Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting and decoding a visually imperceptible or perceptible watermark. A watermark detection apparatus determines whether the particular image includes a visually imperceptible or perceptible watermark using detector a machine learning model. If the watermark detection apparatus detects a watermark, the particular image is routed to a watermark decoder. If the watermark detection apparatus cannot detect a watermark in the particular image, the particular image is filtered from further processing. The watermark decoder decodes the visually imperceptible or perceptible watermark detected in the particular image. After decoding, an item depicted in the particular image is validated based data extracted from the decoded visually imperceptible or perceptible watermark.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining a visually imperceptible or a visually perceptible watermark and outputting a result based on the determination. A watermark decoder receives an input image. The watermark decoder applies a decoder machine learning model to decode a watermarks at different levels of zoom. The water mark decoder determines whether a watermark was decoded to obtain a decoded watermark. The watermark decoder outputs a result based on the determination whether the watermark was decoded through application of the decoder machine learning model to the input image that includes outputting a zoomed output decoded through application of the decoder machine learning model to the input image.

A system may include an imaging system coupled to a host subsystem. The imaging system may include an image sensor that provides image frames to the host subsystem. The image sensor may include a data authentication subsystem that appends corresponding authentication data to each of the image frames. Each set of authentication data may be generated based on a subset of the image frame data (e.g., corresponding to image data generated by pixels defined by a sparse region-of-interest within the pixel array). The host subsystem may securely provide region-of-interest parameters to the image sensor to update the sparse region-of-interest in an adaptive manner to account for factors such as computational load of the host subsystem and authentication coverage for the entire pixel array.

Systems and methods are provided for determining a quantity of network location visitors that are likely generated or encouraged by specific offline events. A corresponding number of leads may then be attributed to and associated with those specific events. Ongoing conversion activity of those visitors may be tracked and associated with the offline events. Conversions of those visitors may be attributed entirely or partially to one or more specific offline events. The effectiveness of each offline may then be evaluated based on aggregate lead and conversion information.

Optical code signal components are generated and then transformed into signal bearing art that conveys machine readable data. The components of an optical code are optimized to achieve improved signal robustness, reliability, capacity and/or visual quality. An optimization program can determine spatial density, dot distance, dot size and signal component priority to optimize robustness. An optical code generator transforms tiles of an optical code or image embedded with the optical code into signal-bearing art using stipple, Voronoi, Delaunay or other graphic drawing methods so as to retain prioritized components of the optical code. The optical code is merged into a host image, such as imagery, text and graphics of a package or label, or it may be printed by itself, e.g., on an otherwise blank label or carton. A great number of other features and arrangements are also detailed.

An image processing method determines a geometric transform of a suspect image by efficiently evaluating a large number of geometric transform candidates in environments with limited processing resources. Processing resources are conserved by using complementary methods for determining a geometric transform of an embedded signal. One method excels at higher geometric distortion, and specifically, distortion caused by greater tilt angle of a camera. Another method excels at lower geometric distortion, for weaker signals. Together, the methods provide a more reliable detector of an embedded data signal in image across a larger range of distortion while making efficient use of limited processing resources in mobile devices.

Image processing technology embeds signal (e.g., digital watermarks) within imagery during a raster image process(or). One claim recites: an image processing method of embedding a signal within imagery using a raster image processing (RIP), comprising: obtaining a plurality of elements representing a signal; and modulating a plurality of print structures within the RIP according to the plurality of elements, in which said modulating varies density, and direction or angle, of the plurality of print structures, and in which said modulating introduces the signal within the imagery. Of course, other claims, combinations and technology are described too.

The geometric pose of a patch of watermark data is estimated based on the position of a similar, but non-identical, patch of information within a data structure. The information in the data structure corresponds to a tiled array of calibration patterns that is sampled along at least three non-parallel paths. In a particular embodiment, the calibration patterns are sampled so that edges are globally-curved, yet locally-flat. Use of such information in the data structure enables enhanced pose estimation, e.g., speeding up operation, enabling pose estimation from smaller patches of watermark signals, and/or enabling pose estimation from weaker watermark signals. A great variety of other features and arrangements are also detailed.

Signal processing devices and methods estimate transforms between signals using a least squares technique. From a seed set of transform candidates, a direct least squares method applies a seed transform candidate to a reference signal and then measures correlation between the transformed reference signal and a suspect signal. For each candidate, update coordinates of reference signal features are identified in the suspect signal and provided as input to a least squares method to compute an update to the transform candidate. The method iterates so long as the update of the transform provides a better correlation. At the end of the process, the method identifies a transform or set of top transforms based on a further analysis of correlation, as well as other results.

Differential modulation schemes encode a data channel within host signal or noisy environment in a manner that is robust, flexible to achieve perceptual quality constraints, and provides improved data capacity. Differential arrangements enable a decoder to suppress host signal or other background signal interference when detecting, synchronizing and extracting an encoded data channel. They also enable the incorporation of implicit or explicit synchronization components, which are either formed from the data signal or are complementary to it.