Natural Handwriting Research Articles

Off-line isolated handwritten Thai OCR using island-based projection with n-gram model and hidden Markov models

Many traditional works on off-line Thai handwritten character recognition used a set of local features including circles, concavity, endpoints and lines to recognize hand-printed characters. However, in natural handwriting, these local features are often missing due to rough or quick writing, resulting in dramatic reduction of recognition accuracy. Instead of using such local features, this paper presents a method called multi-directional island-based projection to extract global features from handwritten characters. As the recognition model, two statistical approaches, namely interpolated n-gram model ( n-gram) and hidden Markov model (HMM), are proposed. The experimental results indicate that the proposed scheme achieves high accuracy in the recognition of naturally-written Thai characters with numerous variations, compared to some common previous feature extraction techniques. Another experiment with English characters also displays quite promising results.

Towards an art based mathematical editor, that uses on-line handwritten symbol recognition

A new mathematical editor, based on the recognition of run-on discrete handwritten symbols, is proposed. The tested laboratory prototype of the system, modular and adaptable to the user habits and site requirements, uses a natural handwriting interface as well as human gestures. Two methods were used for symbol recognition, namely the state-of-the-art elastic matching algorithm and an Adaptive Resonance Theory neural architecture. The neural solution is proved to be better adapted to the cognitive nature of the problem and faster in both learning and test phases. Finally a novel attribute grammar permits the detection and subsequent correction of errors in the mathematical expressions.

Expertise in person recognition

The dramatic effect of inversion on the episodic recognition of unfamiliar faces has been considered as proof of specific mechanisms for the processing of faces. This view was challenged by Diamond and Carey (1986), who observed similar effects when photographs of dogs were shown to dog experts. However, they compared experts with younger novices, they used identical photographs at encoding and at test, their experts were no more accurate than the novices in the recognition of dogs, and dog recognition is remote from other inputs to the person recognition system such as natural handwriting. In Experiment 1, the results of Diamond and Carey were replicated with natural handwriting as stimuli, with novices matched in age to the experts, and with different structural representations of the targets at encoding and during the recognition test. In Experiment2, younger novices participated, but this did not affect the pattern of results. Experiment 3 showed that the results were not due to floor effects.

Models for the generation of writing units in handwriting under variation of size, slant, and orientation

This study presents empirical data concerning the psychological validity of fourteen different computational models for the production of writing strokes in handwriting. An earlier study reviewed the mathematical properties of several published models and of some further models developed by the authors. In the present study these fourteen models were compared with regard to the criterion that global parameters, such as size, slant, and orientation of the handwriting, should not affect the fit between the simulated writing trace and the specimens of natural handwriting. This prediction was based upon a characteristic of a psychomotor model of handwriting, developed by one of the authors, which assumes that global parameters are set by independent and hierarchically higher processors than the more peripheral, biophysical-force generators that produce the particular concrete stroke trajectories. The results show that those models that produce a close fit to natural handwriting in a standard condition, yield the best fits under variation of size, slant, and orientation. All models with consistent results appear to have in common that the timing of the transition points remains unaffected by global parameter settings.

An evaluation of motor models of handwriting

A general method is presented for describing and analyzing biomedical handwriting models. Using Laplace's transform theory, a model can be represented in what is called the neural firing-rate domain. Consistent terminology is proposed to facilitate model evaluation and comparison. An overview of previously published models suggests that they could be described using this method, with second- and third-order linear model representation. Fourteen simplified theoretical models are simulated in an experiment designed to study the parameter domain in which handwriting is controlled by the nervous system in order to gain insight into which type of model provides the best reconstruction of natural handwriting. Results show that velocity-controlled models produce the best outputs, with no significant difference between second- and third-order systems. In handwriting, fine motor behavior is thus velocity-controlled. These findings agree with other recent automatic signature verification results and are of interest for a number of applications, from pattern recognition to handwriting education.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Disguised handwriting

This paper presents a study on disguised handwriting. Due to several changes of standard handwriting systems in Sweden, people of different ages have acquired different systems in school. Ninety-eight persons took part in the study and were divided into three groups regarding age, social background and/or occupation. They copied a text twice, the first time using their natural handwriting and the second time trying to disguise the writing. The purpose of the study was to examine which characteristics were most frequently disguised or which methods were most used, and if there were any significant differences between the groups. The results showed that a majority followed what is considered to be the common pattern of the most popular methods of disguise but that there were certain interesting differences between the groups.

Changing Slant: Is It the Only Change?

Abstract The examination of handwriting for identification purposes provides many interesting and thought-provoking problems. One of the most commonly encountered challenges arises when an individual consciously attempts to change, alter, or otherwise disguise the presence and appearance of normal, natural handwriting characteristics. Included among these mindful attempts are capital letter style changes, alteration of normal writing slant, and use of the awkward hand, to name just a few [1]. Throughout all such attempts, the fundamental axiom remains that the writing is not completely natural. However, while such attempts are a contrived, forced effort, in many cases they still contain those unique and individual characteristics upon which an identification or elimination can be based.

A Comprehensive Survey on On-line Handwriting Recognition Technology and its Real Application to the Nepalese Natural Handwriting

Handwriting Recognition Technology has been improving much under the purview of pattern recognition and image processing since a few decades. This paper focuses on the comprehensive survey on on-line handwriting recognition system along with the real application by taking Nepali natural handwriting (a real example of one of the cursive handwritings). The survey mainly includes pre-processing, feature vector and similarity measures in between the non-linear 2D sequences of coordinates, and their effective applications. A very highlighting topic "Dynamic Time Warping Algorithm'' (DTW) is introduced, which has been popular in determining the distance between two non-linear sequences ranging from handwriting to speech recognition. Besides these contemporary research issues/areas, stroke number and order free Nepalese natural handwritten recognition system is presented in the second step. Writing one's own style brings unevenness in writing units, which is the most difficult part to classify. Writing units reveal number, shape, size, order of stroke, and speed in writing. Variation in the number of strokes, their order, shapes and sizes, tilting angles and similarities among characters from one another are the important factors, which are to be considered in classification for Nepali. This paper utilizes structural properties of those alphanumeric characters, which have variable writing units. It uses a string of pen tip's positions and tangent angles of every consecutive point as a feature vector sequence of a stroke. We constructed a prototype recognizer that uses the DTW algorithm to align handwritten strokes with stored strokes' templates and determine their similarity. Separate system is trained for original and preprocessed writing samples and achieved recognition rates of 85.87% and 88.59% respectively. This introduces novel real time handwriting recognition on Nepalese alphanumeric characters, which are independent of number of strokes, as well as their order. Key Words: Handwriting Recognition System; Pre-processing; Feature Vector; Dynamic Time Warping; Agglomerating Hierarchical Clustering; Nepali. DOI: 10.3126/kuset.v5i1.2845 Kathmandu University Journal of Science, Engineering and Technology Vol.5, No.1, January 2009, pp 31-55