Towards End-to-End Deep Learning-based Writer Identification

Abstract

Writer identification is an important task to gain knowledge about life in the past, which is commonly solved by paleographic experts. In this work, we investigate an automatic writer identification procedure based on deep learning. So far, the most approaches are based on two or more different pipeline steps and only few of them can be trained in an end-to-end manner. In this paper, we propose a fully end-to-end deep learning-based model, which consists of a U-Net for binarization, a ResNet-50 for feature extraction, and an optimized learnable residual encoding layer to obtain global descriptors. We evaluate the proposed end-to-end model on the ICDAR17 competition dataset on historical document writer identification (Historical-WI) dataset. Moreover, we investigate the performance of our optimized encoding layer on three texture datasets. While the optimized encoding layer does not work well in the task of writer identification, it provides better performance on the texture datasets. Furthermore, we show that a pre-trained U-Net can improve the performance for writer identification.