Computer-implemented method for detecting and decoding one or more watermarks stored within one or more watermarked regions of an image
AssigneeSasha ApS
InventorsMatthew Helmi Leth LARSEN, Tu BUI, Zhuha Olena OLEKSANDRIVNA
Life of this patent
Estimating the term…
Abstract
A computer-implemented method for detecting and decoding a watermarked image is provided, the method including obtaining the watermarked image; determining an orientation of the watermarked image by processing a first trained data-driven model, wherein the watermarked image is fed as a digital input to the first trained data-driven model; and aligning the watermarked image in accordance with the orientation.
Claims20
A computer-implemented method for detecting and decoding a watermarked image, the method comprising:
- obtaining the watermarked image;
- determining an orientation of the watermarked image by processing a first trained data-driven model, wherein the watermarked image is fed as a digital input to the first trained data-driven model;
- and
- aligning the watermarked image in accordance with the orientation.
A system for detecting and decoding a watermarked image, the system comprising:
- a processor,
- wherein the processor is configured to perform the following steps:
- obtaining the watermarked image;
- determining an orientation of the watermarked image by processing a first trained data-driven model, wherein the watermarked image is fed as a digital input to the first trained data-driven model;
- and
- aligning the watermarked image in accordance with the orientation.
A non-transitory computer-readable medium with instructions stored thereon, the instructions causing a processor to perform a method for detecting and decoding a watermarked image, the method comprising:
- obtaining the watermarked image;
- determining an orientation of the watermarked image by processing a first trained data-driven model, wherein the watermarked image is fed as a digital input to the first trained data-driven model;
- and
- aligning the watermarked image in accordance with the orientation.
Dependencies are inferred from the claim text.