Method for determining skew angle and location of a document in an over-scanned image
View Patent ↗A method for determining skew angle ( 5 ) and location of a document in an over-scanned digital image is disclosed. A document is scanned to capture a gray scale image. The outline pixel ( 1 ) of a document from the captured gray scale image are connected ( 2 ). An initial angle is set at zero and a x-minimum, y-minimum, x-maximum, and y-maximum of the polygon are determined ( 3 ). A rectangular boundary ( 4 ) area based on the x-minimum, y-minimum, x-maximum, and y-maximum is calculated and recorded. The angle is recorded and the polygon is rotated z-degree. The process is repeated and a minimum boundary area is selected. An angle corresponding to the minimum boundary is the skew angle of the document.
1. A method for determining skew angle and location of a document in an over-scanned digital image comprising the steps of:
a) scanning a document;
b) capturing a gray scale image;
c) detecting outline pixels of a document from said captured gray scale image;
d) connecting said detected pixels in a sequential order to form an outline polygon;
e) setting angle θ=0;
f) determining a x-minimum, y-minimum, x-maximum, and y-maximum of said polygon;
g) calculating a rectangular boundary area based on said x-minimum, y-minimum, x-maximum, and y-maximum;
h) recording said boundary area and θ;
i) rotating said polygon z-degrees;
j) resetting θ=θ+z-degrees;
k) repeating step f-j n-times;
l) selecting a minimum boundary area from said boundary areas recorded in step h);
m) recording a corresponding angle at said minimum boundary area; and
n) assigning said rotation angle having the minimum bounding area as said skew angle of said document.
2. A method as in claim 1 comprising the additional step of:
o) subtract x-minimum, from x-maximum, at said skew angle to determine document width; and
p) subtract y-minimum from said y-maximum, at said skew angle to determine document length.
3. A method as in claim 2 comprising the additional step of:
q) performing a location transformation of an origin point of said minimum bounding area to locate the document.
4. A method as in claim 3 comprising the additional step of:
r) calculating an area of said polygon;
s) comparing send area of said polygon to said minimum boundary area; and
t) if said area of said polygon is within k-units of said minimum boundary area, there is a high degree of confidence that said location is correct.
5. A method as in claim 1 wherein said scanning is accomplished by a CCD sensor.
6. A method as in claim 1 wherein z=½ degree.
7. A method as in claim 1 wherein a rotation point for said polygon is located outside of said polygon.
8. A method as in claim 1 wherein a rotation point of said polygon is on said polygon.
9. A method as in claim 1 wherein a rotation point for said polygon is located inside said polygon.
10. An image processing method for determining skew angle and location of a document in an over-scanned digital image comprising:
a) scanning a document;
b) capturing a digital image;
c) detecting outline pixels of a document from said captured digital image;
d) connecting detected pixels in a sequential order to form an outline polygon;
e) determine a x-minimum, y-minimum, x-maximum, and y-maximum of said polygon;
f) set n=1
g) calculating a n rectangular boundary area based on said x-minimum, y-minimum, x-maximum, and y-maximum;
h) rotating said polygon z-degrees;
i) determine a new x-minimum, y-minimum, x-maximum, and y-maximum of said polygon;
j) m=n+1
k) calculating a new rectangular boundary area based on said x-minimum, y-minimum, x-maximum, and y-maximum; and
l) if said m rotational boundary area is greater than said n rectangular boundary area go to step m); if m boundary area is less than said n boundary area, reset n=n+1 and go to step g); if said m boundary area is equal to said n boundary area go to step m); and
m) end program.
11. A method for determining skew angle and location of a document in an over-scanned digital image comprising the steps of:
a) scanning a document;
b) capturing a color digital image;
c) detecting outline pixels of a document from said captured color digital image;
d) connecting said detected pixels in a sequential order to form an outline polygon;
e) setting angle θ=0;
f) determining a x-minimum, y-minimum, x-maximum, and y-maximum of said polygon;
g) calculating a rectangular boundary area based on said x-minimum, y-minimum, x-maximum, and y-maximum;
h) recording said boundary area and θ;
i) rotating said polygon z-degrees;
j) resetting θ=θ+z-degrees;
k) repeating step f-j n-times;
l) selecting a minimum boundary area from said boundary areas recorded in step h);
m) recording a corresponding angle at said minimum boundary area; and
n) assigning said rotation angle having the minimum bounding area as said skew angle of said document.