LabCom V2 - Laboratoires communs organismes de recherche publics – PME/ETI

INtelligent notebooKS LabCom – LabCom INKS

Submission summary

To reach this goal, the industrial partner is willing to gain the technological know how in handwriting recognition and develop innovative applications for its products. The strategy of the group is to create its own R&D department and develop partnerships with research labs. The INKS LabCom will allow boosting this strategy. LITIS laboratory has a 20 years long expertise in processing digitized documents and handwriting. He will bring the LabCom INKS the required expertise for accessing the textual content of digitized documents and go further in the integration of paper documents into the digital workflow of personal or professional applications. INKS LabCom will benefit from a LITIS transfert of knowledge while providing the unique opportunity to validate its technologies at a new industrial scale and contribute to new research in the field of Machine Learning, especially in the field of Deep Learning, to allow optimal combination of optical (image) and language models for the design of personalized recognition systems. The collaboration will allow the INKS LabCom to design a handwriting recognition technology dedicated to the intelligent processing of digital handwritten notes captured with a mobile device. This new technology will be the core of new mobile and cloud applications. The LabCom INKS will rest on the recent advances in speech and handwriting processing, bearing on statistical suitable models at both the image and the language level. Deep learning technologies have demonstrated their superiority at both level and they will be the core of the future developments for both research and technology integration, based on the Open Source libraries made available by the giants of the internet. The INKS LabCom brings together the required skills to implement state of the art technologies, will be able to gather for the first time the large amount of data required to train recognition systems based on deep neural networks, and improve these technologies towards new applications that will enrich the products. INKS LabCom gathers two partners committed for years in research and development of handwriting recognition technologies.

Project coordination

Thierry Paquet (Laboratoire d'Informatique, Traitement de l'Information et des Systèmes)

The author of this summary is the project coordinator, who is responsible for the content of this summary. The ANR declines any responsibility as for its contents.

Partner

LITIS Laboratoire d'Informatique, Traitement de l'Information et des Systèmes

Help of the ANR 300,000 euros
Beginning and duration of the scientific project: December 2016 - 36 Months

Useful links

Explorez notre base de projets financés

 

 

ANR makes available its datasets on funded projects, click here to find more.

Sign up for the latest news:
Subscribe to our newsletter