Digimarc Corporation

Features from a style image are adapted to express a machine-readable code. For example, grains of rice depicted in a style image may be positioned to create a pattern mimicking that of a machine-readable code. The resulting output image can then be used as a graphical component in product packaging (e.g., as a background, border, or pattern fill), while also serving to convey a product identifier to a compliant reader device (e.g., a retail point-of-sale terminal). In some embodiments, a neural network is trained to apply a particular style image to machine readable codes. A great variety of other features and arrangements are also detailed.

A watermark image is stylized using a neural network. Stylization can employ a composite loss function in which a content loss term is based on image similarity to the watermark image itself, rather than based on similarity to layer activations produced by the neural network. The composite loss function may further avoid use of mean-squared error in connection with content loss, to allow the network freedom to produce a stylized image having a mean luma value that is remote from a mean luma value of the watermark image. An exemplary application generates texture patterns that simulate leather, yet convey plural-symbol payloads. Many other features and arrangements are also detailed.

Advanced image signal processing is used to generate detectability measures. Such detectability measures can predict robustness of embedded printed objects prior to printing. Other technology is described and claimed as well.

Watermarking media content, in combination with blockchain and distributed storage networks, prevents the proliferation of Deepfake content. Digital watermarks are embedded in the audio and video tracks of video clips of trusted content producers at the time the videos are captured or before they are distributed. The watermarks are detected at the social media network's portals, nodes, and back ends. The embedded watermark imparts a unique identifier to the video, that links it to a blockchain. The watermarks also allow video source tracking, integrity verification, and alteration localization. The watermark detectors can be standalone software applications, or they can be integrated with other applications. They are used to perform three main tasks: (1) they alert the Internet user when he watches an inauthentic news video, so that he may discard it, (2) they prevent a Deepfake content from propagating through the network (3) they perform forensic analysis to help track and remove Deepfake content postings.

A frictionless checkout system identifies items in retail transactions using multiple cameras and image processing. Ceiling-, bagging area- and/or shelf-mounted cameras capture video frames of items in a shopping cart from different perspectives to form an initial list of items associated with a shopper. A bagging-area camera captures video frames as items are removed from the cart and placed into bags. An image processing system, comprising object segmentation, digital watermark reading, and complementary methods such as barcode detection and object recognition, identifies the items and updates a transaction tally. Prior to unloading, the system maintains a global state of items and their positions in the cart. As items are removed, changes in this state are detected and verified at the bagging area. The system provides real-time identification, reduces manual scanning, and generates alerts when items detected in the cart are not added to the transaction tally.

A neural-network is trained to produce a visibility model based on just noticeable difference training data. The trained network is used to generate visibility masks to control the visual quality of image processing operations, such as digital watermarking, compression and other image editing operations. The visibility model is refined by iteratively adjusting for over and under predictions of a just noticeable difference threshold via an interactive user interface that pinpoints visual artifacts and captures updates from users, who provide adjustments such that the artifact is below what they perceive to be a just noticeable difference. Image processing, such as digital watermarking is performed in real time to provide the user with feedback to ascertain just noticeable difference levels corresponding to watermark embedding operations.

A steganographic digital watermark signal is decoded from host imagery without requiring a domain transformation for signal synchronization, thereby speeding and simplifying the decoding operation. In time-limited applications, such as in supermarket point-of-sale scanners that attempt watermark decode operations on dozens of video frames every second, the speed improvement allows a greater percentage of each image frame to be analyzed for watermark data. In battery-powered mobile devices, avoidance of repeated domain transformations extends battery life. A great variety of other features and arrangements, including machine learning aspects, are also detailed.

A thermoplastic resin is molded to define a container bearing a surface 2D code signal, such as a digital watermark pattern. In some arrangements, the mold dimensions are tailored, and process parameters are selected, so that an indentation in the mold gives rise to a corresponding indentation—rather than a corresponding protrusion—in the shaped plastic. In other arrangements, a metal mold is provided with a patterned resin on its surface to define the 2D code signal. The resin may take the form of a rigid or non-rigid insert that can be removed or re-worked to change the code signal without changing the metal mold. A variety of other improvements and arrangements are also detailed.

In one aspect, an elongated lighting module includes plural colors of LEDs that flash in a cyclical sequence to provide multi-spectral illumination. Several such modules can be arranged end-to-end to span a conveyor system that transports a stream of plastic waste items in a recycling center, enabling capture of differently-illuminated image frames depicting the items. Each module may include N LEDs of a first color (e.g., red) and M LEDs of a second color (e.g., blue), where N and M are different. Drive circuitry can be simplified by configuring the LEDs in strings of common colors, but with different counts. Electrical noise due to switching transients can be reduced by operating the LEDs at a low current when not being flashed. A great variety of other features and arrangements are also detailed.

A series of marks and absences of marks (voids) arrayed along one or a few mathematically-defined paths, define a message-conveying sparse path code. Multiple improvements in the forms of such codes, and related encoding and reading techniques, are detailed. Some such improvements provide greatly increased robustness and decreased visibility. A variety of other features and arrangements are also detailed.