Method and apparatus for locating bar codes including QR codes
A method for identifying a QR code in an image includes inputting an image, and using one or more computer processor to identify edges in the image; create an edge count image; label connected regions in the edge count image; create a candidate region list; for each individual candidate in the candidate region list: find regions that overlap with the region in the individual candidate; group regions that overlap into a group of overlapped regions; for each group: merge the overlapped regions into a merged region; add each merged region to the candidate region list to form a new candidate region list; and perform decoding of a QR code in each region in the new candidate region list.
1. A method for identifying a QR code in an image, comprising:
inputting an image;
using a processor to:
identify edges in the image;
create an edge count image;
label connected regions in the edge count image;
create a candidate region list;
for each individual candidate in the candidate region list:
find regions that overlap with the region in the individual candidate;
group regions that overlap into a group of overlapped regions;
for each group:
merge the overlapped regions into a merged region;
add each merged region to the candidate region list to form a new candidate region list; and
perform decoding of a QR code in each region in the new candidate region list.
2. A method for identifying a QR code in an image as in claim 1 , wherein finding regions that overlap with the region in the individual candidate comprises:
finding horizontal overlap between two regions, region 1 and region 2 as follows
DisCx
=
cx
2
-
cx
1
,
W
1
=
width
of
region
1
2
,
W
2
=
width
of
region
2
2
If
(
DisCx
<
W
1
+
W
2
)
then
two
regions
are
overlapped
where cx 1 is the center of region 1 in the x direction and cx 2 is the center of region 2 in the x direction.
3. A method for identifying a QR code in an image as in claim 1 , wherein finding regions that overlap with the region in the individual candidate comprises:
finding vertical overlap between two regions, region 1 and region 2 as follows
DisCy
=
cy
2
-
cy
1
,
H
1
=
height
of
region
1
2
,
H
2
=
height
of
region
2
2
If
(
DisCy
<
H
1
+
H
2
)
then
two
regions
are
overlapped
where cy 1 is the center of region 1 in the y direction and cy 2 is the center of region 2 in the y direction.
4. A method for identifying at least two barcodes in the same image with one barcode being rotated with respect to another barcode, comprising:
inputting an image;
using a processor to:
decode a horizontal or vertical barcode in the image, including decoding a PDF417 barcode;
next, decode a rotated barcode in the image, the rotated barcode being rotated with respect to the horizontal or vertical barcode.
5. A method for identifying at least two barcodes in the same image with one barcode being rotated with respect to another barcode, comprising:
inputting an image;
using a processor to:
decode a horizontal or vertical barcode in the image;
next decode a rotated barcode in the image, the rotated barcode being rotated with respect to the horizontal or vertical 1 barcode;
after decoding the rotated barcode in the image, then decode a 2D barcode.
6. A method for identifying at least two barcodes in the same image as in claim 5 , wherein the 2d barcode is a QR code and further comprising:
using the processor to:
identify edges in the image;
create an edge count image;
label connected regions in the edge count image;
create a candidate region list;
for each individual candidate in the candidate region list:
find regions that overlap with the region in the individual candidate;
group regions that overlap into a group of overlapped regions;
for each group:
merge the overlapped regions into a merged region;
add each merged region to the candidate region list to form a new candidate region list; and
perform decoding of a QR code in each region in the new candidate region list.
7. A device for identifying a QR code in an image, comprising:
a unit for inputting an image;
a processor that:
identifies edges in the image;
creates an edge count image;
labels connected regions in the edge count image;
creates a candidate region list;
for each individual candidate in the candidate region list:
finds regions that overlap with the region in the individual candidate;
groups regions that overlap into a group of overlapped regions;
for each group:
merges the overlapped regions into a merged region;
adds each merged region to the candidate region list to form a new candidate region list; and
performs decoding of a QR code in each region in the new candidate region list.
8. A device for identifying a QR code in an image as in claim 7 , wherein finding regions that overlap with the region in the individual candidate comprises:
finding horizontal overlap between two regions, region 1 and region 2 as follows
DisCx
=
cx
2
-
cx
1
,
W
1
=
width
of
region
1
2
,
W
2
=
width
of
region
2
2
If
(
DisCx
<
W
1
+
W
2
)
then
two
regions
are
overlapped
where cx 1 is the center of region 1 in the x direction and cx 2 is the center of region 2 in the x direction.
9. A device for identifying a QR code in an image as in claim 7 , wherein finding regions that overlap with the region in the individual candidate comprises:
finding vertical overlap between two regions, region 1 and region 2 as follows
DisCy
=
cy
2
-
cy
1
,
H
1
=
height
of
region
1
2
,
H
2
=
height
of
region
2
2
If
(
DisCy
<
H
1
+
H
2
)
then
two
regions
are
overlapped
where cy 1 is the center of region 1 in the y direction and cy 2 is the center of region 2 in the y direction.
10. A device for identifying a QR code in an image as in claim 7 , wherein the unit for inputting an image is a scanner.
11. A device for identifying a QR code in an image as in claim 7 , further comprising a memory for storing the image.