Method and apparatus for capturing text images

• US 20030086615A1
• Filed: 11/02/2001
• Published: 05/08/2003
• Est. Priority Date: 11/02/2001
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Dance, Christopher R., Taylor, Stuart A., Newman, William M., Ruddock, Guy J.
• Granted Patent: US 6,922,487 B2
• Time in Patent Office: Days
• US Class Current: 382/200
• CPC Class Codes: G06V 10/20 Image preprocessing
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/133 Evaluation of quality of the acquired characters
• CPC Class Codes: G06V 30/1478 of characters or characters lines
• CPC Class Codes: G06V 30/158 using character size, text spacings or pitch estimation
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables

Abstract

A device and method are described for capturing an image of a document using a digital camera. The invention includes a resolution analyzer for analyzing the resolution of text characters in the image, to assess whether the resolution is suitable for OCR. In one aspect, if the resolution is too small or too large, an indicator is generated to guide the user as to the corrective movement of the camera to improve the resolution for OCR. In a second aspect, an electronic zoom control is controlled to alter the magnification of the captured image, to correct the resolution. In a third aspect, a method is described for analyzing the image to determine the resolution according to the height of text characters in the image. The method includes analyzing the run lengths of pixels in the image to identify a predominant length corresponding to the average character height (in pixels).

Claims

1. An apparatus for capturing an image of a document, comprising:

an image capture device for capturing a digital image of a document in a field of view of the image capture device;

a resolution analyzer for analyzing the image to determine an approximate resolution of text characters in the image;

a comparison device responsive to the determined resolution of text characters, for comparing the determined resolution with predetermined data representing a maximum desired image resolution and a minimum desired image resolution;

an output device for generating a first output to indicate to the user a condition that the resolution is less than the desired minimum resolution, and a second output to indicate to the user a condition that the resolution is greater than the desired maximum.

2. An apparatus according to claim 1, wherein the first and second outputs are different visual outputs.

3. An apparatus according to claim 2, wherein the first output is an indicator to indicate that the camera should be moved closer to the document object to increase the resolution of the image, and the second output is an indicator to indicate that the camera should be moved away from the document object to reduce the resolution of the image.

4. An apparatus according to claim 2, wherein the first indicator includes a “

down arrow”

symbol, and the second indicator includes an “

up arrow”

symbol.

5. An apparatus according to claim 2, wherein the first output is an indicator to indicate that the zoom of the camera should be increased to increase the resolution of the image, and the second output is an indicator to indicate that the zoom of the camera should be decreased to reduce the resolution of the image.

6. An apparatus according to claim 1, wherein the resolution analyzer comprises a device for analyzing the image to determine the height of text characters in the image.

7. An apparatus according to claim 6, wherein the resolution analyzer comprises a device for identifying a prominent stroke length in the image, by statistically analyzing the lengths of runs of similar pixel values in the image.

8. An apparatus according to claim 1, wherein the image capture device comprises a digital camera contained in a camera body, and wherein the resolution analyzer, the comparison device, and the output device are implemented in the camera body.

9. An apparatus according to claim 1, wherein the image capture device comprises a digital camera coupled to external electronic processing apparatus, and wherein the resolution analyzer, the comparison device and the output device are implemented in said external processing apparatus.

10. An apparatus for capturing an image of a document, comprising:

an image capture device for capturing a digital image of a document in a field of view of the image capture device;

a variable zoom lens system for adjusting the optical image formed at the image capture device, the variable zoom lens system being responsive to an electronic zoom control signal,

a resolution analyzer for analyzing the image to determine an approximate resolution of text characters in the image;

a comparison device responsive to the determined resolution of text characters, for comparing the determined resolution with predetermined data representing at least one threshold resolution, and for generating an error output if the determined resolution does not meet the threshold requirement; and

a zoom control device for generating said zoom control signal, in response to said error output, to adjust the magnitude of zoom of said field of view, to correct the image resolution.

11. An apparatus according to claim 10, wherein the resolution analyzer comprises a device for analyzing the image to determine the height of text characters in the image.

12. An apparatus according to claim 11, wherein the resolution analyzer comprises a device for identifying a prominent stroke length in the image, by statistically analyzing the lengths of runs of similar pixel values in the image.

13. An apparatus according to claim 10, wherein the image capture device comprises a digital camera contained in a camera body, and wherein the resolution analyzer, the comparison device, and the zoom control device are implemented in the camera body.

14. An apparatus according to claim 10, wherein the image capture device comprises a digital camera coupled to external electronic processing apparatus, and wherein the resolution analyzer, the comparison device and the zoom control device are implemented in said external processing apparatus.

15. A method of determining the resolution of text characters in a digital image of a document, the method comprising:

determining run lengths of runs of pixels in the digital image; and

analyzing the run lengths to identify a predominant length corresponding to the average character height.

16. A method according to claim 15, further comprising determining at least one axis of the image corresponding to at least one of the direction of lines of text and a direction generally perpendicular to the direction of the lines of text.

17. A method according to claim 16, wherein the step of determining at least one axis comprises determining two axes, being respectively parallel to the direction of lines of text and perpendicular to the direction of lines of text, and repeating the steps of determining and analyzing run lengths for each axis.

18. A method according to claim 15, wherein the step of analyzing the run lengths comprises identifying at least one peak in a run-length histogram, wherein the magnitude of the peak represents a pseudo probability factor that the peak corresponds to the predominant character height.

19. A method according to claim 18, further comprising selecting a peak representing a longer run length as representing the predominant character height, in the case of two candidate peaks at different run lengths.

20. A method according to claim 15, wherein the image includes a gray-scale component, and wherein the method comprises binarizing the gray-scale component according to a threshold, prior to the step of determining said run lengths.