An adaptive approach to offline handwritten word recognition

Abstract

An adaptive handwritten word recognition method is presented. The key ideas of adaptation are 1) to actively and successively select a subset of features for each word image which provides the minimum required classification accuracy to get a valid answer and 2) to derive a consistent decision metric which works in a multiresolution feature space and considers the interrelationships of a lexicon at the same time. A recursive architecture based on interaction between flexible character classification and deductive decision making is developed. The recognition process starts from the initial coarse level using a minimum number of features, then increases the discrimination power by adding other features adaptively and recursively until the result is accepted by the decision maker. For the computational aspect of a feasible solution, a unified decision metric, recognition confidence, is derived from two measurements: pattern confidence, evaluation of absolute confidence using shape features, and lexical confidence, evaluation of the relative string dissimilarity in the lexicon. Practical implementation and experimental results in reading the handwritten words of the address components of US mail pieces are provided. Up to a 4 percent improvement in recognition performance is achieved compared to a nonadaptive method. The experimental result shows that the proposed method has advantages in producing valid answers using the same number of features as conventional methods.