Recognizing Challenging Handwritten Annotations with Fully Convolutional Networks
This addresses the specific problem of document analysis for historians and archivists, but is incremental as it applies existing methods to new data.
The paper tackles the problem of locating handwritten annotations in historic German documents using Fully Convolutional Neural Networks, achieving a mean Intersection over Union score of 95.6% on a new challenging dataset.
This paper introduces a very challenging dataset of historic German documents and evaluates Fully Convolutional Neural Network (FCNN) based methods to locate handwritten annotations of any kind in these documents. The handwritten annotations can appear in form of underlines and text by using various writing instruments, e.g., the use of pencils makes the data more challenging. We train and evaluate various end-to-end semantic segmentation approaches and report the results. The task is to classify the pixels of documents into two classes: background and handwritten annotation. The best model achieves a mean Intersection over Union (IoU) score of 95.6% on the test documents of the presented dataset. We also present a comparison of different strategies used for data augmentation and training on our presented dataset. For evaluation, we use the Layout Analysis Evaluator for the ICDAR 2017 Competition on Layout Analysis for Challenging Medieval Manuscripts.