An information processing system includes circuitry that receives position information of first stroke information and second stroke information drawn on a display at different timing, adds additional information indicating a relationship of the received first stroke information and the received second stroke information to the received first stroke information, and generates, based on the position information of the received first stroke information, the position information of the received second stroke information and the added additional information, consecutive data used for displaying (playing) information drawn on the display as the first stroke information and the second stroke information, and a memory that stores the generated consecutive data.

A method of generating handwriting information about handwriting of a user includes determining a first writing focus and a second writing focus; sequentially shooting a first local writing area, which is within a predetermined range from a first writing focus, and a second local writing area, which is within a predetermined range from a second writing focus; obtaining first handwriting from the first local writing area and second handwriting from the second local writing area; combining the first handwriting with the second handwriting; and generating the handwriting information, based on a result of the combining.

One aspect of the present disclosure relates to a method of sentiment analysis based on ambiguity analysis, which includes analyzing information with the sentiment analysis models and the ambiguity analysis models. Another aspect of the present disclosure relates to a method of training the sentiment analysis models and ambiguity analysis models, which includes acquiring information, constructing lexicons, conducting sentiment analysis and ambiguity analysis with said lexicons, acquiring corpus, and training models, etc. Meanwhile, another aspect of the present disclosure relates to a system of sentiment analysis, which includes input, and output modules, acquisition modules, processing modules and database.

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, system, and/or computer program product operate a touch-screen device. A first touch on a touch-screen is detected, and a character is selected therefrom. A second touch on the touch-screen is detected, and a diacritic is selected therefrom. A location of the second touch on the touch-screen is determined. A location for the diacritic is selected according to a determined location of the second touch on the touch-screen. A specific touch-screen output of a selected character and a selected diacritic is then generated, where the selected diacritic is located on the selected character according to a selected diacritic location.

A computer-implemented technique is described herein that receives captured stroke information when a user enters a handwritten note using an input capture device. The technique then analyzes the captured stroke information to produce output analysis information. Based on the output analysis information, the technique modifies the captured stroke information into an actionable form that contains one or more actionable content items, while otherwise preserving the original form of the captured stroke information. The technique then presents the modified stroke information on a canvas display device. The user may subsequently activate one or more actionable content items in the modified stroke information to perform various supplemental tasks that pertain to the handwritten note. In one case, for example, the technique can recognize the presence of entity items and/or list items in the note and then reproduce them in an actionable form.

Systems and methods for identifying a printer that generated a printed document. The methods comprise: generating an electronic image of the printed document; obtaining a dot pattern contained on the printed document via an analysis of the electronic image; overlaying the dot pattern on Voronoi diagrams; selecting a first Voronoi diagram from the Voronoi diagrams that has a single dot of the dot pattern in each of at least some cells thereof; and identifying a printer associated with the first Voronoi diagram that was selected from the Voronoi diagrams. The printer associated with the first Voronoi diagram comprises the printer that generated a printed document.

Methods, systems, and apparatuses for natural content editing with gestures include a gesture recognition engine with an input component that receives first information concerning content rendered to a user interface and second information concerning a user gesture applied to the user interface. A context-free gesture recognizer obtains shape features based on the second information and generates a context-free gesture hypothesis for the user gesture based on the shape features. A context-aware gesture recognizer obtains contextual features based on the first information and the second information and evaluates the context-free gesture hypothesis based on the contextual features to make a final gesture decision for the user gesture. An output component outputs the final gesture decision for the user gesture to the application. An application programming interface enables an application to invoke the gesture recognition engine and allows for customized gesture configuration and recognition.

The present method includes: transforming a gray matrix of a natural scene image into a local contrast matrix, and performing a binary division to the obtained local contrast matrix using an Otsu method, thereby obtaining a binary matrix; performing a connected domain analysis to the binary matrix, eliminating non-character connected domains to obtain character connected domains; performing a detection of elements of a special structure of a formula to the character connected domains using a correlation coefficient method, and separately annotating all the detected elements of the special structure: dividing rows of the binary matrix by means of horizontal projection; recognizing each character connected domain by means of a convolutional neural network; defining an output sequence, and outputting the results of recognition in a corresponding sequence according to a typesetting format of LaTeX.

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.