Myscript

Pierre-Michel Lallican

Zsolt Wimmer

Freddy Perraud

Guillermo Aradilla

Fabio Valente

Cyril Cerovic

Robin Melinand

Gaël Manson

Udit Roy

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.

Recognizing handwritten text by combining neural networks

The invention relates to a method implemented by a computing device for processing math and text in handwriting, comprising: identifying symbols by performing handwriting recognition on a plurality of strokes; classifying, as a first classification, first symbols as either a text symbol candidate or a math symbol candidate with a confidence score reaching a first threshold; classifying, as a second classification, second symbols other than first symbols as either a text symbol candidate or a math symbol candidate with a respective confidence score by applying predefined spatial syntactic rules; updating or confirming, as a third classification, a result of the second classification by establishing semantic connections between symbols and comparing the semantic connections with the result of the second classification; and recognising each symbol as either text or math based on a result of said third classification.

Classifying handwritten math and text symbols using spatial syntactic rules, semantec connections, and ink-related information of strokes forming the symbols

A system and method that is able to recognize a user's natural superimposed handwriting without any explicit separation between characters. The system and method is able to process single-stroke and multi-stroke characters. It can also process cursive handwriting. Further, the method and system can determine the boundaries of input words either by the use of a specific user input gesture or by detecting the word boundaries based on language characteristics and properties. The system and method analyzes the handwriting input through the processes of fragmentation, segmentation, character recognition, and language modeling. At least some of these processes occur concurrently through the use of dynamic programming.

System and method for superimposed handwriting recognition technology

A system and method is able to recognize a user's natural superimposed handwriting without any explicit separation between characters. The system and method is able to process single-stroke and multi-stroke characters. The system and method can also process cursive handwriting. Further, the system and method can determine the boundaries of input words either by the use of a specific user input gesture or by detecting the word boundaries based on language characteristics and properties. The system and method analyzes the handwriting input through the processes of segmentation, character recognition, and language modeling. These three processes occur concurrently through the use of dynamic programming.

A method for searching for at least one term, consisting of at least one character, in at least one set of ink data is disclosed. This method advantageously includes an operation for converting ink data into intermediate data, in an intermediate format, in the form of at least one segmentation graph, each node of one of the graphs including at least one ink segment associated with at least one assumption of correspondence with a recognition unit, and an operation for searching for the term or terms, carried out on the intermediate data, the conversion operation being carried out once and for all during storage of one of the sets of data, and the search operation being capable of being carried out at any time.

Method for searching for, recognizing and locating a term in ink, and a corresponding device, program and language

Disclosed are music symbol recognition apparatuses and methods that recognise music symbols from handwritten music notations. Various implementations may process handwritten music notations by segmenting the handwritten music notations into a plurality of elementary ink segments and then grouping the segments into graphical objects based on spatial relationships between the segments. One or more candidate music symbols may be determined for each graphical object, along with a symbol cost for each symbol, which represents a likelihood that the graphical object belongs to a predetermined class of symbols. The music symbol candidates may be parsed to form graphs based on grammar rules, and the graph most likely to represent the handwritten music notations may be selected for display or other use. The selection may be based on the symbol costs associated with each candidate and on spatial costs associated with the grammar rules that are applied to the candidates.

Method and apparatus for recognising music symbols

A system and method that is able to recognize a user's natural superimposed handwriting without any explicit separation between characters. The system and method is able to process single-stroke and multi-stroke characters. It can also process cursive handwriting. Further, the method and system can determine the boundaries of input words either by the use of a specific user input gesture or by detecting the word boundaries based on language characteristics and properties. The system and method analyzes the handwriting input through the processes of segmentation, character recognition, and language modeling. These three processes occur concurrently through the use of dynamic programming.

Disclosed are music symbol recognition apparatuses and methods that recognize music symbols from handwritten music notations. Various implementations may process handwritten music notations by segmenting the handwritten music notations into a plurality of elementary ink segments and then grouping the segments into graphical objects based on spatial relationships between the segments. One or more candidate music symbols may be determined for each graphical object, along with a symbol cost for each symbol, which represents a likelihood that the graphical object belongs to a predetermined class of symbols. The music symbol candidates may be parsed to form graphs based on grammar rules, and the graph most likely to represent the handwritten music notations may be selected for display or other use. The selection may be based on the symbol costs associated with each candidate and on spatial costs associated with the grammar rules that are applied to the candidates.

Growing community of inventors

Petit-Mars, France

Pierre-Michel Lallican