GMM-based handwriting style identification system for historical documents

  title={GMM-based handwriting style identification system for historical documents},
  author={Fouad Slimane and Torsten Scha{\ss}an and Volker M{\"a}rgner},
  journal={2014 6th International Conference of Soft Computing and Pattern Recognition (SoCPaR)},
In this paper, we describe a novel method for handwriting style identification. [] Key Method Our method is based on Gaussian Mixture Models (GMMs) using different kind of features computed using a combined fixed-length horizontal and vertical sliding window moving over a document page. For each writing style a GMM is built and trained using page images. At the recognition phase, the system returns log-likelihood scores. The GMM model with the highest score is selected. Experiments using page images from…

Figures from this paper

Core Region Detection for Off-Line Unconstrained Handwritten Latin Words Using Word Envelops

  • Shilpa PandeyGaurav Harit
  • Computer Science
    2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)
  • 2017
A new method for separating ascenders and descenders from an unconstrained handwritten word and identifying its core-region and promising results are obtained by the core- Region detection method when compared with the current state of the art methods.

Letter-based classification of Arabic scripts style in ancient Arabic manuscripts: Preliminary results

This paper proposed using segmented letters from Arabic manuscripts to recognize handwriting style using both Gabor Filters and Local Binary Pattern to extract features from letters.

Deep Learning and Image Processing for Handwritten Style Recognition



A New Text-Independent GMM Writer Identification System Applied to Arabic Handwriting

  • Fouad SlimaneV. Märgner
  • Computer Science
    2014 14th International Conference on Frontiers in Handwriting Recognition
  • 2014
This paper proposes a system for text-independent writer identification based on Arabic handwriting using only 21 features. Gaussian Mixture Models (GMMs) are used as the core of the system. GMMs

Writer and writing-style classification in the recognition of online handwriting

The starting point for the writing style analyses is an existing recognition system for online connected-cursive handwriting, and a neural-network technique, the Kohonen self-organizing map, is used to obtain a finite list of prototypical strokes (PS): A stroke alphabet (PSA).

A set of handwriting families: style recognition

  • J. Crettez
  • Computer Science
    Proceedings of 3rd International Conference on Document Analysis and Recognition
  • 1995
Based on an analysis of 980 different handwritten amounts, it is shown that these measures define a variability space of non-uniform density that allows to regroup handwriting styles into a small number of specific families.

Gaussian Mixture Models for Arabic Font Recognition

A new approach to use a fixed-length sliding window for the feature extraction and to model feature distributions with Gaussian Mixture Models (GMMs) which presents a double advantage for Arabic font recognition.

On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey

The nature of handwritten language, how it is transduced into electronic data, and the basic concepts behind written language recognition algorithms are described.

A New Baseline Estimation Method Applied to Arabic Word Recognition

It is shown that classical baseline identification approaches using horizontal projection histograms may fail in detecting accurately the baseline of short words, impacting the overall processing chain and inducing errors, and a novel approach based on stochastic models able to propose probable baseline regions from characters features is proposed.

Speaker Verification Using Adapted Gaussian Mixture Models

The major elements of MIT Lincoln Laboratory's Gaussian mixture model (GMM)-based speaker verification system used successfully in several NIST Speaker Recognition Evaluations (SREs) are described.

Labeled images verification using Gaussian mixture models

An automated system to verify that images are correctly associated to labels as well as in several improvements introduced specifically for the verification task, using Gaussian Mixture Models as statistical modeling scheme.

Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper

Vibratory power unit for vibrating conveyers and screens comprising an asynchronous polyphase motor, at least one pair of associated unbalanced masses disposed on the shaft of said motor, with the