Some implementations provide a computer-assisted method for embedding information in an identification document. The method includes: modulating information by varying lengths of line segments; generating a line code that includes the line segments with corresponding lengths; and applying the line code on an identification document such that the information is used to authenticate the identification document as genuine when a person presents the identification document to verify an identify of the person.

Techniques are disclosed for rendering a watermark on content in a manner as to not obfuscate or otherwise cause visual defects to data elements in the content. An example methodology implementing the techniques includes segmenting a watermark to be rendered on the content into multiple watermark pieces. Then, prior to rendering a particular watermark piece, a check is made to determine whether there is a data element at the location in the content at which the particular watermark piece is to be rendered. If a data element is detected at that location, the particular watermark piece is rendered such that the data element overlays the particular watermark piece to render the watermark as a masked watermark. Otherwise, if no data element is detected at that location, the watermark piece is rendered on the content to be visible. The process is repeated to render the remaining watermark pieces.

This disclosure relates to advanced signal processing technology including signal encoding and image processing. One implementation describes an encoding system including a masking module. The masking module scales or eliminates signal encoding adjustments based on an image's luminance or chrominance values. Of course, other implementations, combinations and claims are also provided.

Provided is a method of embedding and extracting watermark data that is robust against geometric distortion and low-quality photographing and for which the probability of successfully extracting watermark data for an original image is high, while the probability of successfully extracting the watermark data in the case of unauthorized copying is seriously impaired. The data embedding method according to an embodiment of the present invention comprises a step of converting the noise-based image using watermark data, and a step of adjusting the original image using the converted noise-based image.

Provided is a method of embedding and extracting watermark data that is robust against geometric distortion and low-quality photographing and for which the probability of successfully extracting watermark data for an original image is high, while the probability of successfully extracting the watermark data in the case of unauthorized copying is seriously impaired. The data embedding method according to an embodiment of the present invention comprises a step of converting the noise-based image using watermark data, and a step of adjusting the original image using the converted noise-based image.

Vision sensor dynamic watermarking via noise characterization are disclosed herein. An example device can capture an image by a first device, where the image comprising a pixel group has baseline noise characterization caused by a base noise profile for the first device. The device can produce a noise watermark to create a watermarked image, where the noise watermark can be produced by altering the baseline noise characterization to produce modified noise characterization. The device can also transmit the watermarked image to a receiver.

A printing system receives a print request containing patterns of marks to be printed on print media to produce printed output. A processor evaluates the print request to identify non-marking areas and identify different printing densities of the patterns of marks. The processor alters the patterns of marks to create hidden features on the printed output by adding a uniform printed background to the non-marking areas and adding different printing densities of fluorescent spots to different areas of the patterns of marks. The different printing densities of the fluorescent spots are based on the different printing densities of the patterns of marks and on the size of the hidden features. A printing device prints the print request on the print media to produce the printed output.

This disclosure relates to advanced image signal processing technology including encoded signals and digital watermarking. A printed object is provided including: a white substrate or printed white background comprising a first area; an ink mixture printed at a first plurality of spatial locations within the first area, the ink mixture printed such that the first area comprises a second plurality of spatial locations without the ink mixture, in which the first plurality of spatial locations is arranged in a 2-dimensional pattern conveying an encoded signal. The white substrate or white background and the ink mixture comprise a spectral reflectivity difference at or around 660 nm in a difference range of 8%-30%. Of course, other implementations, methods, packages, systems and apparatus are described in this patent document.

Methods and apparatus, including computer program products, are provided for watermarking neural networks. In some embodiments, there may be provided a method. The method may include determining, for a neural network, an activation layer output by a hidden layer of the neural network. The method may include selecting a watermarking process. The method may include applying the selected watermarking process to the activation layer output to generate a key. The method may include storing, for the neural network to enable detection of copying of the neural network, the selected watermarking process and the key. Related systems, methods, and articles of manufacture are also described.

This disclosure relates to advanced signal processing technology including signal encoding and image processing. One implementation describes an encoding system including a masking module. The masking module scales or eliminates signal encoding adjustments based on an image's luminance or chrominance values. Of course, other implementations, combinations and claims are also provided.