Document authentication using template matching with fast masked normalized cross-correlation
View Patent ↗Techniques are described for authenticating security documents having security images that incorporate multiple security features. The techniques may produce robust template matching results in situations of lighting unevenness, even with stronger occluding objects. The techniques may be particularly useful in validating a security document having a security image composed of one or more “virtual” retroreflective images formed over a background of a repeating retroreflective image. The virtual retroreflective images within the security image provide strong signals that may dominate analysis and validation of the background retroreflective image, thereby resulting incorrect authentication. The techniques provide a modified normalized cross-correlation analysis that masks out the strong signals contributed by the additional security features, such as the retroreflective virtual images, while still allowing for fast and efficient template matching to be performed with respect to the background image.
1. A document authentication device comprising:
an image capture interface that receives a captured image of at least a portion of an article, wherein the portion of the article includes an image having a first retroreflective feature and a second retroreflective feature;
a masking image generator that generates a masking image from the captured image;
a fast masked normalized cross-correlation (FMNCC) module that applies the masking image to the captured image to obtain a masked image and calculates a modified normalized cross-correlation between a reference image associated with the first retroreflective feature and the masked image; and
a display that outputs indicia of one or more matches between the reference image and the captured image.
2. The authentication device of claim 1 ,
wherein the FMNCC module modifies the calculated normalized cross-correlation with a masking effect modifier representing the ratio of the size of the reference image to a masked area at each matching region.
3. The authentication device of claim 1 ,
wherein the masking image and the captured image are comprised of a plurality of pixels, and
wherein the masking image generator generates the masking image by setting a pixel of the masking image to a first value when a corresponding pixel of the captured image has a brightness value outside a predefined range of brightness values, and setting the pixel of the masking image to a second value when the corresponding pixel of the captured image has a brightness value within the pre-defined range of brightness values.
4. The authentication device of claim 1 , wherein the FMNCC module determines matching regions within the captured image based on the calculated modified normalized cross-correlation, and wherein the display displays the determined matching regions and a correlation score corresponding to each determined matching region.
5. The authentication device of claim 1 , wherein the article is one of a passport, a credit card, an identification card, a birth certificate, or a security document.
6. The authentication device of claim 1 , wherein the FMNCC module calculates the modified normalized cross-correlation using a fast Fourier transform.
7. The authentication device of claim 1 , further comprising:
an image storage module that stores the captured image and a library of reference images that includes the reference image; and
a user interface that receives user input selecting the reference image from the library of reference images, wherein the authentication device retrieves the selected reference image from the image storage module.
8. The authentication device of claim 1 , further comprising:
an image storage module that stores the captured image and a library of reference images that includes the reference image,
wherein an automatic document identifier selects the reference image from the library of reference images based on characteristics of the captured image, wherein the authentication device retrieves the selected reference image from the image storage module.
9. A document authentication system comprising:
an image capture device that captures an image of at least a portion of an article, wherein the portion of the article includes an image having a first retroreflective feature and a second retroreflective feature; and
a host system that comprises:
a masking image generator that generates a masking image from the captured image; and
a fast masked normalized cross-correlation (FMNCC) module that applies the masking image to the captured image to obtain a masked image and calculates a modified normalized cross-correlation between a reference image associated with the first retroreflective feature and the masked image, and outputs indicia of one or more matches between the reference image and the captured image.
10. The authentication system of claim 9 , wherein the FMNCC module modifies the calculated normalized cross-correlation with a masking effect modifier representing the ratio of the size of the reference image to a masked area at each matching region.
11. The authentication system of claim 9 , wherein the second retroreflective feature is a retroreflective virtual image, and wherein the host system removes at least a portion of the retroreflective virtual image from the captured image by applying the masking image to the captured image.
12. The authentication system of claim 9 , further comprising a light source that illuminates the article, wherein the light source is arranged at an angle relative to a viewing position, and wherein the image capture device is arranged at the viewing position.
13. The authentication device of claim 2 , wherein the masking effect modifier is of the form
{
{
M
t
×
N
t
}
∑
x
,
y
m
(
x
+
u
,
y
+
v
)
}
o
,
where M t and N t define the dimension of the reference image, m(x, y) represents the masking image, and α represents the modification strength.
14. The authentication device of claim 1 , wherein the second retroreflective feature is a retroreflective virtual image, and wherein the FMNCC module applies the masking image to the captured image to remove at least a portion of the retroreflective virtual image from the captured image.