Abstract: A recognition system for recognizing multiple inputs of gestures, handwriting symbols and virtual keys on a touch screen includes a touch IC serves to convert a plurality of touch signals of the touch screen to a touch data frame. A processor set is connected to the touch IC and serves to perform a touch data processing on the touch data frame. The touch data processing is performed by using a processing directly executed by an OS (Operating System) and a processing of AI (artificial intelligence) recognizing. An AI recognition module is connected to the processor set. The AI recognition module is used for recognizing multiple key inputs, operation gestures and handwriting symbols. The key inputs and handwriting symbols are corrected by a grammar correction and a symbol correction respectively. The touch screen serves to display a virtual keyboard.

Abstract: An online handwriting document layout analysis system includes a preprocess unit serving to receive a document composed of a plurality of strokes and to generate an undirected graph including a plurality of nodes and a plurality of edges for representing relations between different strokes. A bidirectional recursive neural network unit for initializing a feature vector of each of the nodes and initializing a feature vector of each of edges. A graphic neural network unit serves to update the feature vectors of the nodes and the edges for obtaining updated feature vectors. A fully connected neural network unit serves for performing a coarse-grained object classifying and a fine-grained object classifying for each of the nodes and the edges based on the updated feature vectors. A document restoration unit serves for restoring a tree structure of the document.

Abstract: A digital trajectory prediction system includes a preprocess unit serving to receive an input trajectory from an input device for preforming a preprocessing on the input trajectory to form a processed trajectory. A neural network prediction model serves to receive the processed trajectory and to output a prediction result including a predicted point. A post-processing unit serves to perform a post-processing on the prediction result for determining whether to add the predicted point to a render point set. A point output unit serves for rendering the render point set. When the predicted point is added to the render point set in the post-processing, the input trajectory and the predicted point are rendered on a screen. When the predicted point is not added to the render point set in the post-processing, only the input trajectory is rendered on the screen.

Abstract: A handwriting geometry recognition and calibration system by using neural network and mathematical feature includes: a pre-processor for pre-processing coordinate points of geometric figures from user's handwriting so as to get a plurality of sample points which expresses the geometric figures to be recognized; a neural network connected to the pre-processor for receiving the sample points of the geometric figure and recognizing the geometric figure so as to acquire a coarse class of the geometric figure; and an mathematical logic unit connected to the neural network for receiving recognition results from the neural network, including coarse classifications which are used in a secondary classification by using conventional mathematical recognition logics so as to determine an exact geometry shape of the geometric figure; then the geometric figure being calibrated so as to get a geometry with a regular shape.

Abstract: A syntax-directed mathematical expression recognition system combines online handwritten mathematical expression, offline handwritten and printed mathematical expression and structured mathematical expressions to generate a huge amount of mathematical expressions which are usable in training of neural networks. An end to end learning way is used to train the neural network for increment of learning effect and recognition ability. The problem of overfitting in multi-layer neural networks is reduced effectively so as to increase accuracy of testing set. The mode of neural network is usable for online handwritten mathematical expression, offline handwritten and printed mathematical expression. Therefore only one recognition system is used, no other system is needed.

Abstract: A recognition system for recognizing dual inputs of gestures and virtual keys on a touch screen includes a touch IC connected to the touch screen for receiving a plurality of touch signals generated by the touch screen and converting the touch signals to a touch data frame. A processor set is connected to the touch IC. The processor set serves to perform a touch data processing on the touch data frame from the touch IC. The touch data processing is performed by using a processing directly executed by an OS (Operating System) and a processing of AI (artificial intelligence) recognizing. The processor set serves to perform a grammar correction on a recognition result of the AI recognizing. A result of the grammar correction is output to the OS for processing.