Patents by Inventor Thibault ASSELBORN

Thibault ASSELBORN has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Method of handwritten character recognition confirmation
    Patent number: 11164025
    Abstract: The present invention concerns a method for an artificial neural network to confirm the recognition of handwritten characters produced by a user. The method comprising: training the artificial neural network with a training data set comprising a first set of characters; collecting handwritten characters of a second set of characters produced by the user; and analysing the collected characters of the second set of characters by using the artificial neural network to obtain a first set of probability values comprising character specific probability values for the collected characters, each character specific probability value indicating the probability that the collected character has been correctly interpreted. The analysis considers at least the manner how the collected characters are handwritten and the appearance of the collected characters to obtain the character specific probability values. The invention also relates to a corresponding data processing apparatus.
    Type: Grant
    Filed: November 24, 2017
    Date of Patent: November 2, 2021
    Assignee: ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE (EPFL)
    Inventors: Konrad Zolna, Thibault Asselborn, Wafa Johal
  • METHOD OF HANDWRITTEN CHARACTER RECOGNITION CONFIRMATION
    Publication number: 20200285877
    Abstract: The present invention concerns a method for an artificial neural network to confirm the recognition of handwritten characters produced by a user. The method comprising: training the artificial neural network with a training data set comprising a first set of characters; collecting handwritten characters of a second set of characters produced by the user; and analysing the collected characters of the second set of characters by using the artificial neural network to obtain a first set of probability values comprising character specific probability values for the collected characters, each character specific probability value indicating the probability that the collected character has been correctly interpreted. The analysis considers at least the manner how the collected characters are handwritten and the appearance of the collected characters to obtain the character specific probability values. The invention also relates to a corresponding data processing apparatus.
    Type: Application
    Filed: November 24, 2017
    Publication date: September 10, 2020
    Applicant: ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE (EPFL)
    Inventors: Konrad ZOLNA, Thibault ASSELBORN, Wafa JOHAL