Text Line Extraction in Handwritten Historical Documents

We present a novel approach for the extraction of text lines in handwritten documents using a Convolutional Neural Network to label document image patches as text lines or separators. We first process the document to identify the most suitable patch size on the basis of an overall text line distance estimation. Using this information, we then extract several patches to train the CNN model. Finally, we use the trained model to segment text lines. We have evaluated this technique on the public database Saint Gall and on a private collection provided by the Ancestry company.