Record Counting in Historical Handwritten Documents with Convolutional Neural Networks
This work addresses a domain-specific problem for historians and archivists by providing an incremental improvement in automated document analysis.
The paper tackled the problem of counting records in historical handwritten documents by training convolutional neural networks exclusively on synthetic images, achieving near-perfect evaluation results that outperformed previous benchmarks on a marriage records dataset.
In this paper, we investigate the use of Convolutional Neural Networks for counting the number of records in historical handwritten documents. With this work we demonstrate that training the networks only with synthetic images allows us to perform a near perfect evaluation of the number of records printed on historical documents. The experiments have been performed on a benchmark dataset composed by marriage records and outperform previous results on this dataset.