Image resizing for optical character recognition in portable reading machine

• US 20060017752A1
• Filed: 04/01/2005
• Published: 01/26/2006
• Est. Priority Date: 04/02/2004
• Status: Active Grant

• Current Assignee: National Federation of the Blind
• Original Assignee: KNFB Reader LLC
• Inventors: Gibson, Lucy, Albrecht, Paul, Kurzweil, Raymond C.
• Granted Patent: US 8,873,890 B2
• Time in Patent Office: Days
• US Class Current: 345/698
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06F 3/0304 Detection arrangements using opto-electronic means constructional details of pointing devices not related to the detection arrangement using opto-electronic means G06F3/033; optical digitisers G06F3/042
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/142 using hand-held instruments; Constructional details of the instruments
• CPC Class Codes: G06V 30/1478 of characters or characters lines
• CPC Class Codes: G06V 30/1607 Correcting image deformation, e.g. trapezoidal deformation caused by perspective
• CPC Class Codes: G06V 30/166 Normalisation of pattern dimensions
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16

Abstract

A reading machine that operates in various modes includes image correction processing is described. The reading device pre-processes an image for optical character recognition by receiving the image and determining whether text in the image is too large or small for optical character recognition processing by determining that text height falls outside of a range in which optical character recognition software will recognize text in a digitized image. If necessary the image is resized according to whether the text is too large or too small.

Claims

1. A computer program product residing on a computer readable medium for processing an image for optical character recognition, the computer program product comprises instructions for causing the reading machine to:

receive an image for processing;

determine whether text in the image is too large or small for optical character recognition processing by determining that text height falls outside of a range in which optical character recognition software will recognize text in a digitized image;

resize the image according to whether the text is too large or too small.

2. The computer program product of claim 1 wherein the range is approximately 20 to 170 pixels in height.

3. The computer program product of claim 1 further comprising:

applying the Hough transform to the digitized image to provide an estimate of text size in the image.

4. The computer program product of claim 1 wherein if the text is determined to be too small, instructions to resize, comprise instructions to:

mathematically double the size of the text and add in missing pixels using an interpolation process.

5. The computer program product of claim 1 wherein if the text is too large, instructions to resize further comprise instructions to:

apply decimation to the image to reduce the size of the text in the digitized image.

6. The computer program product of claim 5 wherein decimation ratios are determined by the largest expected size of the text.

7. The computer program product of claim 5 wherein decimation ratios are determined such that characters in the image are at a pixel height that makes OCR reliable.

8. The computer program product of claim 5 wherein decimation ratios are chosen to provide overlap in the text in images with different decimation ratios.

9. The computer program product of claim 1 wherein a plurality of different re-sizings are processed using optical character recognition.

10. The computer program product of claim 1 further comprising instructions to:

determine a quality of the OCR on each of the different re-sizings.