Systems and techniques are provided for automatically analyzing and processing domain-specific image artifacts and document images. A process can include obtaining a plurality of document images comprising visual representations of structured text. An OCR-free machine learning model can be trained to automatically extract text data values from different types or classes of document image, based on using a corresponding region of interest (ROI) template corresponding to the structure of the document image type for at least initial rounds of annotations and training. The extracted information included in an inference prediction of the trained OCR-free machine learning model can be reviewed and validated or corrected correspondingly before being written to a database for use by one or more downstream analytical tasks.

This invention overcomes disadvantages of the prior art by providing a vision system and method of use, and graphical user interface (GUI), which employs a camera assembly having an on-board processor of low to modest processing power. At least one vision system tool analyzes image data, and generates results therefrom, based upon a deep learning process. A training process provides training image data to a processor remote from the on-board processor to cause generation of the vision system tool therefrom, and provides a stored version of the vision system tool for runtime operation on the on-board processor. The GUI allows manipulation of thresholds applicable to the vision system tool and refinement of training of the vision system tool by the training process. A scoring process allows unlabeled images from a set of acquired and/or stored images to be selected automatically for labelling as training images using a computed confidence score.

A fresh food return processing system may include a mobile wireless communications device associated with a user to obtain an image of a previously purchased fresh food product, and initiate a mobile return of the previously purchased fresh food product based upon the image. A server may store a product purchase history associated with the user, obtain the image from the mobile wireless communications device, and provide the image to a machine learning algorithm to train the machine learning algorithm to identify the previously purchased fresh food product from the image. The server may also verify a purchase by the given user based upon comparing the identification of the image via the machine learning algorithm and the product purchase history associated with the given user, and generate and communicate a user credit redeemable toward a future purchase based upon verifying the purchase by the user.

Detection of textual phrases in a non-horizontal orientation at a scene is a critical problem. This disclosure relates to a processor implemented method to detect a text from multimedia content captured at a scene. An input original image is processed by a trained model to obtain an individual character with a bounding box on the original image. The original image is positioned by a gradient to obtain a rotated image if a number of detected characters is not equal to a number of expected characters on the original image. At least one missing character bounding box on the original image and on the rotated image are estimated to construct a horizontal text image if the number of detected characters is not equal to the number of expected characters on the rotated image. At least one missing character in the estimated bounding box is detected by at least one text returned from an optical character reader.

Imaging systems and techniques are described. An imaging system receives image data of an environment according to a first perspective. The imaging system detects an object in the image data. The imaging system generates, based on the image data, reprojected image data of at least a portion of the environment (e.g., representing at least the object) according to a second perspective that is distinct from the first perspective. In some examples, the imaging system generates and outputs an indicator of a status of the object based on the reprojected image data. In some examples, the indicator of the status of the object can indicate a change in the status of the object, such as a change in an illumination characteristic of a light source, a change in content displayed on a display screen, a change in the object's movement, and the like.

Systems and methods are described for generating image content. The systems and methods may include, in response to receiving a request to cause a sensor of a computing device to identify image content associated with optical data captured by the sensor, detecting a first sensor data stream having a first image resolution, and detecting a second sensor data stream having a second image resolution. The systems and method may also include identifying, by processing circuitry of the computing device, at least one region of interest in the first sensor data stream, determining cropping coordinates that define a first plurality of pixels in the at least one region of interest in the first sensor data stream, and generating a cropped image representing the at least one region of interest.

An intelligent meeting assistance system and a method for generating meeting minutes are provided. The intelligent meeting assistance system includes an image capturing device and an image analyzing device. The image capturing device is configured to capture an image displayed by an interactive device during a meeting. The image analyzing device is coupled to the image capturing device, and is configured to execute an image analysis process on the image to generate first meeting minutes that record image content.

Implementations utilize an AI-powered whiteboard to enhance communications and collaborations. A user can provide a handwritten input via a whiteboard user interface, and one or more machine learning models can be utilized to recognize and interpret the handwritten input, to generate whiteboard content that is responsive to the handwritten input and that is to be rendered within the whiteboard user interface with respect to the handwritten input. The handwritten input can include a handwritten text string and/or a hand-drawn sketch. The whiteboard content can be tailored based on a user profile, audible input, and/or control input.

Systems and techniques are provided for automatically analyzing and processing domain-specific image artifacts and document images. A process can include obtaining a plurality of document images comprising visual representations of structured text. An OCR-free machine learning model can be trained to automatically extract text data values from different types or classes of document image, based on using a corresponding region of interest (ROI) template corresponding to the structure of the document image type for at least initial rounds of annotations and training. The extracted information included in an inference prediction of the trained OCR-free machine learning model can be reviewed and validated or corrected correspondingly before being written to a database for use by one or more downstream analytical tasks.

According to some embodiments, a method by a computing system includes accessing a plurality of images captured by an imaging device. The imaging device and the computing system are coupled to a vehicle that moves within an intermodal container yard. The method further includes determining, by analyzing the plurality of images using a machine-learning module, that a shipping container is depicted within at least one of the plurality of images. The method further includes determining, using a map of the intermodal container yard, a parking location of the shipping container. The method further includes electronically communicating, in response to determining that the shipping container is depicted within at least one of the plurality of images, a message comprising data about the shipping container. The data includes the determined parking location of the shipping container and one or more identification markings of the shipping container.