Section based algorithm for image enhancement

• US 7,168,621 B2
• Filed: 04/28/2004
• Issued: 01/30/2007
• Est. Priority Date: 12/04/2003
• Status: Expired due to Fees

• Current Assignee: Scanbuy Incorporated
• Original Assignee: Scanbury Incorporated
• Inventors: Frantz, Didier, Ghai, Rashmi
• Primary Examiner(s): Paik; Steven S.
• Application Number:
  US10/833,017
• Publication Number:
  US 20050121521A1
• Time in Patent Office: 1,007 Days
• Field of Search: 235/462.25, 235/462.01, 235/462.06, 235/462.24, 235/462.1, 235/494, 235/487, 382/176, 382/284, 382/534
• US Class Current: 235/462.25
• CPC Class Codes: G06K 7/10851 Circuits for pulse shaping, amplifying, eliminating noise signals, checking the function of the sensing device basic electronic circuitry H03
• CPC Class Codes: G06K 7/14 using light without selection of wavelength, e.g. sensing reflected white light G06K7/10831 - G06K7/1097 take precedence
• CPC Class Codes: G06T 2207/20012 Locally adaptive
• CPC Class Codes: G06T 2207/20021 Dividing image into blocks, subimages or windows
• CPC Class Codes: G06T 7/11 Region-based segmentation

Abstract

This present invention discloses a system and method for enhancing images of barcodes and other similar objects taken by the digital camera connected to or embedded in a mobile device. This filter works by converting the image into its equivalent gray scale. The algorithm then divides the image into sections and finds the pixels of minimum intensity in each section of the image. This minima is used to calculate cut-off values for thresholding. After thresholding, the image is reassembled from its divided sections.

Claims

1. A method of enhancing an image comprising the steps of:

converting the image to a two-dimensional array;

converting said image to grayscale;

dividing said image into vertical sections of fixed width;

assigning all pixels in said image having an intensity below a first threshold an intensity corresponding to black;

assigning all pixels in said image having an intensity above a second threshold an intensity corresponding to white, wherein said second threshold is greater than said first threshold;

determining the minimum pixel intensity in each of said sections;

assigning a pixel in a section an intensity corresponding to black if the intensity of said pixel lies within a predetermined range of the minimum pixel intensity for that section; and

assigning a pixel in a section an intensity corresponding to black if the average intensity of pixels surrounding said pixel lie within a second predetermined range of minimum pixel intensity for said section, wherein said average intensity is calculated by averaging the intensity values of all pixels which are in direct contact with said pixel; and

recombining said image sections to reform said image.

2. A method for enhancing an image according to claim 1, wherein said sections are further divided into an equal number of horizontal sections.