FragNet: Writer Identification using Deep Fragment Networks
This work addresses writer identification for forensic or historical document analysis, presenting a novel method but is incremental as it builds on existing deep learning approaches.
The paper tackles writer identification from small text samples by proposing FragNet, a deep neural network with dual pathways for feature extraction and fragment-based writer prediction, achieving efficient and robust performance on four benchmark datasets.
Writer identification based on a small amount of text is a challenging problem. In this paper, we propose a new benchmark study for writer identification based on word or text block images which approximately contain one word. In order to extract powerful features on these word images, a deep neural network, named FragNet, is proposed. The FragNet has two pathways: feature pyramid which is used to extract feature maps and fragment pathway which is trained to predict the writer identity based on fragments extracted from the input image and the feature maps on the feature pyramid. We conduct experiments on four benchmark datasets, which show that our proposed method can generate efficient and robust deep representations for writer identification based on both word and page images.