US 9,349,085 B1 · Methods and system to decode hidden images

Abstract

In one implementation, a computer-implemented method for identifying hidden features in digital images includes: detecting, by the computer system, one or more visual features in a digital image; applying one or more edge detection filters to the digital image to generate a modified digital image; detecting one or more candidate hidden features that are included in the modified digital image; comparing the one or more visual features in the digital image with the one or more candidate hidden features; determining whether a hidden image is present in the digital image based on the comparison of the one or more visual features in the digital image with the one or more candidate hidden features; and providing, by the computer system and in response to determining that a hidden image is present in the digital image, information that identifies that the hidden image has been detected.

Claims20

Dependent claims

A computer-implemented method for identifying hidden features in digital images, the method comprising:

accessing, by a computing device, a digital image;
repeatedly applying, by the computing device, one or more edge detection filters to the digital image until a hidden image is detected, wherein each iteration of the repeatedly applying comprises:
selecting, by the computing device at each iteration, one or more parameters for the one or more edge detection filters,
generating, by the computing device at each iteration, a modified digital image by applying the one or more edge detection filters to the digital image using the one or more parameters, and
detecting, by the computing device at each iteration, whether the hidden image is visible in the modified digital image, wherein the hidden image is visible when at least a portion of the hidden image's contours have at least a threshold level of contrast with regard to other portions of the modified digital image that are adjacent to the hidden image;
and
outputting, by the computing device and in response to detecting the hidden image, information identifying the hidden image detected from the digital image.

4 more elements

A computing device for identifying hidden features in digital images, the computing device comprising:

one or more processors;
and
one or more storage devices storing instructions that, when executed, cause the one or more processors to perform operations comprising:
accessing a digital image;
repeatedly applying one or more edge detection filters to the digital image until a hidden image is detected, wherein each iteration of the repeatedly applying comprises:
selecting, at each iteration, one or more parameters for the one or more edge detection filters,
generating, at each iteration, a modified digital image by applying the one or more edge detection filters to the digital image using the one or more parameters, and
detecting, at each iteration, whether the hidden image is visible in the modified digital image, wherein the hidden image is visible when at least a portion of the hidden image's contours have at least a threshold level of contrast with regard to other portions of the modified digital image that are adjacent to the hidden image;
and
outputting, in response to detecting the hidden image, information identifying the hidden image detected from the digital image.

7 more elements

Dependencies are inferred from the claim text.

Methods and system to decode hidden images

Life of this patent

Methods and system to decode hidden images

Life of this patent

Abstract

Claims20