A system comprising one or more processors, and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations comprising: displaying, one or more instructions on a user interface of a mobile device to instruct a user to capture each respective image of a prescription label; determining, using contrast, a location of each respective image in the set of images that is associated with the respective different portions of the prescription label on the medication package; reconstructing each of the respective different portions of the prescription label on the medication package as a flattened reconstruction of the respective different portions of the prescription label; and providing for display on the user interface a reconstructed prescription label. Other embodiments are disclosed herein.

Methods and apparatus for blending unknown pixels in overlapping images. In one embodiment, an action camera captures two hyper-hemispherical fisheye images that are stitched to a 360 panorama. In order to remove exposure differences between the two cameras, the images are pre-processed prior to multiband blending. The pre-processing leverages image information from pixels to make informed guesses about pixels that were not captured. In particular, various pixels with different knowability (e.g., known, unknown, consistent, and conflicting) may be handled differently so as to emphasize/de-emphasize their importance in pre-processing.

A glare reducing optical recognition system that recognizes alphanumeric text wherein the system includes a first light emitter that emits light in a first direction and a second light emitter that emits light in a second direction different from the first direction. The system includes an image capturing device that captures a first image of alphanumeric text illuminated by the first light emitter emitting light in the first direction, and a second image of the alphanumeric text illuminated by the second light emitter emitting light in the second direction. The system includes an image processor that constructs a glare reduced image by comparing sections of the first image with corresponding sections of the second image and selecting the section with the least luminosity to populate the corresponding section of the glare reduced image. The system may include a character recognition processor, a label producing apparatus, and/or a conveyance system.

One embodiment of the present invention sets forth a technique for extracting data from a document. The technique includes determining, via execution of one or more machine learning models, a first set of bounding boxes for a first set of values associated with a first key within the document and a second set of bounding boxes for a second set of values associated with a second key within the document. The technique also includes generating a first set of mappings between a list of items in the document and the first set of bounding boxes and a second set of mappings between the first and second sets of bounding boxes based on locations of the bounding boxes. The technique further includes determining, for a given item, one or more associated bounding boxes in the first and second sets of bounding boxes based on the mappings.

A system comprises one or more processors and one or more non-transitory computer-readable storage devices storing computing instructions configured to run on the one or more processors and cause the one or more processors to perform operations comprising: receiving a set of images of respective different portions of a label on a package. The operations also can include: determining, using contrast, one or more respective locations in the images of the set of images that are associated with the respective different portions of the label on the package. The operations further can include: providing, for display on a user interface, a flattened reconstruction of the respective different portions of the label on the package based at least in part on the one or more respective locations that have been determined. Other embodiments and features are also disclosed.

A multi-module imaging system and an image-synchronization method are provided. The multi-module imaging system includes a photographic component having multiple photosensitive modules, an image signal processor and a data processor. The different photosensitive modules generate multiple sets of motion images respectively. The image signal processor then retrieves continuous frame images from each of the sets of motion images. The data processor obtains multiple frames generated at the same time from the continuous frame images and generates a composite frame that vertically combines the multiple frames by performing a vertical encoding procedure. Therefore, the multiple sets of motion images are encoded to be continuously-outputted multiple composite frames. Accordingly, the multi-module imaging system can synchronously output the frames that are generated by different photosensitive modules.

Apparatus for scanning and recognizing characters comprises: an optical sensor for capturing images, which optical sensor carries out continuous shooting of the scanned characters to obtain an image frame sequence containing the scanned characters, and the content of an image frame partly overlaps content of the previous image frame in the sequence; and a control module for processing the images and recognizing the characters. The control module divides the image frames in the image frame sequence into groups of image frames including reference frames, skip frames and predictive frames according to the overlapping contents, and combines the standard frames and the predictive frames into a panorama image, taking a group of image frames as a unit, and carries out character recognition after performing skew correction based on the panorama image, to obtain the character codes of the scanned characters. The skip frames can be skipped directly, increasing the splicing speed.

Aspects and implementations provide for techniques of fast and efficient identification of objects of multiple types in electronic documents. The disclosed techniques include, for example, processing, using a machine learning model (MLM), an image of a document to generate a plurality of pixel-level maps (PLMs), characterizing associations of pixels of the image with various object types. The MLM includes a backbone neural network (NN) processing the image and generating a feature tensor for the image. The MLM further includes a plurality of classification NNs that process the feature tensor and generate PLMs. The techniques further include generating, using the PLMs, an object-level map identifying placement of one or more objects in the document. The classification NNs may be trained together (end-to-end) with the backbone NN.

A method for optical character recognition (OCR) on a surface, comprising: activating an image capture device; scanning the surface to obtain a plurality of scans of sections of the surface; performing OCR on the plurality of scans; separating the OCRed content into layers for each of the plurality of scans; merging these layers into single layers; and combining the single layers into a unified image.

A multi-module imaging system and an image-synchronization method are provided. The multi-module imaging system includes a photographic component having multiple photosensitive modules, an image signal processor and a data processor. The different photosensitive modules generate multiple sets of motion images respectively. The image signal processor then retrieves continuous frame images from each of the sets of motion images. The data processor obtains multiple frames generated at the same time from the continuous frame images and generates a composite frame that vertically combines the multiple frames by performing a vertical encoding procedure. Therefore, the multiple sets of motion images are encoded to be continuously-outputted multiple composite frames. Accordingly, the multi-module imaging system can synchronously output the frames that are generated by different photosensitive modules.