Methods and systems for signal processing
An object (e.g., a driver's license) is tested for authenticity using imagery captured by a consumer device (e.g., a mobile phone camera). Corresponding data is sent from the consumer device to a remote system, which has secret knowledge about features indicating object authenticity. The phone, or the remote system, discerns the pose of the object relative to the camera from the captured imagery. The remote system tests the received data for the authentication features, and issues an output signal indicating whether the object is authentic. This testing involves modeling the image data that would be captured by the consumer device from an authentic object—based on the object's discerned pose (and optionally based on information about the camera optics), and then comparing this modeled data with the data sent from the consumer device. A great variety of other features and arrangements are also detailed.
1. A method useful for judging authenticity of an object by reference to features encoded therein, the method being performed by a camera-equipped consumer device that captured an image of the object, and also involving a remote system that has key data that is not available to the consumer device, the method comprising the acts:
processing data corresponding to said image, said processing including computing intra-image gradient information for plural pixel locations in the image, said computing including comparing, for each of said pixel locations, a value of a pixel at said location with values of one or more neighboring pixels, said computing yielding a value that can be represented with five bits as the intra-image gradient information for said pixel location, said processing being performed by a processor in the consumer device configured to perform such act;
sending the computed intra-image gradient information for N pixel locations in the image to the remote system, where N is less than all the pixel locations in the image, and the sent intra-image gradient information consists of one value for each of said N locations; and
in response to said sending, receiving data at the consumer device indicating whether the remote system was able to confirm the presence of said features in said object from said sent intra-image gradient information;
wherein the consumer device learns whether the object depicted in the captured image includes the encoded features—while not having key data necessary for such determination, thereby enhancing security; and
wherein the remote system determines whether the object depicted in the captured image includes the encoded features—while not having access to the complete captured image, thereby enhancing privacy.
2. The method of claim 1 that includes generating pose information including X-offset, Y-offset, scale, and rotation information, said pose information indicating relative positioning of the object and the camera.
3. The method of claim 2 that includes generating said pose information by analysis of the data corresponding to the image performed by the consumer device, and sending said generated pose information from the consumer device to the remote system.
4. The method of claim 1 that further includes the consumer device receiving information sent by the remote system that provides specifications for the intra-image gradient information to be sent by the consumer device to the remote system.
5. The method of claim 1 wherein N is less than half the pixel locations in the image.
6. The method of claim 1 wherein N is less than ten percent of the pixel locations in the image.
7. The method of claim 1 wherein said features are too small to be distinguished in the image captured by said camera.
8. The method of claim 1 in which the sending act comprises sending a five bit integer for each of said N pixel locations.
9. A method useful for judging authenticity of an object by reference to features encoded therein, the method being performed by a remote system, and also involving a camera-equipped consumer device that captured an image of said object, the method comprising the acts:
receiving information at the remote system, sent from the consumer device, the received information including intra-image gradient information computed by the consumer device for N pixel locations in said image of the object, where N is less than all the pixel locations in the image, said intra-image gradient information consisting of one value for each of said N locations;
with a hardware processor in the remote system, processing (a) the received intra-image gradient information, and (b) key information, to yield result data, the key information not being available to the camera-equipped consumer device; and
sending at least some of the result data from the remote system to the consumer device, to confirm the presence of said features encoded in the object;
wherein the consumer device learns whether the object depicted in the captured image includes the encoded features—while not having key data necessary for such determination, thereby enhancing security; and
wherein the remote system determines whether the object depicted in the captured image includes the encoded features—while not having access to the complete captured image, thereby enhancing privacy.
10. The method of claim 9 that further includes:
obtaining pose information about a spatial relationship between the object and the camera of the consumer device;
processing (a) the received intra-image gradient information, (b) key information, and (c) the pose information, to yield said result data.
11. The method of claim 10 in which obtaining the pose information comprises receiving the pose information from the consumer device.
12. The method of claim 10 in which obtaining the pose information comprises calculating the pose information at the remote system, from the received intra-image gradient information.
13. The method of claim 10 in which the pose information comprises X-offset, Y-offset, scale, and rotation information.
14. The method of claim 9 that further includes sending data from the remote system to the consumer device, the sent data providing specifications for the intra-image gradient information to be sent by the consumer device to the remote system.
15. The method of claim 9 in which N is less than half the pixel locations in said image.
16. The method of claim 9 in which N is less than ten percent of the pixel locations in said image.
17. The method of claim 9 wherein said features are too small to be distinguished in the image captured by said camera.
18. A non-transitory computer readable medium containing instructions that configure a computer system to confirm the presence of features encoded in an object, to aid in judging authenticity of the object, the object being depicted in an image captured by a camera-equipped consumer device, by performing acts including:
receiving information at said computer system, sent from the consumer device, the received information including intra-image gradient information computed by the consumer device for N pixel locations in said image of the object, where N is less than all the pixel locations in the image, said intra-image gradient information consisting of one value for each of said N locations;
processing (a) the received intra-image gradient information, and (b) key information, to yield result data; and
sending at least some of the result data from the computer system to the consumer device, to confirm the presence of said features encoded in the object;
wherein the consumer device learns whether the object depicted in the captured image includes the encoded features—while not having key data necessary for such determination, thereby enhancing security; and
wherein the remote system determines whether the object depicted in the captured image includes the encoded features—while not having access to the complete captured image, thereby enhancing privacy.
19. The computer readable medium of claim 18 in which the received intra-image gradient information is for less than half of the pixel locations in said image of the object.
20. The computer readable medium of claim 18 in which the received intra-image gradient information is for less than ten percent of the pixel locations in said image of the object.