Feature-based signal localization in digital capture systems
AssigneeDigimarc Corporation
InventorsVojtech Holub, Tomas Filler
Life of this patent
Estimating the term…
Abstract
The present disclosures relates generally to image signal processing and encoding signal within imagery. One claim recites a method comprising: obtaining data representing captured imagery, the captured imagery depicting packaging including digital watermarking, the digital watermarking including an orientation signal that is detectable in a transform domain; generating a n-dimensional feature set of the data representing captured imagery, the n-dimensional feature set representing the captured imagery in a spatial domain, where n is an integer great than 13; using a trained classifier to predict the presence of the orientation signal in a transform domain from the feature set in the spatial domain. Of course, other claims and combinations are provided too.
Claims24
A method comprising:
- obtaining data representing optically captured imagery, the optically captured imagery depicting packaging or a printed label, the packaging or printed label including an encoded signal, the encoded signal including an orientation signal that is detectable in a transform domain;
- generating a feature set of the data representing the optically captured imagery, the feature set representing the optically captured imagery in a spatial domain;
- using a trained classifier to predict the presence of the orientation signal in a transform domain from the feature set in the spatial domain.
An apparatus comprising:
- memory for buffering blocks of image data, the image data having been captured with a camera and depicting product packaging or a printed label;
- one or more processors programmed for:
- generating a spatial domain feature set representation of a block of image data;
- applying a machine-trained classifier to predict from the spatial domain feature set whether the block of image data includes a transform domain encoded signal.
A non-transitory computer readable medium comprising instructions stored therein, said instructions configure one or more processors for:
- obtaining data representing optically captured imagery, the optically captured imagery depicting packaging or a printed label, the packaging or printed label including an encoded signal, the encoded signal including an orientation signal that is detectable in a transform domain;
- generating a feature set of the data representing the optically captured imagery, the feature set representing the optically captured imagery in a spatial domain;
- using a trained classifier to predict the presence of the orientation signal in a transform domain from the feature set in the spatial domain.
Dependencies are inferred from the claim text.