An image processing system performs tilt correction with respect to a document image having handwritten characters and typed letters mixed with each other. The image processing system separates the document image into an image with handwritten characters determined as handwritten characters and an image without handwritten characters not determined as handwritten characters, estimates a tilt angle of the image without handwritten characters, and corrects the document image on the basis of the tilt angle.

A document reading device includes a document conveyer, a first reader reading, in a first reading position, a first surface of a conveyed document such that a read area is larger than the conveyed document, a second reader reading, in a second reading position, a surface (second surface) opposite to the first surface such that a read area is larger than the conveyed document, a region detector executing a process of detecting a first document region that is a region of a document in first document image data and a process of detecting a second document region that is a region of the document in second document image data, and a cropping processor cropping a document portion on the first surface as first cropped image data and cropping a document portion on the second surface as second cropped image data, based on one of the document regions successfully detected.

There are provided a learning recommendation apparatus and method for detecting a problem from an image through character recognition and providing at least one sub-topic learning among a plurality of sub-topic learnings related to the detected problem. The provided learning recommendation apparatus recommends, as a recommendation target, a plurality of learning topics including the concept of a formula which has been read through the character recognition for an image, wherein a priority order is set to the plurality of learning topics based on the concept distance between the learning topic and the learning history, and the learning topics are recommended so that the learning topic having a higher priority order is located at a higher position.

A geographic object recognition unit (120) recognizes, using image data (192) obtained by photographing in a measurement region where a geographic object exists, a type of the geographic object from an image that the image data (192) represents. A position specification unit (130) specifies, using three-dimensional point cloud data (191) indicating a three-dimensional coordinate value of each of a plurality of points in the measurement region, a position of the geographic object.

A monocular visual simultaneous localization and mapping (SLAM) data processing method. The SLAM data processing method comprises: obtaining rotation angular velocities and accelerations of a camera cyclically; obtaining a plurality of feature point pairs in two frames of images acquired by the camera, and obtaining pixel coordinate values of feature points in the feature point pairs, where each of the feature point pairs includes two feature points that correspond to a same feature of a same object and that are respectively in the two frames of images; obtaining to-be-selected rotation matrices and to-be-selected displacement matrices according to the pixel coordinate values; obtaining a reference rotation matrix of the camera according to the rotation angular velocities, and obtaining a reference displacement matrix of the camera according to the accelerations; and filtering the to-be-selected rotation matrices and the to-be-selected displacement matrices according to the reference rotation matrix and the reference displacement matrix.

Methods, apparatus, systems, and articles of manufacture are disclosed to decode receipts based on neural graph architecture. An example apparatus for decoding receipts includes, vertex feature representation circuitry to extract features from optical-character-recognition (OCR) words, polar coordinate circuitry to: calculate polar coordinates of the OCR words based on respective ones of the extracted features, graph neural network circuitry to generate an adjacency matrix based on the extracted features, post-processing circuitry to traverse the adjacency matrix to generate cliques of OCR processed words, and output circuitry to generate lines of text based on the cliques of OCR processed words.

A license plate number recognition method includes: extracting license plate number features of an image to be recognized including a license plate number, through a pre-trained convolutional neural network; extracting an intermediate convolution result during extracting the license plate number features, and extracting a first verification feature and/or a second verification feature according to the intermediate convolution result; verifying whether the license plate number features are correct according to the first and/or second verification features; if correct, outputting a predicted license plate number result according to the license plate number features. During the feature extraction process of the license plate number features, an intermediate feature is extracted as a verification feature to verify whether the extracted license plate number features are correct, and only when the verification is passed, outputting the license plate number result, which reduces the output error rate of the license plate number recognition result.

A license plate number recognition method includes: extracting license plate number features of an image to be recognized including a license plate number, through a pre-trained convolutional neural network; extracting an intermediate convolution result during extracting the license plate number features, and extracting a first verification feature and/or a second verification feature according to the intermediate convolution result; verifying whether the license plate number features are correct according to the first and/or second verification features; if correct, outputting a predicted license plate number result according to the license plate number features. During the feature extraction process of the license plate number features, an intermediate feature is extracted as a verification feature to verify whether the extracted license plate number features are correct, and only when the verification is passed, outputting the license plate number result, which reduces the output error rate of the license plate number recognition result.

A display apparatus includes circuitry to receive an operation of changing a direction of display of a character string displayed in a first direction on a display, and control the display to display a converted character string in a second direction corresponding to the operation of changing. The converted character string is converted from the character string into a target language associated with the second direction.

Disclosed herein are devices and methods for determining the identity of markings on tires. A portable tire scanner can comprise one or more light sources and detector that reflect light off tire markings and capture imagery of them. The scanner is operable to process the imagery to determine the identity of the markings. The marking can be the same color as the area of the tire around the marking (e.g., black-on-black) and the scanner can identify the marking by determining angular edges of the markings. Plural light sources and/or detectors can be used to provide plural perspectives to better determine the edges of the markings. The housing can have a form factor that allows the scanner to be hand-held, such that a user can aim the scanner at tires even while on a vehicle or in hard to reach positions. The scanner can be used to scan and identify several tire marking in succession.