A novel approach to on-line handwriting recognition based on bidirectional long short-term memory networks
Year: 2007
Type: conference-paper
Abstract: In this paper we introduce a new connectionist approach to on-line handwriting recognition and address in particular the problem of recognizing handwritten whiteboard notes.The approach uses a bidirectional recurrent neural network with long short-term memory blocks.We use a recently introduced objective function, known as Connectionist Temporal Classification (CTC), that directly trains the network to label unsegmented sequence data.Our new system achieves a word recognition rate of 74.0 %, compared with 65.4 % using a previously developed HMMbased recognition system.
Source: BORIS (University Library Bern)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2587486463