Recognizing Handwriting Styles in a Historical Scanned Document Using Unsupervised Fuzzy Clustering
This provides a method for forensic document analysis in historical manuscripts, though it appears incremental as it builds on existing clustering techniques.
The study tackled the problem of attributing handwriting in historical documents to multiple scribes by using unsupervised fuzzy clustering with PCA, successfully detecting hand shifts without labeled data.
The forensic attribution of the handwriting in a digitized document to multiple scribes is a challenging problem of high dimensionality. Unique handwriting styles may be dissimilar in a blend of several factors including character size, stroke width, loops, ductus, slant angles, and cursive ligatures. Previous work on labeled data with Hidden Markov models, support vector machines, and semi-supervised recurrent neural networks have provided moderate to high success. In this study, we successfully detect hand shifts in a historical manuscript through fuzzy soft clustering in combination with linear principal component analysis. This advance demonstrates the successful deployment of unsupervised methods for writer attribution of historical documents and forensic document analysis.