Method and apparatus for creating pixel tokens from machine-readable symbols to improve decoding accuracy in low resolution images
First Claim
Patent Images
1. A method for decoding a bar code comprising:
- segmenting the bar code into black tokens, white tokens and gray boundary pixels; and
calculating a boundary position of each token with sub-pixel positional accuracy using intensity values of pixels in a boundary region;
wherein calculating the boundary position of each token includes;
identifying the boundary region, identifying a boundary pixel in the boundary region associated with a single white token and an adjacent black token with either a maximum gradient value or a minimum gradient value; and
calculating the boundary position between a single white token and an adjacent black token based on a position of the boundary pixel, an intensity of the boundary pixel, an intensity of a brightest pixel among pixels of the white token; and
an intensity of the darkest pixel among pixels of the black token.
2 Assignments
0 Petitions
Accused Products
Abstract
The present invention is directed towards systems and methods for decoding a bar code. Decoding the bar code includes segmenting the bar code into black tokens, white tokens and gray boundary pixels. Decoding the bar code also includes calculating a boundary position of each token with sub-pixel positional accuracy using intensity values of pixels in a boundary region.
6 Citations
18 Claims
-
1. A method for decoding a bar code comprising:
-
segmenting the bar code into black tokens, white tokens and gray boundary pixels; and calculating a boundary position of each token with sub-pixel positional accuracy using intensity values of pixels in a boundary region; wherein calculating the boundary position of each token includes; identifying the boundary region, identifying a boundary pixel in the boundary region associated with a single white token and an adjacent black token with either a maximum gradient value or a minimum gradient value; and calculating the boundary position between a single white token and an adjacent black token based on a position of the boundary pixel, an intensity of the boundary pixel, an intensity of a brightest pixel among pixels of the white token; and
an intensity of the darkest pixel among pixels of the black token. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 12, 13)
-
-
10. A method for decoding a bar code comprising:
-
segmenting the bar code into black tokens, white tokens and gray boundary pixels; and calculating a boundary position of each token with sub-pixel positional accuracy using intensity values of pixels in a boundary region; wherein calculating the boundary includes; identifying a particular white token adjacent to a particular black token, in which;
a first pixel associated with the particular white token is separated from a second pixel associated with the particular black token by one or more gray boundary pixels;
or the first pixel is adjacent to the second pixel;indentifying a first boundary pixel as the brightest pixel associated with the particular white token; indentifying a second boundary pixel as the darkest pixel associated with the particular black token; identifying the boundary region as the first boundary pixel, the second boundary pixel, and all the pixels between the first boundary pixel and the second boundary pixel; calculating a gradient value for each pixel in the boundary region; identifying a white-to-black boundary pixel as the pixel in the boundary region with a minimum gradient value; and calculating the boundary position as the sum of a position of the white-to-black boundary pixel and a first quotient;
a dividend of the first quotient being equal to a difference between an intensity of the white-to-black boundary pixel and a minimum intensity of pixels in the black token; and
a divisor of the first quotient being equal to a difference between a maximum intensity of pixels in the particular white token and the minimum intensity of pixels in the particular black token. - View Dependent Claims (11)
-
-
14. A non-transitory computer readable medium encoded with instructions for decoding a bar code comprising:
-
instructions for segmenting the bar code into black tokens, white tokens and gray boundary pixels; and instructions for calculating a boundary position of each token with sub-pixel positional accuracy using intensity values of pixels in a boundary region; wherein calculating the boundary position of each token includes; identifying the boundary region, identifying a boundary pixel in the boundary region associated with a single white token and an adjacent black token with either a maximum gradient value or a minimum gradient value; and calculating the boundary position between a single white token and an adjacent black token based on a position of the boundary pixel, an intensity of the boundary pixel, an intensity of a brightest pixel among pixels of the white token; and
an intensity of the darkest pixel among pixels of the black token.
-
-
15. A system for decoding a bar code including:
-
a processor with logic circuits; logic circuits configured to segment data representing the bar code into black tokens, white tokens and gray boundary pixels; and logic circuits for calculating a boundary position of each token with sub-pixel positional accuracy using intensity values of pixels in a boundary region; wherein calculating the boundary position of each token includes; identifying the boundary region, identifying a boundary pixel in the boundary region associated with a single white token and an adjacent black token with either a maximum gradient value or a minimum gradient value; and calculating the boundary position between a single white token and an adjacent black token based on a position of the boundary pixel, an intensity of the boundary pixel, an intensity of a brightest pixel among pixels of the white token; and
an intensity of the darkest pixel among pixels of the black token. - View Dependent Claims (16, 17, 18)
-
Specification