In this paper, we give a comprehensive description of our writer-independent online handwriting recognition system frog on hand. The focus of this work concerns the presentation of the classification/training approach, which we call cluster generative statistical dynamic time warping (CSDTW). CSDTW is a general, scalable, HMM-based method for variable-sized, sequential data that holistically combines cluster analysis and statistical sequence modeling. It can handle general classification problems that rely on this sequential type of data, e.g., speech recognition, genome processing, robotics, etc. Contrary to previous attempts, clustering and statistical sequence modeling are embedded in a single feature space and use a closely related distance measure. We show character recognition experiments of frog on hand using CSDTW on the UNIPEN online handwriting database. The recognition accuracy is significantly higher than reported results of other handwriting recognition systems. Finally, we describe the real-time implementation of frog on hand on a Linux Compaq iPAQ embedded device.

/pdf/the-writer-independent-online-handwriting-recognition-system-265aci8tbn.pdf

The writer independent online handwriting recognition system frog on hand and cluster generative statistical dynamic time warping

Online handwriting recognition of Arabic script is a difficult problem since it is naturally both cursive and unconstrained. The analysis of Arabic script is further complicated in comparison to Latin script due to obligatory dots/stokes that are placed above or below most letters. This paper introduces a Hidden Markov Model (HMM) based system to provide solutions for most of the difficulties inherent in recognizing Arabic script including: letter connectivity, position-dependent letter shaping, and delayed strokes. This is the first HMM-based solution to online Arabic handwriting recognition. We report successful results for writerdependent and writer-independent word recognition.

/pdf/online-arabic-handwriting-recognition-using-hidden-markov-28dcg4yr5b.pdf

Online Arabic Handwriting Recognition Using Hidden Markov Models

This paper investigates the use of three different schemes to optimize the number of states of linear left-to-right hidden Markov models (HMM). In the first method, we describe the fixed length modeling scheme where each character model is assigned the same number of states. The second method considered is the Bakis length modeling where the number of model states is set to a given fraction of the average number of observations of the corresponding character. In the third modeling scheme the number of model states is set to a specified quantile of the corresponding character length histogram. This method is called quantile length modeling. A comparison of different length modeling schemes was carried out with a handwriting recognition system using off-line images of cursively handwritten English words from the IAM database. For the fixed length modeling, a recognition rate of 61% was achieved. Using the Bakis or quantile length modeling the word recognition rates could be improved to over 69%.

Hidden Markov model length optimization for handwriting recognition systems

We investigate a new approach for online handwritten shape recognition. Interesting features of this approach include learning without manual tuning, learning from very few training samples, incremental learning of characters, and adaptation to the user-specific needs. The proposed system can deal with two-dimensional graphical shapes such as Latin and Asian characters, command gestures, symbols, small drawings, and geometric shapes. It can be used as a building block for a series of recognition tasks with many applications

Online Handwritten Shape Recognition Using Segmental Hidden Markov Models

Hidden Markov models using the fully-connected, left-right and left-right banded model structures are applied to the problem of alphabetical letter gesture recognition. We examine the effect of training techniques, in particular the Baum-Welch and Viterbi path counting techniques, on each of the model structures. We show that recognition rates improve when moving from a fully-connected model to a left-right model and a left-right banded 'staircase' model with peak recognition rates of 84.8%, 92.31% and 97.31% respectively. The left-right banded model in conjunction with the Viterbi path counting present the best performance. Direct calculation of model parameters from analysis of the physical system was also tested, yielding a peak recognition rate of 92%, but the simplicity and efficiency of this approach is of interest.

/pdf/model-structure-selection-training-algorithms-for-an-hmm-1t53aqvzts.pdf

Model structure selection & training algorithms for an HMM gesture recognition system

Although HMM is widely used for online handwriting recognition, there is no simple and well-established method of designing the HMM topology. We propose a data-driven systematic method to design HMM topology. Data samples in a single pattern class are structurally simplified into a sequence of straight-line segments. Then the resulting multiple models of the class are combined to form an architecture of a multiple parallel-path HMM, which behaves as single HMM. To avoid excessive growing of the number of the states, parameter trying is applied such that structural similarity among patterns is reflected. Experiments on online Hangul recognition showed about 19% of error reductions, compared to the intuitive deisgn method.

/pdf/data-driven-design-of-hmm-topology-for-online-handwriting-44b6rpe724.pdf

Jin H. Kim

Papers

Data-driven design of HMM topology for online handwriting recognition