Text Recognition of Historical Documents Using Deep Neural Network Technologies

Abstract

   The application of deep neural network technologies to the problem of handwriting recognition in pre-reform Russian is considered. The initial data used are scanned JPG images of historical documents from the 19^th century, in particular containing various noises and interference, which complicates the work of the recognition algorithm. Text recognition is performed in three stages: noise removal, segmentation (highlighting) of text lines in the image, since the input data for the deep neural network are precisely the lines, and then recognition of the text of the highlighted lines using the pre-trained Tesseract OCR model, which performs electronic translation of images of handwritten or printed text into text data. The model used is a convolutional recurrent neural network; the model is a combination of a convolutional neural network for extracting local features from an image and a recurrent neural network represented by two layers of bidirectional LSTM networks for processing the sequence. Using this model allows for reliable recognition of handwritten text.