Ridgelet-DTW-based word spotting for Arabic historical document
- 1 September 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA)
Abstract
In this paper we propose a system for word spotting in Arabic historical document using Ridgelet transform and Dynamic Time Warping (DTW). First, a preprocessing and segmentation processes are applied to all document pages to create a word image dataset. Keeping each word into its original size, Ridgelet descriptor is generated without applying the normalization criteria for Radon transform, where the rotation, translation and scaling invariance is achieved. Therefore, DTW algorithm is employed to match corresponding projection angle pairs from Ridgelet descriptor, while avoiding problems associated with dimensionality reduction of descriptor sets into one vector which cause a loss of useful information. Experiments were conducted on historical Arabic document from the National library. The obtained results showed the effectiveness of the proposed method.Keywords
This publication has 29 references indexed in Scilit:
- Machine printed handwritten text discrimination using Radon transform and SVM classifierPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Handwritten character recognition using wavelet energy and extreme learning machineInternational Journal of Machine Learning and Cybernetics, 2011
- Persian/arabic handwritten word recognition using M-band packet wavelet transformImage and Vision Computing, 2008
- Retrieval and classification of shape-based objects using Fourier, generic Fourier, and wavelet-Fourier descriptors technique: A comparative studyOptics and Lasers in Engineering, 2007
- A new shape descriptor defined on the Radon transformComputer Vision and Image Understanding, 2006
- Translation invariants of Zernike momentsPattern Recognition, 2003
- Ridgelets: a key to higher-dimensional intermittency?Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 1999
- Shape Representation and Recognition from Multiscale CurvatureComputer Vision and Image Understanding, 1997
- Orthogonal moment features for use with parametric and non-parametric classifiersIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996
- Use of the Radon transform as a method of extracting information about shape in two dimensionsImage and Vision Computing, 1992