Methods, systems, and computer-readable media related to a technique for providing handwriting input functionality on a user device. A handwriting recognition module is trained to have a repertoire comprising multiple non-overlapping scripts and capable of recognizing tens of thousands of characters using a single handwriting recognition model. The handwriting input module provides real-time, stroke-order and stroke-direction independent handwriting recognition for multi-character handwriting input. In particular, real-time, stroke-order and stroke-direction independent handwriting recognition is provided for multi-character, or sentence level Chinese handwriting recognition. User interfaces for providing the handwriting input functionality are also disclosed.

The electronic devices described herein are configured to enhance user experience associated with drawing or otherwise inputting shape data into the electronic devices. Shape input data is identified and matched against known shape patterns and, when a match is found, an entity associated with the shape is determined. The entity is converted into an annotation for rendering and/or displaying to the user. The shape identification, entity determination, and annotation conversion may all be based on one or more context elements to increase the accuracy of the shape interpretation. In particular, elements of conversations held via the electronic devices may be used as context for the shape interpretation. Further, machine learning techniques may be applied based on a variety of feedback data to improve the accuracy, speed, and/or performance of the shape interpretation process.

The electronic devices described herein are configured to enhance user experience associated with drawing or otherwise inputting shape data into the electronic devices. Shape input data is identified and matched against known shape patterns and, when a match is found, an entity associated with the shape is determined. The entity is converted into an annotation for rendering and/or displaying to the user. The shape identification, entity determination, and annotation conversion may all be based on one or more context elements to increase the accuracy of the shape interpretation. In particular, elements of conversations held via the electronic devices may be used as context for the shape interpretation. Further, machine learning techniques may be applied based on a variety of feedback data to improve the accuracy, speed, and/or performance of the shape interpretation process.

Methods, systems, and computer program products are provided for stroke attribute matrices. User input strokes may be converted into attributes encoded in one or more stroke attribute matrices (SAMs), such as bitmaps, for image or other multidimensional analysis. One or more convolutional neural networks (CNNs) may recognize letters, symbols, shapes and gestures in SAMs. A selector may select output classifications from among multiple CNNs. A sequence analyzer may select a sequence of selected CNN outputs. Stroke information may comprise, for example, velocity (e.g. direction and speed), tilt, pressure, line width, pen up/down events, hover height, etc. Stroke information may be stored, for example, in bitmap color channels (e.g. to facilitate human review). For example, an x, y velocity vector and x, y tilt may be encoded, respectively, as RGBA components of pixel data. Stroke crossings may be encoded, for example, by combining attribute values at pixels where strokes intersect.

Methods, systems, and computer-readable media related to a technique for providing handwriting input functionality on a user device. A handwriting recognition module is trained to have a repertoire comprising multiple non-overlapping scripts and capable of recognizing tens of thousands of characters using a single handwriting recognition model. The handwriting input module provides real-time, stroke-order and stroke-direction independent handwriting recognition for multi-character handwriting input. In particular, real-time, stroke-order and stroke-direction independent handwriting recognition is provided for multi-character, or sentence level Chinese handwriting recognition. User interfaces for providing the handwriting input functionality are also disclosed.

The electronic devices described herein are configured to enhance user experience associated with drawing or otherwise inputting shape data into the electronic devices. Shape input data is identified and matched against known shape patterns and, when a match is found, an entity associated with the shape is determined. The entity is converted into an annotation for rendering and/or displaying to the user. The shape identification, entity determination, and annotation conversion may all be based on one or more context elements to increase the accuracy of the shape interpretation. In particular, elements of conversations held via the electronic devices may be used as context for the shape interpretation. Further, machine learning techniques may be applied based on a variety of feedback data to improve the accuracy, speed, and/or performance of the shape interpretation process.

An interactive method for generating strokes with Chinese ink painting style, includes steps: obtaining an image including a pattern as an image object; obtaining a delimiting operation delimiting at least one stroke sample on a pre-stored ink painting sample, obtaining a basic outline forming a preliminary basic path of a stroke to be generated and drawn by a user on the image object; correcting stroke outlines in the stroke sample to obtain accurate stroke samples as candidate stroke samples; using the candidate stroke samples as references to generate morphological sample groups; correcting the preliminary basic path to obtain an accurate basic path; selecting morphological samples best matching the accurate basic path in the morphological sample groups as final stroke samples; and mapping style features of the final stroke samples onto the accurate basic path to generate an output image with Chinese ink painting style.

Methods, systems, and computer program products are provided for stroke attribute matrices. User input strokes may be converted into attributes encoded in one or more stroke attribute matrices (SAMs), such as bitmaps, for image or other multidimensional analysis. One or more convolutional neural networks (CNNs) may recognize letters, symbols, shapes and gestures in SAMs. A selector may select output classifications from among multiple CNNs. A sequence analyzer may select a sequence of selected CNN outputs. Stroke information may comprise, for example, velocity (e.g. direction and speed), tilt, pressure, line width, pen up/down events, hover height, etc. Stroke information may be stored, for example, in bitmap color channels (e.g. to facilitate human review). For example, an x, y velocity vector and x, y tilt may be encoded, respectively, as RGBA components of pixel data. Stroke crossings may be encoded, for example, by combining attribute values at pixels where strokes intersect.

Methods, systems, and computer program products are provided for stroke attribute matrices. User input strokes may be converted into attributes encoded in one or more stroke attribute matrices (SAMs), such as bitmaps, for image or other multidimensional analysis. One or more convolutional neural networks (CNNs) may recognize letters, symbols, shapes and gestures in SAMs. A selector may select output classifications from among multiple CNNs. A sequence analyzer may select a sequence of selected CNN outputs. Stroke information may comprise, for example, velocity (e.g. direction and speed), tilt, pressure, line width, pen up/down events, hover height, etc. Stroke information may be stored, for example, in bitmap color channels (e.g. to facilitate human review). For example, an x, y velocity vector and x, y tilt may be encoded, respectively, as RGBA components of pixel data. Stroke crossings may be encoded, for example, by combining attribute values at pixels where strokes intersect.

A system, method and computer program product for hand-drawing diagrams including text and non-text elements on a computing device are provided. The computing device has a processor and a non-transitory computer readable medium for detecting and recognizing hand-drawing diagram element input under control of the processor. Display of input diagram elements in interactive digital ink is performed on a display device associated with the computing device. One or more of the diagram elements are associated with one or more other of the diagram elements in accordance with a class and type of each diagram element. The diagram elements are re-displayed based on one or more interactions with the digital ink received and in accordance with the one or more associations.