An image reader includes a document reading unit, and a control unit that functions as an individual image cutting section, character string detection section, mismatch detection section, judgment section, and correction section. The individual image cutting section cuts out individual images from image data obtained through reading by the document reading unit. The character string detection section detects character strings present on the individual images. The mismatch detection section detects, for the character strings detected by the character string detection section, a mismatching portion by making comparison between the individual images with considering character strings having contents identical or similar to each other as same information. The judgment section judges for the mismatching portions whether a ratio of majority characters reaches a predefined ratio. Upon judging that the ratio of the majority characters has reached the predefined ratio, the correction section replaces a minority character with the majority character.

The positioning of elements of a broken word can be corrected by receiving an optical character recognition (OCR) conversion of a printed publication and identifying multiple parts of the broken word from the OCR conversion to output in a graphical user interface (GUI). The multiple parts can be placed in the GUI using original positioning data for the printed publication. A user can make a selection in the GUI indicating that multiple parts from the OCR conversion are of the broken word and can automatically adjust bounds of the multiple parts to form a corrected word.

An intelligent TTS providing method and an intelligent computing device providing TTS are disclosed. An intelligent TTS providing method according to an embodiment of the present disclosure can seamlessly provide continuous TTS by receiving a text read command, adjusting a photographing angle of a camera such that a position of an object on which text is written is included in the photographing angle, photographing the object, converting the text written on the object into a speech and outputting the speech. One or more of the intelligent computing device and artificial intelligent speaker of the present disclosure can be associated with artificial intelligence (AI) modules, unmanned aerial vehicle (UAV) robots, augmented reality (AR) devices, virtual reality (VR) devices, 5G service related devices, etc.

Some aspects of the invention relate to a mobile apparatus including an image sensor configured to convert an optical image into an electrical signal. The optical image includes an image of a vehicle license plate. The mobile apparatus includes a license plate detector configured to process the electrical signal to recover information from the vehicle license plate image.

Provided is a method for recognizing handwritten characters in a terminal through federated learning. In the method, a first common prediction model for recognizing text from handwritten characters input from a user is applied, the handwritten characters are received from the user, feature values are extracted from an image including the handwritten characters, the feature values are input to the first common prediction mode, first text information is determined from an output of the first common prediction model, the first text information and a second text information received from the user for error correction of the first text information are cached, and the first common prediction model is learned using the image including the handwritten characters, the first text information, and the second text information. In this way, the terminal can determine the text from the handwritten characters input by the user, and can learn the first common prediction model through a feedback operation of the user.

A method of sorting baggage at an airport, which method comprises acquiring a plurality of digital images (IN) of a piece of baggage, which piece of baggage carries an unambiguous identification label bearing textual information about a flight, the method further comprising video coding in which a computer unit automatically detects the presence of characteristic elements of the unambiguous identification label in the digital images, computes a score for each of the digital images on the basis of a count of the characteristic elements, ranks the images as a function of their respective scores, and displays the images on a screen (132) as a function of the ranking.

Methods for automatically verifying text detected by optical character recognition (OCR). The method includes obtaining a native digital document having an image layer comprising a matrix of computer-renderable pixels and a text layer comprising computer-readable encodings of a sequence of characters. The method includes obtaining OCR-detected text from the image layer of the native digital document and a pixel-based coordinate location of the OCR-detected text in the image layer of the native digital document. The method includes determining, using a pixel transformation, a computer-interpretable location of the OCR-detected text in the text layer of the native digital document. The method includes detecting text in the text layer based on the computer-interpretable location of the OCR-detected text in the text layer. The method includes rendering only the detected text in the text layer when the OCR-detected text does not match the detected text in the text layer.

Systems and methods for augmented-reality tutoring can utilize optical character recognition, natural language processing, and/or augmented-reality rendering for providing real-time notifications for completing a determined task. The systems and methods can include utilizing one or more machine-learned models trained for quantitative reasoning and can include providing a plurality of different user interface elements at different times.

An analysis method includes: executing first accumulation processing for accumulating analysis reports including an analysis item regarding an analysis target and analysis results with respect to the analysis item; executing first extraction processing for extracting the analysis item and texts representing the analysis results from each of the analysis reports accumulated; executing first identification processing for identifying analysis techniques corresponding to the texts extracted; executing generation processing for generating analysis patterns; executing second identification processing for identifying first analysis patterns; executing third identification processing for identifying other analysis patterns; executing second accumulation processing for accumulating pattern information; executing second extraction processing for extracting the analysis item and the texts from a new analysis report; and executing output processing for identifying an analysis technique.

Methods for automatically verifying text detected by optical character recognition (OCR). The method includes obtaining a native digital document having an image layer comprising a matrix of computer-renderable pixels and a text layer comprising computer-readable encodings of a sequence of characters. The method includes obtaining OCR-detected text from the image layer of the native digital document and a pixel-based coordinate location of the OCR-detected text in the image layer of the native digital document. The method includes determining, using a pixel transformation, a computer-interpretable location of the OCR-detected text in the text layer of the native digital document. The method includes detecting text in the text layer based on the computer-interpretable location of the OCR-detected text in the text layer. The method includes rendering only the detected text in the text layer when the OCR-detected text does not match the detected text in the text layer.