Deconvolution of digital images

• US 10,140,495 B2
• Filed: 10/03/2016
• Issued: 11/27/2018
• Est. Priority Date: 10/12/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bhagwan, Varun, Liu, Timothy, Ormont, Justin, Underwood, Heather
• Primary Examiner(s): Patel, Jayesh A
• Application Number:
  US15/283,817
• Publication Number:
  US 20170024594A1
• Time in Patent Office: 785 Days
• Field of Search: None
• CPC Class Codes: G06K 7/146 the method including quality enhancement steps
• CPC Class Codes: G06T 2207/10004 Still image; Photographic image
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 3/10 Selection of transformation methods according to the characteristics of the input images
• CPC Class Codes: G06T 3/14 Transformations for image registration, e.g. adjusting or mapping for alignment of images
• CPC Class Codes: G06T 5/73 Deblurring; Sharpening
• CPC Class Codes: G06V 10/20 Image preprocessing
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1607 Correcting image deformation, e.g. trapezoidal deformation caused by perspective
• CPC Class Codes: G06V 40/166 using acquisition arrangements

Abstract

A method for deconvolution of digital images includes obtaining a degraded image from a digital sensor, a processor accepting output from the digital sensor and recognizing a distorted element within the image. The distorted element is compared with a true shape of the element to produce a degrading function. The degrading function is deconvolved from at least a portion of the image to improve image quality of the image. A method of indirectly decoding a barcode includes obtaining an image of a barcode using an optical sensor in a mobile computing device, the image comprising barcode marks and a textual character. The textual character is optically recognized and an image degrading characteristic is identified from the textual character. Compensating for the image degrading characteristic renders previously undecodable barcode marks decodable. A system for deconvolution of digital images is also included.

Claims

1. A system for deconvolution of digital images comprising:

a processor; and

a memory to provide instructions to the processor;

wherein the processor, when executing the instructions, implements;

an element identification module to recognize distorted text within a degraded image by performing optical character recognition on the distorted text to produce an optically recognized character;

a degrading function calculator to compare the optically recognized character with the distorted text from which the optically recognized character was recognized to produce a degrading function; and

a deconvolution module to deconvolve the degrading function for at least a portion of the degraded image to improve the image quality.

2. The system of claim 1, wherein the degrading function calculator is further to overlay the optically recognized character on portions of the image from which the optically recognized character was recognized.

3. The system of claim 1, wherein the degrading function calculator is further to compare the optically recognized character with the distorted text using a fast Fourier transform.

4. The system of claim 1, wherein the degrading function calculator is further to quantify the degrading function as a point spread function.

5. The system of claim 1, wherein the distorted text is associated with barcode marks in the degraded image and contains the same information that is encoded in the barcode marks, the element identification module to verify information decoded from the barcode marks against the optically recognized character.

6. A system for indirectly decoding a barcode by deconvolution of a digital image comprising:

a processor; and

a memory to provide instructions to the processor;

wherein the processor, when executing the instructions, implements;

an element identification module to recognize distorted text within a degraded image that comprises both a barcode and the distorted text, wherein recognizing the distorted text comprises performing optical character recognition on the distorted text to produce an optically recognized character;

a degrading function calculator to compare the optically recognized character with the distorted text from which the optically recognized character was recognized to produce a degrading function;

a deconvolution module to deconvolve the degrading function for at least a portion of the degraded image comprising the barcode to improve image quality of the barcode; and

a decoding module to decode the barcode based on the improved image quality of the barcode.

7. The system of claim 6, wherein the degrading function calculator is further to overlay the optically recognized character on portions of the image from which the optically recognized character was recognized.

8. The system of claim 6, wherein the degrading function calculator is further to compare the optically recognized character with the distorted text using a fast Fourier transform.

9. The system of claim 6, wherein the degrading function calculator is further to quantify the degrading function as a point spread function.

10. The system of claim 6, wherein the distorted text is associated with the barcode in the degraded image and contains the same information that is encoded in the barcode, the element identification module to verify information decoded from the barcode against the optically recognized character.

11. A method for improving image quality of digital images comprising:

obtaining a degraded image, a processor accepting a digital representation of the degraded image;

recognizing distorted text within the degraded image by using the processor to perform optical character recognition on the distorted text to produce an optically recognized character;

then comparing the optically recognized character with the distorted text from which the optically recognized character was recognized to produce a degrading function; and

applying the degrading function to at least a portion of the degraded image to improve image quality of the degraded image.

12. The method of claim 11, wherein applying the degrading function to at least a portion of the degraded image comprises deconvolving the degrading function with respect to the portion of the degraded image to improve image quality of the degraded image.

13. The method of claim 11, in which the degrading function quantifies an image blur path and distance.

14. The method of claim 11, in which a first degrading function is calculated at a first location in the degraded image and a second degrading function is calculated at a second location within the degraded image.

15. The method of claim 14, in which deconvolution of portions of the image between the first location and second location are made by interpolating the first degrading function and the second degrading function.

16. The method of claim 14, further comprising extrapolating from the first and second degrading functions to cover areas of the degraded image which are beyond both the first location and second location.