An information processing apparatus includes: a text fragment detecting unit configured to detect one or more text fragments from a document page, each text fragment being a group of multiple texts; a meta information obtaining unit configured to obtain meta information from the one or more text fragments; and a text fragment extracting unit configured to extract a text fragment from the one or more text fragments based on the meta information.

A method includes obtaining, by a processor, an image captured in response to an input from a user, the image comprising a screenshot or a photo. The method also includes processing, by the processor, the image using an intent-based image understanding model and an optical character recognition model to extract information from the image. The method further includes recommending, by the processor, at least one automatic action to be taken based on the extracted information. In addition, the method includes, in response to a validation by the user of the at least one automatic action, performing, by the processor, the at least one automatic action.

The present disclosure discloses an electronic counter scale intelligent verification method based on deep learning detection and identification, which includes: collecting a top image, top depth data, and a front image of the electronic counter scale, and selecting a reading display apparatus on the front image; inputting the top image into a scale pan detection and identification model to obtain a scale pan target detection result, verifying the result with the top depth data, obtaining a spatial position of a scale pan, and outputting the spatial coordinates of the four vertices of the scale pan; inputting the top image into an indicating value detection and identification model to obtain indicating value characters and a position of the display apparatus, correcting similar characters and low-confidence characters, and obtaining an indicating value of the electronic counter scale; and performing unmanned verification of weighing performance, repeatability, bias load, and discrimination.

Techniques for leveraging completion logic may include: obtaining image data via a user device; detecting, via optical character recognition (OCR), an indeterminate alphanumeric sequence in the image data, the indeterminate alphanumeric sequence including at least one indeterminate character; predicting at least one value for the at least one indeterminate character based on one or more of a predetermined syntax of the alphanumeric sequence or content of the image data separate from the alphanumeric sequence; and determining a complete alphanumeric sequence based on the at least one predicted value and the indeterminate alphanumeric sequence.

An electronic device, a method, and a computer program product automatically anonymize personally identifiable information (PII) in photographic images by inpainting anonymized intelligible descriptive data to appear more natural than blurring or blocking PII. The electronic device detects selection of photographic image(s) for communicating to second device(s) that provide access for presentation to second person(s). In response to determining that the photographic image(s) contains PII, the electronic device delineates the photographic image(s) into multiple segments including first segment(s) encompassing and separating the PII from remaining segments of content that is not PII. The electronic device inpaints anonymized intelligible descriptive data in the first segment(s) containing the PII to prevent sharing of the PII when the photographic image(s) is presented or displayed to the second person(s).

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.

Devices and methods for locating and decoding a label are disclosed herein. The method receives, by a device, information of an area, and captures, by the device, a first image of one or more objects within the area. The method derives a first location and a first orientation of the device during capture of the first image based on the information and first data of at least one sensor of the device. The method detects a first label associated with a first object and processes the first label. The method determines a location of the first label associated with the first object within the area based on the derived first location and first orientation of the device, and assigns the first label a first indicator denoting the determined location of the first label and that the first label has been processed.

According to one embodiment, an information processing system includes a receiving unit, an OCR execution unit, a management unit, an extraction unit, a correction candidate output unit, and a correction acceptance unit. The receiving unit receives image information. The OCR execution unit performs character recognition on the image information using OCR. The management unit stores definition data that defines a workflow based on the image information. The extraction unit extracts a usage item handled in the workflow from the definition data. The correction candidate output unit extracts a value corresponding to the usage item from a recognition result obtained by the OCR execution unit and outputs the value as a correction candidate. The correction acceptance unit accepts a correction for the correction candidate.

The present techniques relate to, inter alia, cryptographically-verifiable insurance credentials and cryptographically-verifiable property transfer. The novel methods and systems of decentralized identity discussed herein improve user experience (whether individual or organizational) by moving control over identity from the hands of centralized entities, back to where it belongsi.e., to the hands of individual organizations and users. In one aspect, a method includes obtaining a scanned image; processing the scanned image; transmitting a claim request; and receiving and storing an attestation response, and a computing system includes a processor; and a memory having stored thereon computer-executable instructions that, when executed by the one or more processors, cause the computing system to: receive a claim request; cryptographically verify the claim; and transmit an attestation response.

A method for handwriting input display, a device thereof and a computer-readable storage medium. The method for handwriting input display includes: displaying one or more first contents, wherein the one or more first contents are generated based on handwriting input; in response to a second input from a user, displaying a mark line with a first line width, wherein the mark line is used to highlight the one or more of first contents; adjusting a line width of the mark line according to a height of the one or more first contents having an overlapping area with the mark line, wherein the line width of the mark line after the adjusting is a second line width, and the second line width is greater than the first line width.