System and method for reading machine readable codes in transportation and logistic applications

Patent metadata

Field	Value
Publication number	US-9818197-B2
Application number	US-201514726084-A
Country	US
Kind code	B2
Filing date	May 29, 2015
Priority date	May 29, 2015
Publication date	Nov 14, 2017
Grant date	Nov 14, 2017

Abstract

A system and computer-implemented method for searching for regions of interest may include performing a first linear image slice of an object including a machine-readable code associated therewith. Interesting blocks within the first linear image slice may be identified. A determination as to whether at least one isolated interesting block or multiple interesting blocks that are adjacent to one another exist within the first linear image slice may be made, and, if so, at least one blob inclusive of the at least one isolated interesting block or multiple interesting blocks being adjacent to one another may be identified, otherwise, the first linear image slice may be discarded. Respective geometrically shaped area(s) that include respective blob(s) may be formed, where the geometrically shaped area(s) define at least one region of interest is which the machine-readable code is located.

First claim

What is claimed:

1. A computer-implemented method for searching for regions of interest, said method comprising:
performing a first linear image slice of an object including a machine-readable code associated therewith;
identifying interesting blocks within the first linear image slice;
determining whether at least one isolated interesting block or multiple interesting blocks that are adjacent to one another exist within the first linear image slice, and, if so,
identifying at least one blob inclusive of the at least one isolated interesting block or multiple interesting blocks being adjacent to one another,
otherwise, discarding the first linear image slice; and

forming at least one geometrically shaped area that includes at least one blob, wherein the at least one geometrically shaped area defines at least one region of interest in which the machine-readable code is located.

2. The computer-implemented method according to claim 1 , further comprising:
determining whether any regions of interest overlap one another; and
if a determination is made that at least two regions of interest overlap each other, merging at least two overlapping regions of interest to form a single region of interest by forming a geometrically shaped area around the at least two overlapping regions of interest;
otherwise, not merging any of the at least two regions of interest.

3. The computer-implemented method according to claim 1 , wherein forming the at least one geometrically shaped area includes forming a rectangular area.

4. The computed-implemented method according to claim 1 , further comprising:
determining whether any of the at least one region of interest does not share a border of the first linear image slice at which a second linear image slice is to be made; and
if a determination is made that the at least one region of interest does not share the border, processing any of the at least one region of interest that does not share the border;
otherwise, freezing any of the at least one region of interest that share the border at which the second linear image slice is to be made.

5. The computer-implemented method according to claim 4 , further comprising:
performing a second linear image slice of the object;
identifying second interesting blocks within the second linear image slice;
identifying at least one second blob inclusive of at least one isolated interesting block or multiple adjacent interesting blocks being adjacent to one another in the second linear image slice; and
forming respective at least one second geometrically shaped area that include respective at least one second blob, the at least one second geometrically shaped area defining at least one second region of interest.

6. The computer-implemented method according to claim 4 , further comprising:
determining whether any of the at least one second region of interest is adjacent to any of the at least one region of interest that was frozen; and
if a determination is made that any of the at least one second region of interest is adjacent to any of the at least one region of interest that was frozen, merging the regions of interest that are determined to be adjacent to one another to form a geometrically shaped region of interest that spans across the border between the successive regions of interest.

7. The computer-implemented method according to claim 1 , further comprising reading the code in the at least one region of interest.

8. The computer-implemented method according to claim 1 , further comprising:
determining a score indicative of including a code for each of the respective blobs; and
in forming respective at least one geometrically shaped area, forming up to a predetermined number of geometrically shaped areas inclusive of blobs with the highest scores.

9. A system for searching for regions of interest, said system comprising:
a linear imaging device configured to linearly image an object within a scene;
a processing unit in communication with said linear imaging device, and configured to:
perform a first linear image slice of an object including a machine-readable code associated therewith;
identify interesting blocks within the first linear image slice;
determine whether at least one isolated interesting block or multiple interesting blocks that are adjacent to one another exist within the first linear image slice, and, if so, identify at least one blob inclusive of the at least one isolated interesting block or the multiple interesting blocks being adjacent to one another, otherwise, discard the first linear image slice; and
form at least one geometrically shaped area that includes at least one blob, the at least one geometrically shaped area defining at least one region of interest in which the machine-readable code is located.

10. The system according to claim 9 , wherein said processing unit is further configured to:
determine whether any regions of interest overlap one another; and
if a determination is made that at least two regions of interest overlap each other, merge at least two overlapping regions of interest to form a single region of interest by forming a geometrically shaped area around the at least two overlapping regions of interest;
otherwise, not merge any of the at least two regions of interest.

11. The system according to claim 9 , wherein said processing unit, in forming the at least one geometrically shaped area, is configured to form a rectangular area.

12. The system accord to claim 9 , wherein said processing unit is further configured to:
determine whether any of the at least one region of interest does not share a border of the first linear image slice at which a second linear image slice is to be made; and
if a determination is made that the at least one region of interest does not share the border, process any of the at least one region of interest that does not share the border;
otherwise, freeze any of the at least one region that share the border at which the second linear image slice is to be made.

13. The system according to claim 12 , wherein said processing unit is further configured to:
perform a second linear image slice of the object;
identify second interesting blocks within the second linear image slice;
identify at least one second blob inclusive of at least one isolated interesting block or multiple adjacent interesting blocks being adjacent to one another in the second linear image slice; and
form respective at least one second geometrically shaped area that includes respective at least one second blob, the second at least one second geometrically shaped area defining at least one second region of interest.

14. The system according to claim 12 , wherein said processing unit is further configured to:
determine whether any of the at least one second region of interest is adjacent to any of the at least one region of interest that were frozen; and
if a determination is made that any of the at least one second region of interest is adjacent to any of the at least one region of interest that was frozen, merge the regions of interest that are determined to be adjacent to one another to form a geometrically shaped region of interest that spans across a border between the successive regions of interest.

15. The system according to claim 9 , wherein said processing unit is further configured to read a code in the at least one region of interest.

16. The system according to claim 9 , wherein said processing unit is further configured to:
determine a score for each of the respective blobs; and
in forming respective at least one geometricall

Assignees

• Datalogic IP Tech Srl

Inventors

• Viti Marco
• Montemurro Emanuele
• Rago Vittorio

Classifications

• G06K7/1443 Primary

  locating of the code in an image · CPC title

• G06V20/62

  Text, e.g. of license plates, overlay texts or captions on TV images · CPC title

• G06V30/424

  Postal images, e.g. labels or addresses on parcels or postal envelopes · CPC title

• G06V10/10

  Image acquisition (document image scanning and transmission H04N1/00; control of digital cameras H04N23/60) · CPC title

• G06V10/50

  by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis · CPC title