This disclosure relates to advanced signal processing technology including signal encoding. One combination disclosed in the description is an image processing method comprising: accessing a design file to obtain image data, the image data comprising a plurality of color separations or channels, in which the image data comprises at least a 1D or 2D barcode represented therein and a first encoded signal encoded therein, the 1D or 2D barcode comprising a first plural-bit code and the first encoded signal comprising a second plural-bit code; operating a barcode reader to analyze the image data to decode the 1D or 2D barcode to obtain the first plural-bit code; operating a signal decoder to analyze one or more combinations of color separations or channels of the plurality of color separations or channels to decode the first encoded signal to obtain the second plural-bit code; determining whether the second plural-bit code conflicts with the first plural-bit code; and identifying a conflict based on said act of determining. Of course, other features and combinations are described as well.

A system, method and computer program product for protecting a deep neural network image classifier against receiving perturbed images. A plurality of watermark bits are embedded into an original digital image intended for the deep neural network image classifier. The watermarked image is transmitted through a potentially adversarial environment. A potentially perturbed image intended for the deep neural network image classifier is received from the potentially adversarial environment. The potentially perturbed image is determined to be an adversely modified or benign image by determining whether the potentially perturbed image includes a plurality of embedded bits matching the plurality of watermark bits embedded into the original digital image. The potentially perturbed image is prevented from being provided to the deep neural network image classifier in response to determining that the potentially perturbed image is the adversely modified image.

Digital watermarking is adapted for the variable data printing. A reference signal serves as a proxy for optimizing the embedding a watermark in a host image to be printed. Using the reference signal, embedding parameters are generated, which are a function of constraints such as visual quality and robustness of the machine readable data. Adjustments needed to embed a unique payload in each printed piece are generated using the embedding parameters. These adjustments are stored in a manner that enables them to be efficiently obtained and applied within the RIP or press during operation of the press. Various other methods, system configurations and applications are also detailed.

A method for watermarking a three-dimensional object is disclosed. The three-dimensional object is represented by a mesh. A mesh comprises a plurality of vertices. The method further comprises computing an original thickness signature for said mesh from a plurality of thickness values, wherein a thickness value is computed for a vertex of the mesh; determining a target thickness signature, wherein the target thickness signature is a function of a watermark payload and of the original thickness signature; and modifying a position of at least one vertex of the mesh wherein a thickness signature computed for the modified mesh reaches the target thickness signature and wherein a distortion constraint between the mesh and the modified mesh is satisfied. A method for detecting a watermark in a three-dimensional object, a three-dimensional object carrying a watermark and, devices for implementing the methods are further disclosed.

A system and method to watermark an uncompressed content received at a client device in a compressed form and encrypted by at least one content key, said content key as well as watermark instruction forming Conditional Access Module (CAS) data, said CAS data being encrypted by a transmission key and comprising at least one signature to authenticate the CAS data, said client device comprising a CAS configured to process the CAS data, a descrambler having an input to receive the encrypted compressed content and an output to produce an compressed content, a decoder to convert the compressed content into uncompressed content, a watermark inserter connected to the output of the decoder, a secure activation module connected with the watermark inserter, a secure element connected with the watermark inserter and the secure activation module.

In one aspect, assembly of multi-part food packaging is checked by reference to payloads of steganographically-encoded digital watermarks printed across plural components of the packaging. Marking all surfaces of the packaging components allows arbitrary orientation of feed stock in assembly equipment, and wide latitude in placement of inspection cameras along the packaging line. In another aspect, a scanner at a retail checkout station is alert to any gap detected in steganographic encoding on retail product packaging and, if found, alerts an operator to possible presence of an adhesive label with a misleading barcode. A great variety of others features and arrangements are also detailed.

In one embodiment, a watermark is embedded in a sequence of video frames, for each one of the video frames, a set of N rectangular patches, two palettes of pixel values in a selected color space, such that the two palettes are denoted as P0 and P1, and P0P1, and in each one of the N patches a processor which chooses one of P0 and P1 according to a value of a payload bit to be encoded, a calculator which calculates one of a variance of pixel values in the frame, and edginess for the pixel values in the frame, thereby determining a calculated value, and a processor which determines if the calculated value is beneath a given threshold value, if the calculated value is beneath the given threshold value the processor is operative to calculate a function of the pixel values, the closest value to a result of the calculation of the function in the chosen palette is chosen, and a replacer which replaces the pixel values within the patch with the chosen closest value. Related systems, apparatus and methods are also described.

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.

This disclosure relates to advanced signal processing technology including signal encoding. One combination includes an apparatus comprising: memory for storing image data, the image data comprising a plurality of color separations or channels, in which the image data comprises at least a first type of machine-readable symbology comprising a 1D barcode represented therein and a second type of machine-readable symbology comprising a first signal represented therein, in which the second type of machine-readable symbology comprises a different type of machine-readable symbology relative to the first type of machine-readable symbology, the 1D barcode comprising a first plural-bit code and the first signal comprising a second plural-bit code; a barcode reader configured to analyze the image data to decode the 1D barcode to obtain the first plural-bit code; a signal decoder configured to analyze one or more color separations or channels of the plurality of color separations or channels to decode the first signal to obtain the second plural-bit code; one or more processors configured to determine whether the second plural-bit code and the first plural-bit code conflict; and to identify a conflict based on a conflict determination. Of course, other features and combinations are described as well.

A method and apparatus for embedding a digital watermark in image content that is not visible to the human eye is performed on single-sensor digital camera images (often called raw images) from a pixel-array. The raw image is transformed to generate preprocessed image coefficients, a watermark message is encrypted using a first key; the encrypted watermark message is randomized using a second key to form a watermark; and the watermark is embedded in randomly selected preprocessed image coefficients.