Fully convolutional network with dilated convolutions for handwritten text line segmentation

Guillaume Renton (1) , Yann Soullard (1) , Clément Chatelain (1) , Sébastien Adam (1) , Christopher Kermorvant (2, 1) , Thierry Paquet (1)

1 DocApp - LITIS - Equipe Apprentissage
2 Teklia

We present a learning-based method for handwritten text line segmentation in document images. Our approach relies on a variant of deep fully convolutional networks (FCNs) with dilated convolutions. Dilated convolutions allow to never reduce the input resolution and produce a pixel-level labeling. The FCN is trained to identify X-height labeling as text line representation, which has many advantages for text recognition. We show that our approach outperforms the most popular variants of FCN, based on deconvolution or unpooling layers, on a public dataset. We also provide results investigating various settings, and we conclude with a comparison of our model with recent approaches defined as part of the cBAD (https://scriptnet.iit.demokritos.gr/competitions/5/) international competition, leading us to a 91.3% F-measure.

Domaines: Apprentissage [cs.LG]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Guillaume Renton, Yann Soullard, Clément Chatelain, Sébastien Adam, Christopher Kermorvant, et al.. Fully convolutional network with dilated convolutions for handwritten text line segmentation. International Journal on Document Analysis and Recognition, In press, ⟨10.1007/s10032-018-0304-3⟩. ⟨hal-01823604⟩