonal to the first direction at each of a plurality of coordinate positions along the first direction over the image;

a setting device setting a section having a predetermined width at each of a plurality of different positions by shifting the section along the first direction over the image;

a first extracting device extracting a first point where a pixel value integrated by the integrating device is the minimum value in each of the sections set by the setting device;

a block setting device setting a plurality of blocks corresponding to sequences of the first points, wherein each distance between the adjacent first points in the sequence is not in excess of a predetermined threshold value;

a second extracting device extracting a second point where a pixel value integrated by the integrating device is the minimum value in each of the plurality of blocks of first points, extracted by the first extracting device, in sequence along the first direction;

an interpolating device calculating a base value at each of the plurality of coordinate positions along the first direction over the image from an interpolation based on the pixel values integrated by the integrating device at the second points extracted by the second extracting device;

a compensating device subtracting the base value from the pixel value integrated by the integrating device as a compensated value at each of the plurality of coordinate positions along the first direction over the image;

a recognition device recognizing an area having the compensated value compensated by the compensating device in excess of a predetermined threshold value as a character area; and

a display device including a character string display part for displaying a character string having a plurality of characters and a character area display part surrounding each character included in the character area recognized by the recognition device.

2. The character extracting apparatus according to claim 1, wherein the predetermined width of the section set by the setting device is set to be substantially the same as a width of the character to be extracted.

3. The character extracting apparatus according to claim 1, wherein the predetermined width of the section set by the setting device is set to 110% to 120% of a width of the character to be extracted.

4. The character extracting apparatus according to claim 1, wherein the predetermined width of the section set by the setting device is set based on a predetermined height of the character string and a preset ratio of height to width of the character to be extracted.

5. The character extracting apparatus according to claim 1, wherein

the display device includes a rectangular-shaped window;

and further comprising;

a waveform display part for displaying a waveform formed by the pixel values integrated by the integrating device at each of a plurality of coordinate positions along the first direction over the image; and

wherein the display device displaying the plurality of characters displayed on the character string display part and for displaying the waveform displayed on the waveform display part at a position where each part of the waveform is disposed at each location corresponding to each character displayed on the character string display part to indicate a mutual positioning relationship between the character and the waveform on the display device.

6. The character extracting apparatus according to claim 1, further comprising:

an adjusting device manually adjusting the width of the section, and

a waveform display part for displaying a waveform formed by the compensated values compensated by the compensating device at each coordinate position along the first direction over the image.

7. The character extracting apparatus according to claim 1, further comprising:

an adjusting device manually adjusting the width of the section, and

a waveform display part for displaying a waveform formed by the base values interpolated by the interpolating device at each coordinate position along the first direction over the image.

8. The character extracting apparatus according to claim 1, wherein

the display device

includes a rectangular-shaped window;

and further comprising;

a waveform display part for displaying a waveform formed by the pixel values integrated by the integrating device at each of coordinate position along the first direction over the image and the threshold value overlapping with the waveform; and

wherein the display device displaying the plurality of characters displayed on the character string display part and for displaying the waveform displayed on the waveform display part at a position where each part of the waveform is disposed at each location corresponding to each of the plurality of characters displayed on the character string display part to indicate a mutual positioning relationship between the character and the waveform on the display device.

9. An apparatus for extracting each of a plurality of characters from a character string having the plurality of characters arranged in a first direction and included in an image, comprising:

an integrating device integrating a plurality of pixel values along a second direction orthogonal to the first direction at each of a plurality of coordinate positions along the first direction over the image;

a first extracting device extracting a first point where a pixel value integrated by the integrating device is a local minimum value from the plurality of coordinate positions by shifting the section along the first direction over the image;

a blocking setting device setting a plurality of blocks corresponding to sequences of the first points, wherein each distance between the neighbor first points in the sequence is not in excess of a predetermined threshold value;

a setting device setting a section having a predetermined width corresponding to each of the plurality of blocks of first points extracted by the first extracting device;

a second extracting device extracting the first point as a second point where a pixel value integrated by the integrating device is a minimum value in each of the sections corresponding to the first point;

an interpolating device calculating a base value at each of the plurality of coordinate positions along the first direction over the image from an interpolation based on the pixel values integrated by the integrating device at the second points extracted by the second extracting device;

a compensating device compensating the pixel value integrated by the integrating device as a compensated value at each coordinate position along the first direction over the image based on the base value; and

a recognition device recognizing an area having the compensated value compensated by the compensating device in excess of a predetermined threshold value as a character area; and

a display device including a character string display part for displaying a character string having a plurality of characters and a character area display part surrounding each character included in the character area recognized by the recognition device.

10. The character extracting apparatus according to claim 9, wherein the predetermined width of the section set by the setting device is set to be substantially the same as a width of the character to be extracted.

11. The character extracting apparatus according to claim 9, wherein the predetermined width of the section set by the setting device is set to 110% to 120% of a width of the character to be extracted.

12. The character extracting apparatus according to claim 9, wherein the predetermined width of the section set by the setting device is set based on a predetermined height of the character string and a preset ratio of height to width of the character to be extracted.

13. The character extracting apparatus according to claim 9, wherein

the display device

includes a rectangular-shaped window;

and further comprising;

a waveform display part for displaying a waveform formed by the pixel values integrated by the integrating device at each of a plurality of coordinate positions along the first direction over the image; and

the display device displaying each character displayed on the character string display part and a part of the displayed waveform on the waveform display part corresponding to each character displayed on the character string display part with a mutual positioning relationship on the display device.

14. The character extracting apparatus according to claim 9, further comprising:

an adjusting device manually adjusting the width of the section, and

a waveform display part for displaying a waveform formed by the compensated values compensated by the compensating device at each coordinate position along the first direction over the image.

15. The character extracting apparatus according to claim 9, further comprising:

an adjusting device manually adjusting the width of the section, and

a waveform display part for displaying a waveform formed by the base values interpolated by the interpolating device at each coordinate position along the first direction over the image.

16. The character extracting apparatus according to claim 9, wherein

the display device includes a rectangular-shaped window;

and further comprising;

a waveform display part for displaying a waveform formed by the pixel values integrated by the integrating device at each coordinate position along the first direction over the image and the threshold value overlapping with the waveform; and

the display device displaying each character displayed on the character string display part and a part of the displayed waveform on the waveform display part corresponding to each character displayed on the character string display part with a mutual positioning relationship on the display device.

17. The character extracting apparatus according to claim 9, further comprising:

an evaluating device evaluating an extraordinary point based on the pixel values integrated by the integrating device at each of the plurality of coordinate positions along the first direction over the image and the pixel values integrated by the integrating device at neighbors of each of the plurality of coordinate positions along the first direction over the image, and

an excluding device excluding the extraordinary point evaluated by the evaluating device from points utilized by the interpolating device.

18. A method for extracting each of a plurality of characters from a character string having the plurality of characters arranged in a first direction and included in an image, comprising the steps of:

integrating a plurality of pixel values along a second direction orthogonal to the first direction at each of a plurality of coordinate positions along the first direction over the image;

setting a section having a predetermined width at each of a plurality of different positions by shifting the section along the first direction over the image;

setting a plurality of blocks corresponding to sequences of the first points, wherein each distance between the neighbor first points in the sequence is not in excess of a predetermined threshold value;

extracting a first point where a pixel value integrated by the integrating step is a minimum value in each of the sections set by the setting step;

extracting a second point where a pixel value integrated by the integrating step is a minimum value in each of the plurality of blocks of first points, extracted by the first extracting step, in sequence along the first direction;

calculating a base value at each of the plurality of coordinate positions along the first direction over the image from an interpolation based on the pixel values integrated by the integrating step at the second points extracted by the second extracting step;

subtracting the base value from the pixel value integrated by the integrating step as a compensated value at each coordinate position along the first direction over the image; and

recognizing an area having the compensated value compensated by the compensating step in excess of a predetermined threshold value as a character area.

19. A non-transitory computer readable medium including a program for extracting each of a plurality of characters from a character string having the plurality of characters arranged in a first direction and included in an image, the program including:

an integrating device for integrating a plurality of pixel values along a second direction orthogonal to the first direction at each of a plurality of coordinate positions by shifting the section along the first direction over the image;

a setting device setting a section having a predetermined width at each of a plurality of different positions along the first direction over the image;

a first extracting device extracting a first point where a pixel value integrated by the integrating device is a minimum value in each of the sections set by the setting device;

a blocking setting device setting a plurality of blocks corresponding to sequences of the first points, wherein each distance between the neighbor first points in the sequence is not in excess of a predetermined threshold value;

a second extracting device extracting a second point where a pixel value integrated by the integrating device is a minimum value in each of the plurality of blocks of first points, extracted by the first extracting device, in sequence along the first direction;

an interpolating device calculating a base value at each of the plurality of coordinate positions along the first direction over the image from an interpolation based on the pixel values integrated by the integrating device at the second points extracted by the second extracting device;

a compensating device subtracting the base value from the pixel value integrated by the integrating device as a compensated value at each of the plurality of coordinate positions along the first direction over the image; and

a recognition device recognizing an area having the compensated value compensated by the compensating device in excess of a predetermined threshold value as a character area.