Recognition of Handwritten Numerical Fields in a Large Single-Writer Historical Collection

This paper presents a segmentation-based handwriting recognizer and the performance that it achieves on the numerical fields extracted from a large single-writer historical collection. Our recognizer has the particularity that it uses morphing during training: random elastic deformations are applied to fabricate synthetic training character patterns yielding an improved final recognition performance. Two different digit recognizers are evaluated, a multilayer perceptron (MLP) and radial basis function network (RBF), by plugging them into the same left-to-right Viterbi search framework with a tree organization of the recognition lexicon. We also compare with the performance obtained when no dictionary is used to constrain the recognition results.

• Type: Journal
• Year: 2009
• Where: ICDAR
• Authors: Marius Bulacu, Axel Brink, Tijn van der Zant, Lambert Schomaker
• Keywords: Document Analysis, ICDAR 2009, Improved Final Recognition, Radial Basis Function Network, Segmentation-based Handwriting Recognizer