Forming scanned composite document with optical character recognition function

• US 9,881,223 B2
• Filed: 04/22/2014
• Issued: 01/30/2018
• Est. Priority Date: 04/22/2014
• Status: Active Grant

• Current Assignee: Lenovo PC International Limited (Lenovo Group Ltd.)
• Original Assignee: Lenovo Singapore Pte Limited (Lenovo Group Ltd.)
• Inventors: Kapinos, Robert James, Feng, Xin, Hilburger, Paul
• Primary Examiner(s): Beck, Leron
• Application Number:
  US14/258,276
• Publication Number:
  US 20150302246A1
• Time in Patent Office: 1,379 Days
• Field of Search: 3482071
• CPC Class Codes: G06V 20/20 in augmented reality scenes
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names
• CPC Class Codes: G06V 30/43 Editing text-bitmaps, e.g. alignment, spacing; Semantic analysis of bitmaps of text without OCR

Abstract

An embodiment provides a method, including: capturing, using an image capture device of an electronic device, image data of a document; processing, using a processor, the image data; the processing including identifying text within the image data to form two or more images into a composite document of the document; and storing, in a memory, data related to the composite document. Other aspects are described and claimed.

Claims

1. A method, comprising:

capturing, using an image capture device of an electronic device, a plurality of images of a single physical document, each of the plurality of images including a different part of the single physical document;

processing, using a processor, the plurality of images;

the processing including identifying text within the plurality of images to combine two or more images into an electronic facsimile form of the document comprising the entire content of the single physical document, wherein the processing further comprises determining whether at least one low confidence element of at least one of the plurality of images is present, wherein the at least one low confidence element comprises an unreadable image portion and would result in an incomplete electronic facsimile form;

responsive to determining that a low confidence element is present, notifying a user of the low confidence element, capturing at least one additional image comprising a portion of the single physical document corresponding to the low confidence element, and combining the plurality of images and the at least one additional image into an electronic facsimile form of the document; and

storing, in a memory, the electronic facsimile form of the document.

2. The method of claim 1, wherein:

said capturing comprises capturing continuous image data of the document; and

said analyzing comprises forming two or more images from the continuous image data of the document.

3. The method of claim 2, wherein continuous image data comprises continuous video feed data.

4. The method of claim 1, wherein the analyzing comprises processing the plurality of images to extract text data and perform an action selected from the group consisting of:

transforming the plurality of images, scaling the plurality of images, de-skewing the plurality of images, adjusting contrast of the plurality of images.

5. The method of claim 4, wherein the analyzing comprises linguistically analyzing the text data.

6. The method of claim 5, wherein linguistically analyzing the text data comprises:

accessing a database of linguistic rules; and

analyzing text data of the two or more images to form the electronic facsimile form of the document.

7. The method of claim 1, wherein the analyzing comprises identifying at least one low confidence element of the electronic facsimile form of the document.

8. The method of claim 7, wherein the at least one low confidence element is associated with a characteristic selected from the group of characteristics consisting of:

a blurred image, a missing image portion;

a linguistically erroneous image portion, a low resolution portion of the image, an image portion having poor image contrast, an image portion having poor light level.

9. The method of claim 7, wherein the analyzing comprises identifying at least one image to remedy at least one low confidence element of the electronic facsimile form of the document;

and

the method further comprising prompting the user to capture additional image data associated with the low confidence element.

10. An apparatus, comprising:

an image capture device;

a processor operatively coupled to the image capture device;

a memory storing instructions executable by the processor to;

capture, using the image capture device, a plurality of images of a single physical document, each of the plurality of images including a different part of the single physical document;

process the plurality of images to identify text within the plurality of images to combine two or more images into an electronic facsimile form of the document comprising the entire content of the single physical document, wherein the processing further comprises determining whether at least one low confidence element of at least one of the plurality of images is present, wherein the at least one low confidence element comprises an unreadable image portion and would result in an incomplete electronic facsimile form;

responsive to determining that a low confidence element is present, notify a user of the low confidence element, capture at least one additional image comprising a portion of the single physical document corresponding to the low confidence element, and combine the plurality of images and the at least one additional image into an electronic facsimile form of the document; and

store, in a memory, the electronic facsimile form of the document.

11. The apparatus of claim 10, wherein:

to capture comprises capturing continuous image data of the document; and

to analyze comprises forming two or more images from the continuous image data of the document.

12. The apparatus of claim 11, wherein continuous image data comprises continuous video feed data.

13. The apparatus of claim 10, wherein to analyze comprises processing the plurality of images to extract text data from the plurality of images and perform an action selected from the group consisting of:

transforming the plurality of images, scaling the plurality of images, de-skewing the plurality of images, adjusting contrast of the plurality of images.

14. The apparatus of claim 13, wherein to analyze comprises linguistically analyzing the text data.

15. The apparatus of claim 14, wherein linguistically analyzing the text data comprises:

accessing a database of linguistic rules; and

analyzing text data of the two or more images to form the electronic facsimile form of the document.

16. The apparatus of claim 10, wherein to analyze comprises identifying at least one low confidence element of the document in the electronic facsimile form of the document.

17. The apparatus of claim 16, wherein to analyze comprises identifying at least one image to remedy at least one low confidence element of the document in the electronic facsimile form of the document;

and

the instructions further executable by the processor to prompt the user to capture additional image data associated with the low confidence element.

18. A computer program product, comprising:

a storage device having code stored therewith that is executable by a processor, the code comprising;

code that captures, using an image capture device of an electronic device, a plurality of images of a single physical document, each of the plurality of images including a different part of the single physical document;

code that processes, using a processor, the plurality of images to identify text within the plurality of images to combine two or more images into an electronic facsimile form of the document comprising the entire content of the single physical document, wherein the processing further comprises determining whether at least one low confidence element of at least one of the plurality of images is present, wherein the at least one low confidence element comprises an unreadable image portion and would result in an incomplete electronic facsimile form;

responsive to determining that a low confidence element is present, code that notifies a user of the low confidence element, captures at least one additional image comprising a portion of the single physical document corresponding to the low confidence element, and combines the plurality of images and the at least one additional image into an electronic facsimile form of the document; and

code that stores, in a memory, the electronic facsimile form of the document.