Writing Style Invariant Deep Learning Model for Historical Manuscripts Alignment
This addresses the manual effort in document analysis for historians and archivists, though it is incremental as it builds on existing alignment methods.
The paper tackles the problem of historical manuscript alignment by introducing a writer-independent deep learning model trained on multiple writing styles, achieving an average accuracy of 92.17% on unseen styles through cross-validation.
Historical manuscript alignment is a widely known problem in document analysis. Finding the differences between manuscript editions is mostly done manually. In this paper, we present a writer independent deep learning model which is trained on several writing styles, and able to achieve high detection accuracy when tested on writing styles not present in training data. We test our model using cross validation, each time we train the model on five manuscripts, and test it on the other two manuscripts, never seen in the training data. We've applied cross validation on seven manuscripts, netting 21 different tests, achieving average accuracy of $\%92.17$. We also present a new alignment algorithm based on dynamic sized sliding window, which is able to successfully handle complex cases.