Methods and systems are provided for end-to-end text recognition in digitized documents of handwritten characters over multiple lines without explicit line segmentation. An image is received. Based on the image, one or more feature maps are determined. Each of the one or more feature maps include one or more feature vectors. Based at least in part on the one or more feature maps, one or more scalar scores are determined. Based on the one or more scalar scores, one or more attention weights are determined. By applying the one or more attention weights to each of the one or more feature vectors, one or more image summary vectors are determined. Based at least in part on the one or more image summary vectors, one or more handwritten characters are determined.

A method for recognizing handwritten text is disclosed. The method comprises receiving data comprising a sequence of ink points; applying the received data to a neural network-based sequence classifier trained with a Connectionist Temporal Classification (CTC) output layer using forced alignment to generate an output; generating a character hypothesis as a portion of the sequence of ink points; applying the character hypothesis to a character classifier to obtain a first probability corresponding to the probability that the character hypothesis includes the given character; processing the output of the CTC output layer to determine a second probability corresponding to the probability that the given character is observed within the character hypothesis; and combining the first probability and the second probability to obtain a combined probability corresponding to the probability that the character hypothesis includes the given character.

An image processing method and apparatus for a smart pen, and an electronic device are provided in embodiments of the present disclosure, and belong to the technical field of data processing. The method comprises: monitoring a working state of a second pressure switch provided at a pen tip of a smart pen after a first pressure switch of the smart pen is in a closed state; controlling an image collection module on the smart pen to collect a reflected infrared signal from an area where the smart pen writes; performing feature extraction processing on an original image to obtain a feature matrix corresponding to the original image; determining, based on current load status of the smart pen, the number of convolutional layers used for convolution processing in parallel convolutional layers; and adding current time information to a trajectory classification result to form a time-ordered trajectory vector.

A handwriting input apparatus that displays stroke data handwritten based on a position of an input unit contacting a touch panel, includes circuitry configured to implement a handwriting recognition control unit for recognizing stroke data and converting the stroke data into text data, and an authentication control unit for authenticating a user based on the stroke data, and a display unit for displaying a display component for receiving a signature together with the text data when the authentication control unit determines that a user has been successfully authenticated.

A display includes a display portion formed of an array of unit pixels that each respectively include a light source pixel and a detector pixel. The display includes a control driver including a light source driver and a data driver which are respectively connected to each light source pixel, and a detector driver which is connected to each detector pixel. The display includes a controller configured to control the control driver to operate the display portion in a first mode, a second mode, and a third mode that are each different from each other.

Techniques are disclosed for generating a vector image from a raster image, where the raster image is, for instance, a photographed or scanned version of a hand-drawn sketch. While drawing a sketch, an artist may perform multiple strokes to draw a line, and the resultant raster image may have adjacent or partially overlapping salient and non-salient lines, where the salient lines are representative of the artist's intent, and the non-salient (or auxiliary) lines are formed due to the redundant strokes or otherwise as artefacts of the creation process. The raster image may also include other auxiliary features, such as blemishes, non-white background (e.g., reflecting the canvas on which the hand-sketch was made), and/or uneven lighting. In an example, the vector image is generated to include the salient lines, but not the non-salient lines or other auxiliary features. Thus, the generated vector image is a cleaner version of the raster image.

A presentation system capable of detecting one or more gestures and contacts on a touch sensitive display. The presentation system can displaying indicia of such contacts, such as when a user writes with a fingertip, and can remove or alter such indicia responsive to other gestures and contacts. The system can accurately distinguish between types of gestures detected, such as between a writing gesture and an erasing gesture, on both large and small touch sensitive displays, thereby obviating the need for a user to make additional selective inputs to transition from one type of gesture to another. The system can determine how long to keep user annotations displayed during a presentation, based on the nature of the gesture used to make the annotations and the context in which they are made.

According to the present disclosure, a handwriting image and a background image are combined, thereby generating a combined image, a correct answer label image is generated based on the handwriting image, and the generated combined image and the generated correct answer label image are used as learning data for training a neural network.

An electronic device is disclosed. The electronic device comprises a storage unit for storing a training model of a multi-dimensional long short-term memory (MDLSTM), and a processor for acquiring an image including at least one of handwritten text and printed text, identifying each text line region in the image through image processing, and recognizing text included in the each identified text line region, on the basis of the training model.

A method for motion tracking and text recognition, the method including a step of generating ultrasound waves with a transmitter; a step of receiving the ultrasound waves at a receiver, the receiver including sensors that record the ultrasound waves; a step of estimating with a processor, angle-of-arrival information for the ultrasound waves; a step of associating the angle-of-arrival information with a gesture; a step of extracting features from the gesture; and a step of classifying the gesture as a specific text character based on the extracted features by comparing the extracted features with known text characters stored in one or more templates.