System and method for automatically detecting edges of scanned documents
First Claim
Patent Images
1. A method for detecting an edge of a document being scanned, comprising:
- (a) scanning a portion of the document against a substantially light reflecting backing to obtain a first set of image data;
(b) scanning a portion of the document against a substantially light absorbing backing to obtain a second set of image data;
(c) calculating a set of first values from the first set of image data, each one of the first values being a first-order statistic;
(d) calculating a set of second values from the second set of image data, each one of the second values being a first-order statistic; and
(e) determining a detected edge of the document from the set of first values and the set of second values.
5 Assignments
0 Petitions
Accused Products
Abstract
A method for identifying document edges collects a predetermined number scanlines of the document against a light backing and a dark backing. A first set of first-order statistics are calculated from the image data obtained by scanning the document against the light backing. A second set of first-order statistics are calculated from the image data obtained by scanning the document against the dark backing. A document edge is detected using the first and second sets of first-order statistics.
79 Citations
17 Claims
-
1. A method for detecting an edge of a document being scanned, comprising:
-
(a) scanning a portion of the document against a substantially light reflecting backing to obtain a first set of image data;
(b) scanning a portion of the document against a substantially light absorbing backing to obtain a second set of image data;
(c) calculating a set of first values from the first set of image data, each one of the first values being a first-order statistic;
(d) calculating a set of second values from the second set of image data, each one of the second values being a first-order statistic; and
(e) determining a detected edge of the document from the set of first values and the set of second values. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
(e1) determining a set of first difference values, each one of the first difference values being the difference between one of the first values and one of the second values;
(e2) determining a second difference value, the second difference value being the difference between two of the first difference values; and
(e3) identifying the detected edge when the second difference value is greater than a threshold value.
-
-
3. The method according to claim 2, wherein:
-
step (c) calculates a first mean value for each one of selected columns of pixels within the first set of image data; and
step (d) calculates a second mean value for each for each one of selected columns of pixels within the second set of image data.
-
-
4. The method according to claim 1, further comprising:
-
(f) calculating a set of third values from the second set of image data, each one of the third values being a second-order statistic;
(g) determining a second detected edge of the document from the set of third values; and
(h) reconciling the detected edge and the second detected edge to obtain a document edge.
-
-
5. The method according to claim 4, wherein step (g) comprises:
-
(g1) determining a first slope value, the first slope value being a function of the difference between a plurality of the third values;
(g2) generating a block sum value, the block sum value comprising the sum of a plurality of third values; and
wherein the second detected edge is identified from the first slope value and the block sum.
-
-
6. The method according to claim 5, wherein step (g) further comprises:
-
(g3) determining a second slope value, the second slope value being a function of the difference between a plurality of the second values; and
(g4) computing a product of the first slope value and the second slope value;
wherein the second detected edge is identified from the product, the first slope value and the block sum.
-
-
7. The method according to claim 1, further comprising:
-
(f) calculating a set of third values from the second set of image data, each one of the third values being a fourth-order statistic;
(g) determining a second detected edge of the document from the set of third values; and
(h) reconciling the detected edge and the second detected edge to obtain the document edge.
-
-
8. The method according to claim 7, wherein step (g) comprises:
-
(g1) determining a first slope value, the first slope value being a function of the difference between a plurality of the third values;
(g2) determining a set of first difference values, each one of the first difference values being the difference between one of the first values and one of the second values; and
(g3) determining a second difference value, the second difference value being the difference between two of the first difference values;
wherein the second detected edge is identified from the first slope value and the second difference value.
-
-
9. The method according to claim 1, further comprising:
-
(f) calculating a plurality of block values, each block value comprising a mean of a plurality of second values; and
(g) verifying the detected edge using the plurality of neighbor block values.
-
-
10. The method according to claim 9, wherein step (f) comprises:
-
(f1) calculating a first block value, the first block value comprising a mean of a first plurality of second values;
(f2) calculating a second block value, the second block value comprising a mean of a second plurality of second values; and
(f3) computing a first block difference value, the first block difference value comprising an arithmetic difference between the first block value and the second block value;
wherein step (g) verifies the detected edge when the first block value is greater than a first block difference threshold.
-
-
11. The method according to claim 10, wherein step (f) further comprises:
-
(f4) calculating a third block value, the third block value comprising a mean of a third plurality of second values;
(f5) calculating a fourth block value, the fourth block value comprising a mean of a fourth plurality of second values; and
(f6) computing a second first block difference value, the second block difference value comprising an arithmetic difference between the third block value and the fourth block value;
wherein step (g) verifies the detected edge when the first block value is greater than a first block difference threshold and the second block value is greater than a second block difference threshold.
-
-
12. The method according to claim 1, further comprising:
-
(f) calculating a plurality of first block values, each of the first block values comprising a mean of a plurality of first values;
(g) calculating a plurality of second block values, each second block value comprising a mean of a plurality of second values; and
(h) verifying the detected edge using the first plurality of block values and second plurality of block values.
-
-
13. The method according to claim 12, wherein step (h) comprises:
-
(h1) calculating a plurality of first difference values, each of the first difference values comprising an arithmetic difference between one of the first block values and a selected pixel column;
(h2) calculating a plurality of second difference values, each of the second difference values comprising an arithmetic difference between one of the second block values and the selected pixel column;
(h3) confirming the detected edge when each of the first and second difference values are greater than a threshold value.
-
-
14. A method for detecting an edge of a document being scanned, comprising:
-
(a) scanning a portion of the document against a substantially light reflecting backing to obtain a first set of image data;
(b) scanning a portion of the document against a substantially light absorbing backing to obtain a second set of image data;
(c) calculating a set of first values from the first set of image data, each one of the first values being a first-order statistic;
(d) calculating a set of second values from the second set of image data, each one of the second values being a first-order statistic;
(e) calculating a set of third values from the second set of image data, each one of the third values being a second-order statistic;
(f) calculating a set of fourth values from the second set of image data, each one of the fourth values being a fourth-order statistic;
(g) determining a first edge detection from the set of first values and the set of second values;
(h) determining a second edge detection from the set of first values and the set of second values;
(i) determining a third edge detection from the set of first values, the set of second values and the set of fourth values; and
(k) reconciling the first edge detection, the second edge detection and the third edge detection to obtain a document edge. - View Dependent Claims (15, 16, 17)
(g1) determining a set of first difference values, each one of the first difference values being the difference between one of the first values and one of the second values;
(g2) determining a second difference value, the second difference value being the difference between two of the first difference values; and
(g3) identifying the first edge detection when the second difference value is greater than a threshold value.
-
-
16. The method according to claim 14, wherein step (h) comprises:
-
(h1) determining a first slope value, the first slope value being a function of the difference between a plurality of the third values;
(h2) generating a block sum value, the block sum value comprising the sum of a plurality of third values;
(h3) determining a second slope value, the second slope value being a function of the difference between a plurality of the second values; and
(h4) computing a product of the first slope value and the second slope value;
wherein the second edge detection is identified from the product, the first slope value and the block sum.
-
-
17. The method according to claim 14, wherein step (i) comprises:
-
(i1) determining a first slope value, the first slope value being a function of the difference between a plurality of the fourth values;
(i2) determining a set of first difference values, each one of the first difference values being the difference between one of the first values and one of the second values; and
(i3) determining a second difference value, the second difference value being the difference between two of the first difference values;
wherein the third edge detection is identified from the first slope value and the second difference value.
-
Specification