Many off-line handwritten word recognition systems have been proposed since the early nineties. Most systems reported high recognition rates, however, they overlooked a very important factor in the process; speed factor. In this paper we explore the potential for speeding up an off--line handwritten word recognition system via concurrency. The goal of the system is to achieve both full accuracy and high speed when taking into account large vocabularies. This has been accomplished by integrating the recognition process with multiprocessing and distributed computing concepts. Experimental results showed that the multiprocessing environment is very promising in enhancing a sequential off-line handwritten word recognition system performance.

In this paper we present a hybrid recognition system that integrates hidden Markov models (HMM) with neural networks (NN) in a probabilistic framework. The input data is processed first by a lexicon--driven word recognizer based on HMMs to generate a list of the candidate # --best-- scoring word hypotheses as well as the segmentation of such word hypotheses into characters. An NN classifier is used to generate a score for each segmented character and in the end, the scores from the HMM and the NN classifiers are combined to optimize performance. Experimental results show that for an 80,000--word vocabulary, the hybrid HMM/NN system improves by about 10% the word recognition rate over the HMM system alone.

In this paper we introduce a constrained Level Building Algorithm (LBA) in order to reduce the search space of a Large Vocabulary Handwritten Word Recognition (LVHWR) system. A time and a length constraint are introduced to limit the number of frames and the number of levels of the LBA respectively. A regression model that fits the response variables, namely, accuracy and speed, to a non--linear function of the constraints is proposed and a statistical experimental design technique is employed to analyse the effects of the two constraints on the responses. Experimental results prove that the inclusion of these constraints improve the recognition speed of the LVHWR system without changing the recognition rate significantly.

In this paper we present an off line system for the recognition of the handwritten numeric chains. Our work is divided in two big parts. The first part is the realization of a recognition system of the isolated handwritten digits. In this case the study is based mainly on the evaluation of neural network performances, trained with the gradient back propagation algorithm. The used parameters to form the input vector of the neural network are extracted on the binary images of the digits by several methods: the distribution sequence, the Barr features and the centred moments of the different projections and profiles. The second part is the extension of our system for the reading of the handwritten numeric chains constituted of a variable number of digits. The vertical projection is used to segment the numeric chain at isolated digits and every digit (or segment) will be presented separately to the entry of the system achieved in the first part (recognition system of the isolated handwritten digits). The result of the recognition of the numeric chain will be displayed at the exit of the global system.