HIGHLIGHTS
- who: Homa Davoudi from the Center for Cultural Heritage Technology (CCHT), Fondazione Istituto Italiano di Tecnologia (IIT), Via Torino, Venice, Italy have published the article: Discrete representation learning for handwritten text recognition, in the Journal: (JOURNAL)
- what: The authors propose a novel DNN architecture for handwritten text recognition that extracts discrete representation from the input text-line image. The main motivation is to develop a representation network that matches the configuration of scripts where a limited set of basic components (e_g, signs or drawing strokes) are combined to construct the words and sentences. To tackle . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.