Method for omnidirectional processing of 2D images including recognizable characters

• US 8,682,077 B1
• Filed: 06/11/2010
• Issued: 03/25/2014
• Est. Priority Date: 11/28/2000
• Status: Expired due to Term

• Current Assignee: Hand Held Products Incorporated (Honeywell International Inc.)
• Original Assignee: Hand Held Products Incorporated (Honeywell International Inc.)
• Inventors: Longacre, Andrew Jr.
• Primary Examiner(s): STREGE, JOHN B
• Application Number:
  US12/814,019
• Time in Patent Office: 1,383 Days
• Field of Search: 382/181, 382/176, 382/177
• US Class Current: 382/181
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/136 involving thresholding
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1423 the instrument generating sequences of position coordinates corresponding to handwriting preprocessing or recognising digital ink G06V30/32
• CPC Class Codes: G06V 30/1478 of characters or characters lines
• CPC Class Codes: G06V 30/158 using character size, text spacings or pitch estimation
• CPC Class Codes: G06V 30/1823 using vector-coding
• CPC Class Codes: G06V 30/414 Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text

Abstract

The invention is a method for omnidirectional recognition of recognizable characters in a captured two-dimensional image. An optical reader configured in accordance with the invention searches for pixel groupings in a starburst pattern, and subjects located pixel groupings to a preliminary edge crawling process which records the pixel position of the grouping'"'"'s edge and records the count of edge pixels. If two similar-sized pixel groupings are located that are of sizes sufficient to potentially represent recognizable characters, then the reader launches “alignment rails” at pixel positions substantially parallel to a centerline connecting the center points of the two similarly sized groupings. A reader according to the invention searches for additional recognizable characters within the rail area, and subjects each located pixel grouping within the rail area to a shape-characterizing edge crawling process for developing data that characterizes the shape of a pixel grouping'"'"'s edge. After adjusting the orientation representation of the shape-characterizing data the reader compares the developed shape-characterizing data to previously stored shape-characterizing data to determine the character represented by the grouping on the basis of the best fit data.

Claims

1. A method for utilization of device having an imaging assembly including an image sensor, a memory, a trigger switch, and a hand graspable housing, the method including:

activating capture of image data into said memory utilizing said trigger switch;

searching for pixel groupings utilizing said image data, wherein a pixel grouping is characterized by one or more adjacent like valued pixels;

identifying a pair of similarly sized pixel groupings;

utilizing a result of said identifying, determining a location for searching for a character pixel grouping;

developing shape characterizing data for said character pixel grouping; and

recognizing a character represented by said character pixel grouping.

2. The method of claim 1, wherein the method includes binarizing said image data.

3. The method of claim 1, wherein the method includes determining edge pixels of said pixel groupings.

4. The method of claim 1, wherein the method includes determining edge pixels of said character pixel grouping.

23. The reader of claim 1, wherein the identifying includes utilizing a count of edge pixels.

5. An optical character recognition optical reader for recognizing recognizable characters in a captured image, said reader comprising:

an imaging assembly including an image sensor for generating image signals;

a memory having stored character reference data stored therein;

control circuit in communication with said memory and said image sensor, said control circuit being operative for capturing image data into said memory, said control circuit further being operative for;

searching for pixel groupings utilizing said image data;

determining edge pixels of said pixel groupings;

based on said determining, identifying a pair of similarly sized pixel groupings;

utilizing a result of said identifying, determining a location for searching for a character pixel grouping;

developing shape characterizing data for said character pixel grouping utilizing edge pixels of said character pixel grouping; and

recognizing a character represented by said character pixel grouping.

6. The reader of claim 5, wherein said control circuit is operative for binarizing said image data.

7. The reader of claim 5, wherein said memory stores shape characterizing data.

8. An optical character recognition optical reader for recognizing recognizable characters in a captured image, said reader comprising:

an imaging assembly including an image sensor for generating image signals;

memory circuit having stored character reference data stored therein;

control circuit in communication with said memory circuit and said image sensor, said control circuit being operative for capturing grey scale image data into said memory circuit, said control circuit being programmed to include

binarizing circuit for binarizing said grey scale image data into one bit binary image data, wherein dark pixels are represented by binary “

0”

values and light pixels are represented by binary “

1”

values;

starburst searching circuit for searching for dark pixel groupings in said binary image data starting from a starbust center pixel and continuing said search in a pattern extending radially outwardly in multiple directions for said starburst center pixel;

edge length determining circuit responsive to said starburst searching circuit for subjecting pixel groupings located by said starburst searching circuit to an edge length edge crawl process for determining a length of edges, and pixel positions of edge pixels of said pixel groupings;

size monitoring circuit responsive to said edge length determining circuit for identifying a pair of substantially similarly sized pixel groupings of sufficient edge length to represent a recognizable character in said image data;

rail launching circuit responsive to said size monitoring circuit for launching alignment rails parallel to a centerline intersecting said pair of substantially similarly sized pixel groupings;

centerline search circuit responsive to said rail launch circuit for searching for dark pixels along said centerline;

shape-characterizing circuit responsive to said centerline search circuit for developing shape-characterizing data corresponding to at least one character pixel grouping located by said centerline search circuit, said shape-characterizing circuit including shape orientation adjusting circuit for adjusting an orientation representation of said shape-characterizing data so that said shape-characterizing data can be compared to said stored reference data;

comparison circuit for comparing said shape-characterizing data, as adjusted by said orientation adjusting circuit to said stored reference character data; and

recognition circuit responsive to said comparison circuit for recognizing a character represented by said at least one character pixel grouping on a basis of which data of said stored reference data best fits said shape characterizing data.

9. The reader of claim 8, wherein said binarizing circuit includes circuit for binarizing pixels of said image data according to a tile binarization process.

10. The reader of claim 8, wherein said binarizing circuit includes circuit responsive to said shape-characterizing circuit for binarizing select pixels of said image data according to a high resolution binarization process in which constructed pixel values are interpolated from existing pixel values.

11. The reader of claim 8, wherein said size monitoring circuit identifies similar-sized pixel groupings based on x and y coordinate peak values of said pair of substantially similarly sized pixel groupings.

12. The reader of claim 8, wherein said rail launching circuit includes circuit for calculating respective center positions of each of said pixel groupings and circuit for launching said centerline to intersect said center positions.

13. The reader of claim 8, wherein said shape-characterizing circuit includes circuit for generating a traveling direction value for each edge pixel of said at least one character pixel grouping located by said centerline search circuit.

14. The reader of claim 8, wherein said shape-characterizing circuit includes circuit for generating a high resolution traveling direction value for each edge pixel of said at least one character pixel grouping located by said centerline search circuit.

15. The reader of claim 8, wherein said shape orientation adjustment circuit includes circuit for offsetting said shape-characterizing data by an offset value that depends on a slope of said centerline.

16. The reader of claim 8, wherein said shape-characterizing circuit includes scaling circuit for scaling said shape-characterizing data to the scale of said stored reference character data.

17. The reader of claim 8, wherein said shape-characterizing circuit includes scaling circuit for scaling said shape-characterizing data to the scale of said stored reference character data, and wherein said scaling circuit includes circuit for segmenting edge pixels of said at least one character pixel grouping into a plurality of substantially equal-length segments.

18. An optical character recognition optical reader for recognizing recognizable characters in a captured image, said reader comprising:

an imaging assembly including an image sensor for generating image signals;

memory means having stored character reference data stored therein;

control means in communication with said memory means and said image sensor, said control means being operative for capturing grey scale image data into said memory means, said control means being programmed to include

binarizing means for binarizing said grey scale image data into one bit binary image data, wherein dark pixels are represented by binary “

0”

values and light pixels are represented by binary “

1”

values;

starburst searching means for searching for dark pixel groupings in said binary image data starting from a starburst center pixel and continuing said search in a pattern extending radially outwardly in multiple directions for said starburst center pixel;

edge length determining means responsive to said starburst searching means for subjecting pixel groupings located by said starburst searching means to an edge length edge crawl process for determining a length of edges, and pixel positions of edge pixels of said pixel groupings;

size monitoring means responsive to said edge length determining means for identifying a pair of substantially similarly sized pixel groupings of sufficient edge length to represent a recognizable character in said image data;

rail launching means responsive to said size monitoring means for launching alignment rails parallel to a centerline intersecting said pair of substantially similarly sized pixel groupings;

centerline search means responsive to said rail launch means for searching for dark pixels along said centerline;

shape-characterizing means responsive to said centerline search means for developing shape-characterizing data corresponding to at least one character pixel grouping located by said centerline search means, said shape-characterizing means including shape orientation adjusting means for adjusting an orientation representation of said developed shape-characterizing data so that said shape-characterizing data can be compared to said stored reference data;

comparison means for comparing said shape-characterizing data, as adjusted by said shape orientation adjusting means to said stored reference character data; and

recognition means responsive to said comparison means for recognizing a character represented by said at least one character pixel grouping on a basis of which data of said stored reference data best fits said shape characterizing data.

19. The reader of claim 18, wherein said size monitoring means identifies similar-sized pixel groupings based on x and y coordinate peak values of said pair of substantially similarly sized pixel groupings.

20. The reader of claim 18, wherein said rail launch means includes means for calculating respective center positions of each of said pixel groupings and means for launching said centerline to intersect said center positions.

21. The reader of claim 18, wherein said shape-characterizing means includes means for generating a traveling direction value for each edge pixel of said at least one character pixel grouping located by said centerline search means.

22. The reader of claim 18, wherein said shape-characterizing means includes scaling means for scaling said shape-characterizing data to the scale of said stored reference character data, and wherein said scaling means includes means for segmenting edge pixels of said at least one character pixel grouping into a plurality of substantially equal-length segments.