Abstract: A camera is used to acquire images. Labels are detected in the images. The labels contain a barcode and product information. The product information is analyzed (e.g., by optical character recognition) to obtain a plurality of scan descriptions. Scan descriptions are matched with catalog descriptions to obtain stock keeping units (SKUs). The SKUs are mapped to locations within an environment based on position data of the camera at the time images are acquired.

Abstract: Image analysis is used to map objects in an arrangement. For example, images of a retail shelf are used to map items for sale on the retail shelf A first vector can used to identify a relative position of a first item on a shelf to a shelving diagram, and a second vector can be used to identify a relative position of a second on the shelf to the shelving diagram, using locations of optical codes (e.g., barcodes). Absolute positions can be calculated. In some configurations, multiple images having different fields of view are matched to an overview image.

Abstract: A mechanized store uses a mobile device to authenticate the user. Items removed from one or more displays of the mechanized store by the user are tracked and a list of items removed by the user is updated. The list of items removed is linked with an account of the user.

Abstract: An image is acquired by a camera. The image has a first set of characters and a second set of characters. The first set of characters are classified as an identifier. The second set of characters are classified as data associated with the identifier. The image is divided to create an image segment. The image segment includes the first set of characters and not the second set of characters. The first set of characters are decoded in the image segment to generate a first character string. The second set of characters are decoded to generate a second character string. The first character string is linked to the second character string based on classifying the first set of characters as the identifier and the second set of characters as the data associated with the identifier.

Abstract: Depth information from a depth sensor, such as a LiDAR system, is used to correct perspective distortion for decoding an optical pattern in a first image acquired by a camera. Image data from the first image is spatially correlated with the depth information. The depth information is used to identify a surface in the scene and to distort the first image to generate a second image, such that the surface in the second image is parallel to an image plane of the second image. The second image is then analyzed to decode an optical pattern on the surface identified in the scene.

Abstract: Selection of on optical pattern in a scene is identified by overlaying, on a display, an indicator of a detected optical pattern identifying a location of the optical pattern in one or more images, receiving a user input on the display at a position that does not overlap the location of the optical pattern, and presenting information related to the optical pattern, based on receiving the user input, even though the position of user input did not overlap the location of the optical pattern. The user input can be received at a detached selection indicator and/or using an adaptive input area.

Abstract: For scanning optical patterns, such as two-dimensional QR codes, with a mobile device at increased distances, a first image is acquired. A region of interest likely containing the optical pattern in the first image is identified. The mobile device then zooms in on the region of interest and a second image is acquired. The optical pattern is then decoded using the second image.

Abstract: A method of image analysis is provided for recognition of a pattern in an image. The method includes receiving a plurality of images acquired by a camera, where the plurality of images include a plurality of optical patterns in an arrangement. The method also includes matching the arrangement to a pattern template, wherein the pattern template is a predefined arrangement of optical patterns. The method also includes identifying an optical pattern of the plurality of optical patterns as a selected optical pattern based on a position of the selected optical pattern in the arrangement. The method also includes decoding the selected optical pattern to generate an object identifier and storing the object identifier in a memory device.

Abstract: A memory device is provided including instructions that, when executed, cause one or more processors to perform the steps including receiving a plurality of images acquired by a camera, the plurality of images including a plurality of optical patterns, wherein an optical pattern of the plurality of optical patterns encodes an object identifier. The steps include presenting the plurality of images comprising the plurality of optical patterns on a display, and presenting a plurality of visual indications overlying the plurality of optical patterns in the plurality of images. The steps also include identifying a selected optical pattern of the plurality of optical patterns based on a user action and a position of the selected optical pattern in one or more of the plurality of images. The steps also include decoding the selected optical pattern to generate the object identifier and storing the object identifier in a second memory device.

Abstract: Images of optical codes are mapped to an overview image to localize optical codes within a space. By localizing optical codes, information about locations of various products can be ascertained. One or more techniques can be used to map the images of optical codes to the overview image. The overview image can be a composite image formed by stitching together several images.

Abstract: Image analysis using visual geometry as an anchor for optical character recognition can be configured to receive an image acquired by a camera. The image is analyzed to detect a location within the image having a specified geometry. The specified geometry can be a predefined, visual geometry. The image is divided to create an image segment, where the image segment is based on the location of the specified geometry within the image. The image segment is analyzed to detect one or more characters within the image segment. The one or more characters in the image segment are decoded. A character string is generated based on decoding the one or more characters in the image segment.

Abstract: A mechanized store uses a mobile device to authenticate the user. Items removed from one or more displays of the mechanized store by the user are tracked and a list of items removed by the user is updated. The list of items removed is linked with an account of the user.

Abstract: Image data from a camera and depth information from a depth sensor, such as a LiDAR system, are used to segment an image for decoding an optical pattern. The image data is spatially correlated with the depth information. The depth information is used to partition the image into one or more foreground segments and one or more background segments. Scanning for the optical pattern is performed on the one or more foreground segments.

Abstract: For scanning optical patterns, such as two-dimensional QR codes, with a mobile device at increased distances, a first image is acquired. A region of interest likely containing the optical pattern in the first image is identified. The mobile device then zooms in on the region of interest and a second image is acquired. The optical pattern is then decoded using the second image.

Abstract: A camera on a robot is used to acquire images of a shelving unit. Locations of labels are detected and cropped from the images to form segments. The segments are analyzed to obtain scan descriptions, without decoding barcodes on the labels. The scan descriptions are compared to catalog descriptions to match scan descriptions to catalog descriptions. Products can then be mapped within an environment.

Abstract: For scanning optical patterns, such as two-dimensional QR codes, with a mobile device at increased distances, a first image is acquired. A region of interest likely containing the optical pattern in the first image is identified. The mobile device then zooms in on the region of interest and a second image is acquired. The optical pattern is then decoded using the second image.

Abstract: For scanning optical patterns, such as two-dimensional QR codes, with a mobile device at increased distances, a first image is acquired. A region of interest likely containing the optical pattern in the first image is identified. The mobile device then zooms in on the region of interest and a second image is acquired. The optical pattern is then decoded using the second image.

Abstract: Image analysis is used to map objects in an arrangement. For example, images of a retail shelf are used to map items for sale on the retail shelf. A first vector can used to identify a relative position of a first item on a shelf to a shelving diagram, and a second vector can be used to identify a relative position of a second on the shelf to the shelving diagram, using locations of optical codes (e.g., barcodes). Absolution positions can be calculated. In some configurations, multiple images having different fields of view are matched to an overview image.

Abstract: Images of optical codes are mapped to an overview image to localize optical codes within a space. By localizing optical codes, information about locations of various products can be ascertained. One or more techniques can be used to map the images of optical codes to the overview image. The overview image can be a composite image formed by stitching together several images.

Abstract: Image analysis is used to track multiple optical patterns, such as barcodes. Many applications are becoming web-based. However, web-based applications can have less computational resources than a native application. For example, a native application can be used to track barcodes based on decoding barcodes from a plurality of images. However, decoding barcodes can be computationally intense and cause lag when moved to a web-based platform. To reduce computational resources used for decoding barcodes, barcodes are tracked in several frames and decoded only periodically for a web-based application used to decode barcodes. Positions of barcodes can be tracked relative to each other to form a digital shelf. The digital shelf can be used to visualize a state of a shelf.