Cite Article

High-Quality Wavelets Features Extraction for Handwritten Arabic Numerals Recognition

Choose citation format

BibTeX

@article{IJASEIT6809,
   author = {M. Suhail Akhtar and Hammad A. Qureshi and Hani Al-Quhayz},
   title = {High-Quality Wavelets Features Extraction for Handwritten Arabic Numerals Recognition},
   journal = {International Journal on Advanced Science, Engineering and Information Technology},
   volume = {9},
   number = {2},
   year = {2019},
   pages = {700--710},
   keywords = {Wavelets analysis, Wavelet packets analysis, Handwritten digits recognition, k-NNs, SVMs},
   abstract = {

Arabic handwritten digit recognition is the science of recognition and classification of handwritten Arabic digits. It has been a subject of research for many years with rich literature available on the subject.  Handwritten digits written by different people are not of the same size, thickness, style, position or orientation. Hence, many different challenges have to overcome for resolving the problem of handwritten digit recognition.  The variation in the digits is due to the writing styles of different people which can differ significantly.  Automatic handwritten digit recognition has wide application such as automatic processing of bank cheques, postal addresses, and tax forms. A typical handwritten digit recognition application consists of three main stages namely features extraction, features selection, and classification. One of the most important problems is feature extraction. In this paper, a novel feature extraction approach for off-line handwritten digit recognition is presented. Wavelets-based analysis of image data is carried out for feature extraction, and then classification is performed using various classifiers. To further reduce the size of training data-set, high entropy subbands are selected. To increase the recognition rate, individual subbands providing high classification accuracies are selected from the over-complete tree. The features extracted are also normalized to standardize the range of independent variables before providing them to the classifier. Classification is carried out using k-NN and SVMs. The results show that the quality of extracted features is high as almost equivalently high classification accuracies are acquired for both classifiers, i.e. k-NNs and SVMs.

},    issn = {2088-5334},    publisher = {INSIGHT - Indonesian Society for Knowledge and Human Development},    url = {http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=6809},    doi = {10.18517/ijaseit.9.2.6809} }

EndNote

%A Akhtar, M. Suhail
%A A. Qureshi, Hammad
%A Al-Quhayz, Hani
%D 2019
%T High-Quality Wavelets Features Extraction for Handwritten Arabic Numerals Recognition
%B 2019
%9 Wavelets analysis, Wavelet packets analysis, Handwritten digits recognition, k-NNs, SVMs
%! High-Quality Wavelets Features Extraction for Handwritten Arabic Numerals Recognition
%K Wavelets analysis, Wavelet packets analysis, Handwritten digits recognition, k-NNs, SVMs
%X 

Arabic handwritten digit recognition is the science of recognition and classification of handwritten Arabic digits. It has been a subject of research for many years with rich literature available on the subject.  Handwritten digits written by different people are not of the same size, thickness, style, position or orientation. Hence, many different challenges have to overcome for resolving the problem of handwritten digit recognition.  The variation in the digits is due to the writing styles of different people which can differ significantly.  Automatic handwritten digit recognition has wide application such as automatic processing of bank cheques, postal addresses, and tax forms. A typical handwritten digit recognition application consists of three main stages namely features extraction, features selection, and classification. One of the most important problems is feature extraction. In this paper, a novel feature extraction approach for off-line handwritten digit recognition is presented. Wavelets-based analysis of image data is carried out for feature extraction, and then classification is performed using various classifiers. To further reduce the size of training data-set, high entropy subbands are selected. To increase the recognition rate, individual subbands providing high classification accuracies are selected from the over-complete tree. The features extracted are also normalized to standardize the range of independent variables before providing them to the classifier. Classification is carried out using k-NN and SVMs. The results show that the quality of extracted features is high as almost equivalently high classification accuracies are acquired for both classifiers, i.e. k-NNs and SVMs.

%U http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=6809 %R doi:10.18517/ijaseit.9.2.6809 %J International Journal on Advanced Science, Engineering and Information Technology %V 9 %N 2 %@ 2088-5334

IEEE

M. Suhail Akhtar,Hammad A. Qureshi and Hani Al-Quhayz,"High-Quality Wavelets Features Extraction for Handwritten Arabic Numerals Recognition," International Journal on Advanced Science, Engineering and Information Technology, vol. 9, no. 2, pp. 700-710, 2019. [Online]. Available: http://dx.doi.org/10.18517/ijaseit.9.2.6809.

RefMan/ProCite (RIS)

TY  - JOUR
AU  - Akhtar, M. Suhail
AU  - A. Qureshi, Hammad
AU  - Al-Quhayz, Hani
PY  - 2019
TI  - High-Quality Wavelets Features Extraction for Handwritten Arabic Numerals Recognition
JF  - International Journal on Advanced Science, Engineering and Information Technology; Vol. 9 (2019) No. 2
Y2  - 2019
SP  - 700
EP  - 710
SN  - 2088-5334
PB  - INSIGHT - Indonesian Society for Knowledge and Human Development
KW  - Wavelets analysis, Wavelet packets analysis, Handwritten digits recognition, k-NNs, SVMs
N2  - 

Arabic handwritten digit recognition is the science of recognition and classification of handwritten Arabic digits. It has been a subject of research for many years with rich literature available on the subject.  Handwritten digits written by different people are not of the same size, thickness, style, position or orientation. Hence, many different challenges have to overcome for resolving the problem of handwritten digit recognition.  The variation in the digits is due to the writing styles of different people which can differ significantly.  Automatic handwritten digit recognition has wide application such as automatic processing of bank cheques, postal addresses, and tax forms. A typical handwritten digit recognition application consists of three main stages namely features extraction, features selection, and classification. One of the most important problems is feature extraction. In this paper, a novel feature extraction approach for off-line handwritten digit recognition is presented. Wavelets-based analysis of image data is carried out for feature extraction, and then classification is performed using various classifiers. To further reduce the size of training data-set, high entropy subbands are selected. To increase the recognition rate, individual subbands providing high classification accuracies are selected from the over-complete tree. The features extracted are also normalized to standardize the range of independent variables before providing them to the classifier. Classification is carried out using k-NN and SVMs. The results show that the quality of extracted features is high as almost equivalently high classification accuracies are acquired for both classifiers, i.e. k-NNs and SVMs.

UR - http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=6809 DO - 10.18517/ijaseit.9.2.6809

RefWorks

RT Journal Article
ID 6809
A1 Akhtar, M. Suhail
A1 A. Qureshi, Hammad
A1 Al-Quhayz, Hani
T1 High-Quality Wavelets Features Extraction for Handwritten Arabic Numerals Recognition
JF International Journal on Advanced Science, Engineering and Information Technology
VO 9
IS 2
YR 2019
SP 700
OP 710
SN 2088-5334
PB INSIGHT - Indonesian Society for Knowledge and Human Development
K1 Wavelets analysis, Wavelet packets analysis, Handwritten digits recognition, k-NNs, SVMs
AB 

Arabic handwritten digit recognition is the science of recognition and classification of handwritten Arabic digits. It has been a subject of research for many years with rich literature available on the subject.  Handwritten digits written by different people are not of the same size, thickness, style, position or orientation. Hence, many different challenges have to overcome for resolving the problem of handwritten digit recognition.  The variation in the digits is due to the writing styles of different people which can differ significantly.  Automatic handwritten digit recognition has wide application such as automatic processing of bank cheques, postal addresses, and tax forms. A typical handwritten digit recognition application consists of three main stages namely features extraction, features selection, and classification. One of the most important problems is feature extraction. In this paper, a novel feature extraction approach for off-line handwritten digit recognition is presented. Wavelets-based analysis of image data is carried out for feature extraction, and then classification is performed using various classifiers. To further reduce the size of training data-set, high entropy subbands are selected. To increase the recognition rate, individual subbands providing high classification accuracies are selected from the over-complete tree. The features extracted are also normalized to standardize the range of independent variables before providing them to the classifier. Classification is carried out using k-NN and SVMs. The results show that the quality of extracted features is high as almost equivalently high classification accuracies are acquired for both classifiers, i.e. k-NNs and SVMs.

LK http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=6809 DO - 10.18517/ijaseit.9.2.6809