A novel method for online data acquisition of cursive handwriting is described. A video camera is used to record the handwriting of a user. From the acquired sequence of images, the movement of the tip of the pen is reconstructed. A prototype of the system has been implemented and tested. In one series of tests, the performance of the system was visually assessed. In another series of experiments, the system was combined with an existing online handwriting recognizor. Good results have been obtained in both sets of experiments.

On-line recognition differs from off-line recognition in that additional information about the drawing order of the strokes is available. This temporal information makes it easier to recognize handwritten texts with an on-line recognition system. In this paper we present a method for the recovery of the stroke order from static handwritten images. The algorithm was tested by classifying the words of an off-line database with a state-of-the-art on-line recognition system. On this database with 150 different words, written by four cooperative writers, a recognition rate of 97.4% was obtained.

Off-line handwriting recognition has wider applications than on-line recognition, yet it seems to be a harder problem. While on-line recognition is based on pen trajectory data, off-line recognition has to rely on pixel data only. We present a comparison between an off-line and an on-line recognition system using the same databases and system design. Both systems use a sliding window technique which avoids any segmentation before recognition. The recognizer is a hybrid system containing a neural network and a hidden Markov model. New normalization and feature extraction techniques for the off-line recognition are presented, including a connectionist approach for non-linear core height estimation. Results for uppercase, cursive and mixed case word recognition are reported. Finally a system combining the on- and off-line recognition is presented.

In adaptive noise cancelling, linear digital filters have been used to minimize the mean squared difference between filter outputs and the desired signal. However, for non-Gaussian probability density functions of the involved signals, nonlinear filters can further reduce the mean squared difference, thereby improving the signal-to-noise ratio at the system output. This is illustrated with a two-microphone beamformer for cancelling directional interference. In the case of a single uniformly distributed interference, we establish the optimum nonlinear performance limit. To approximate optimum performance, we realize two nonlinear filter architectures, the Volterra filter and the multilayer perceptron. The Volterra filter is also examined for speech interference. The beamformer is adapted to minimize the mean squared difference, but performance is measured with the intelligibility weighted gain. This criterion requires the signal-to-noise ratio at the beamformer output. For the nonlinear processor, this can only be determined when no target components exist in the reference channel of the noise canceller so that the target is transmitted without distortion. Under these ideal conditions and at equal filter lengths, the quadratic Volterra filter improves the intelligibility-weighted gain by maximally 2 dB relative to the linear filter.

Presents a writer independent system for on-line handwriting recognition which can handle both cursive script and hand-print. The pen trajectory is recorded by a touch sensitive pad, such as those used by note-pad computers. The input to the system contains the pen trajectory information, encoded as a time-ordered sequence of feature vectors. Features include X and Y coordinates, pen-lifts, speed, direction and curvature of the pen trajectory. A time delay neural network with local connections and shared weights is used to estimate a posteriori probabilities for characters in a word. A hidden Markov model segments the word into characters in a way which optimizes the global word score, taking a dictionary into account. A geometrical normalization scheme and a fast but efficient dictionary search are also presented. Trained on 20000 unconstrained cursive words from 59 writers and using a 25000 word dictionary the authors reached a 89% character and 80% word recognition rate on test data from a disjoint set of writers.>