Online Handwriting Recognition and Beyond
In this talk, I will present an overview of the current state of the art in Online handwriting recognition has been a field of interest in the research community since the beginning of graphical user interfaces and the last ten years with an ever growing number of mobile devices with touch screens or stylus support have created a renewed interest in the field, particularly in the industry. In this talk, I will present an overview of the current state of the art in online handwriting recognition and talk about recent advances in applications and modelling. The talk will start at the earliest origins of online handwriting recognition and survey different recognition approaches. I will present how deep learning has enabled major improvements over the state of the art in online handwriting recognition. I will further talk about related applications in drawing classification and how a joyful game has allowed for creating the worlds largest resource of online drawing data. I will conclude the talk with an outlook on problems that warrant further research.
Thomas Deselaers is currently a research manager at Apple in Zurich, Switzerland. Previously he was a software engineer at Google in Zurich, Switzerland where he worked on Handwriting Recognition. Before joining Google, he was a Postdoc at ETH Zurich working on Computer Vision. Thomas received both his PhD and diploma degree from RWTH Aachen University where he worked on image processing and understanding in the Human Language Technology and Pattern Recognition group. Thomas is excited and passionate about solving real world problems from inception to shipping products with novel and innovative approaches. His expertise is in applied machine learning.