Offline Handwritten Text Recognition using Convolutional Recurrent Neural Network

Offline handwriting recognition is an image-based sequence recognition task within computer vision. Traditional approaches rely on lexical segmentation, complex feature extraction techniques and considerable knowledge in the domain of linguistics. This paper presents a novel approach to handwriting recognition by using Convolutional Recurrent Neural Network combined with Connectionist Temporal Classification. The implemented method has the advantage of not being dependent on lexical segmentation and manual feature extraction. Moreover, applied methods are symbolic and character independent, making the model globally trainable and suitable to be applied to multiple languages.