Abstract: 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.

Abstract: Inventory on a rack of store shelves is monitored by a camera-equipped system that senses when items have been removed. Image data is desirably sensed at plural spectral bands, to enhance item identification by digital watermark and/or other image recognition techniques. The system can be alert to the presence of nearby shoppers, and change its mode of operation in response, e.g., suppressing flash illumination or suspending image capture. The system may self-calibrate to the geometry of shelving in its field of view, and affine-correct captured imagery based on the camera's viewpoint. A great many other features and arrangements are also detailed.

Abstract: In computer vision systems that need to decode machine-readable indicia from captured imagery, it is critical to select imaging parameters (e.g., exposure interval, exposure aperture, camera gain, intensity and duration of supplemental illumination) that best allow detection of subtle features from imagery. In illustrative embodiments, a Shannon entropy metric or a KL divergence metric is used to guide selection of an optimal set of imaging parameters. In accordance with other aspects of the technology, different strategies identify which spatial locations within captured imagery should be successively examined for machine readable indicia, in order to have a greatest likelihood of success, within a smallest interval of time. A great variety of other features and arrangements are also detailed.

Abstract: A retail checkout system decodes machine-readable indicia from a composite image frame produced from a sequence of captured image frames. Different regions in the composite image are derived from different ones of the image frames in the captured sequence. Another embodiment generates a composite image frame from image frames captured with different camera focus settings. Still other embodiments concern neural networks, including their training to segment different items presented on a retail checkout surface. Other neural network embodiments discern on which of two items a machine readable indicia appears, when the visual context is ambiguous. A variety of other features and arrangements are also detailed.

Abstract: In computer vision systems that need to decode machine-readable indicia from captured imagery, it is critical to select imaging parameters (e.g., exposure interval, exposure aperture, camera gain, intensity and duration of supplemental illumination) that best allow detection of subtle features from imagery. In illustrative embodiments, a Shannon entropy metric or a KL divergence metric is used to guide selection of an optimal set of imaging parameters. In accordance with other aspects of the technology, different strategies identify which spatial locations within captured imagery should be successively examined for machine readable indicia, in order to have a greatest likelihood of success, within a smallest interval of time. A great variety of other features and arrangements are also detailed.

Abstract: In an illustrative system, a point-of-sale scanner is equipped to respond to multiple different symbologies printed on a single product. The scanner captures many frames per second, as products are swiped through a viewing volume. Each frame is decoded, yielding one or more payloads. A reconciliation module compares each newly-decoded payload against a list of payloads previously output by the module, to determine if the current payload is semantically-equivalent to a previously-output payload. If so, the previously-output payload is output again, in lieu of the just-decoded payload. If no equivalent is found, the current payload is output and added to the list for comparison against future payloads. A great number of other features and arrangements are also detailed.

Abstract: Authenticity of a sticker (e.g., a mark-down sticker on a retail item), or integrity of a closure (e.g., on a delivery bag or package), is confirmed by reference to spatial information. In some embodiments a fingerprint is formed from parameters describing spatial placement of a sticker or pattern on a substrate. In some embodiments a digital watermark pattern provides a spatial frame of reference within which one or more other features can be located. A great many other features and arrangements are also detailed.

Abstract: In computer vision systems that need to decode machine-readable indicia from captured imagery, it is critical to select imaging parameters (e.g., exposure interval, exposure aperture, camera gain, intensity and duration of supplemental illumination) that best allow detection of subtle features from imagery. In illustrative embodiments, a Shannon entropy metric or a KL divergence metric is used to guide selection of an optimal set of imaging parameters. In accordance with other aspects of the technology, different strategies identify which spatial locations within captured imagery should be successively examined for machine readable indicia, in order to have a greatest likelihood of success, within a smallest interval of time. A great variety of other features and arrangements are also detailed.

Abstract: Image data depicting a 2D machine-readable code is up-sampled and compressed with a lossy compression process before being sent from a client device to a remote server for code reading. The remote server decompresses the sent information, extracts a payload from the machine-readable code, and causes result information to be sent back to the client device for display or other action. The up-sampling and compression operations performed on the client device can employ software instructions that are downloaded to, and executed by, browser software on the client device. Many other features and arrangements are also detailed.

Abstract: In an illustrative system, a point-of-sale scanner is equipped to respond to multiple different symbologies printed on a single product. The scanner captures many frames per second, as products are swiped through a viewing volume. Each frame is decoded, yielding one or more payloads. A reconciliation module compares each newly-decoded payload against a list of payloads previously output by the module, to determine if the current payload is semantically-equivalent to a previously-output payload. If so, the previously-output payload is output again, in lieu of the just-decoded payload. If no equivalent is found, the current payload is output and added to the list for comparison against future payloads. A great number of other features and arrangements are also detailed.

Abstract: In computer vision systems that need to decode machine-readable indicia from captured imagery, it is critical to select imaging parameters (e.g., exposure interval, exposure aperture, camera gain, intensity and duration of supplemental illumination) that best allow detection of subtle features from imagery. In illustrative embodiments, a Shannon entropy metric or a KL divergence metric is used to guide selection of an optimal set of imaging parameters. In accordance with other aspects of the technology, different strategies identify which spatial locations within captured imagery should be successively examined for machine readable indicia, in order to have a greatest likelihood of success, within a smallest interval of time. A great variety of other features and arrangements are also detailed.

Abstract: In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed views—further minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. Logos may be identified and used—or ignored—in product identification. A great variety of other features and arrangements are also detailed.

Abstract: In an illustrative system, a point-of-sale scanner is equipped to respond to multiple different symbologies printed on a single product. The scanner captures many frames per second, as products are swiped through a viewing volume. Each frame is decoded, yielding one or more payloads. A reconciliation module compares each newly-decoded payload against a list of payloads previously output by the module, to determine if the current payload is semantically-equivalent to a previously-output payload. If so, the previously-output payload is output again, in lieu of the just-decoded payload. If no equivalent is found, the current payload is output and added to the list for comparison against future payloads. A great number of other features and arrangements are also detailed.

Abstract: The present disclosure relates to advanced image processing and encoded signal processing.

Abstract: In one aspect, a retail store has multiple sensors, including item sensors in a shopping cart for gathering data from a shopper-selected first item. At least certain of the sensor data is provided to a classifier, which was previously-trained (using data including optical data from known items) to identify possible item matches corresponding to data sensed from the first item. An item identification hypothesis that the shopper-selected first item has a particular identity is evaluated based on (a) information from the classifier, and (b) store layout data indicating items associated with a store location visited by the cart or shopper. The item identification hypothesis has a confidence score. If the score meets a criterion, an item of the hypothesized identity is added to a shopping tally. A great number of other features and arrangements are also detailed.

Abstract: In one aspect, a retail store includes a multitude of cameras, including a plurality of 3D cameras, and a plurality of other cameras. Certain of the cameras provide imagery from which a shopper's track through the store is monitored, and certain of the cameras are positioned to detect removal of items from store shelves. The store also includes a computer system that provides a database of information about store layout, indicating stock locations of different items. The computer system receives imagery from the cameras (or information derived from such imagery) and uses this data, together with information from the database and information derived from other sensors in the store, to produce a probabilistic tally of items selected by a store shopper. This tally includes an item bearing a barcode, but is produced without reading the barcode. Each item on the tally is associated with a confidence score that meets a computer system-determined threshold.

Abstract: Inventory on a rack of store shelves is monitored by a camera-equipped system that senses when items have been removed. Image data is desirably sensed at plural spectral bands, to enhance item identification by digital watermark and/or other image recognition techniques. The system can be alert to the presence of nearby shoppers, and change its mode of operation in response, e.g., suppressing flash illumination or suspending image capture. The system may self-calibrate to the geometry of shelving in its field of view, and affine-correct captured imagery based on the camera's viewpoint. A great many other features and arrangements are also detailed.

Abstract: In an illustrative system, a point-of-sale scanner is equipped to respond to multiple different symbologies printed on a single product. The scanner captures many frames per second, as products are swiped through a viewing volume. Each frame is decoded, yielding one or more payloads. A reconciliation module compares each newly-decoded payload against a list of payloads previously output by the module, to determine if the current payload is semantically-equivalent to a previously-output payload. If so, the previously-output payload is output again, in lieu of the just-decoded payload. If no equivalent is found, the current payload is output and added to the list for comparison against future payloads. A great number of other features and arrangements are also detailed.

Abstract: Inventory on a rack of store shelves is monitored by a camera-equipped system that senses when items have been removed. Image data is desirably sensed at plural spectral bands, to enhance item identification by digital watermark and/or other image recognition techniques. The system can be alert to the presence of nearby shoppers, and change its mode of operation in response, e.g., suppressing flash illumination or suspending image capture. The system may self-calibrate to the geometry of shelving in its field of view, and affine-correct captured imagery based on the camera's viewpoint. A great many other features and arrangements are also detailed.

Abstract: In some arrangements, product packaging is digitally watermarked over most of its extent to facilitate high-throughput item identification at retail checkouts. Imagery captured by conventional or plenoptic cameras can be processed (e.g., by GPUs) to derive several different perspective-transformed views—further minimizing the need to manually reposition items for identification. Crinkles and other deformations in product packaging can be optically sensed, allowing such surfaces to be virtually flattened to aid identification. Piles of items can be 3D-modelled and virtually segmented into geometric primitives to aid identification, and to discover locations of obscured items. Other data (e.g., including data from sensors in aisles, shelves and carts, and gaze tracking for clues about visual saliency) can be used in assessing identification hypotheses about an item. Logos may be identified and used—or ignored—in product identification. A great variety of other features and arrangements are also detailed.