Performance of curvelets, dual-tree complex wavelet and discrete wavelet transform in handwritten word classification

Abstract

Handwritten words classification is a difficult task due to the high variability and uncertainty of human writing styles. The aim of this work is to Performance of curvelets, dual-tree complex wavelet and discrete wavelet transform in handwritten words classification. Curvelet transform, Dual-Tree complex wavelet transform (DTCWT), Haar, Daubechies, Coiflets, Symlet, Discrete Meyr, Biothogonal and reverse Biothogonal are used in this investigation. Three to four wavelets are chosen randomly from each wavelet family. A dataset of 534 handwritten Latin (HL) and Arabic (HA) word images out of 1068 (267 of each script) are used for training and the remaining is for testing. Energy and entropy are computed at different decomposition sub-bands. Support vector machines (SVM) and 1-NN are used for classification. An exhaustive experimentation is carried out on word images downloaded from IAM Handwriting Database for Latin words and from IFN/ENIT-database for Arabic handwritten words. The experiments showed that the best identification results are achieved using Curvelet transform followed by DTCWT .

Arabic/Latin and Machine-printed/Handwritten Word Discrimination using HOG-based Shape Descriptor

“…we cite now the most recent work that addresses the same issue, which are three works: [15], [30] and [28]. In [15] present a performance comparison of curvelet, dual-tree complex wavelet and discrete wavelet transform in handwritten words classification (Arabic and Latin).…”

“…In [15] present a performance comparison of curvelet, dual-tree complex wavelet and discrete wavelet transform in handwritten words classification (Arabic and Latin). A database of 1086 handwritten Latin (HL) and Arabic (HA) word images are used, 543 for training and 543 for testing.…”

Automatic Script and Type Identification in Bi-lingual Forms

“…considered in [9] affine moment invariants, the number and the XY position of the top and the bottom extrema, the maximal amplitude obtained from the difference between the top and the bottom profiles for Arabic/French and Handwritten/Printed words identification. In [10], Benjelil and al. present a performance comparison of curvelets, dual-tree complex wavelet and discrete wavelet transform in handwritten words classification (Arabic and Latin).…”