Gabor features for offline Arabic handwriting recognition

Chen, Jin; Cao, Huaigu; Prasad, Rohit; Bhardwaj, Anurag; Natarajan, Prem

doi:10.1145/1815330.1815337

Cited by 58 publications

(29 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Arabic texts, like the |Xam texts, contain complex diacritics. In one approach to recognising Arabic text, 34 of the most commonly occurring Arabic sub-words were recognised using a support vector machine without paying specific attention to the diacritics [5] and a recognition accuracy of 84.3% was achieved. This is a relatively high recognition rate, though the number of classes that needed to be recognised (34) was relatively low.…”

Section: Related Workmentioning

confidence: 99%

“…A Gabor filter is a Gaussian function modulated by a complex sinusoid in both the spatial domain and frequency domain and contains both a real and imaginary part [5]. Gabor filters are orientation specific [5] and thus they have been used for extracting stroke information from characters for use as features for character recognition [24].…”

Section: Gabor Filtersmentioning

confidence: 99%

“…Gabor filters are orientation specific [5] and thus they have been used for extracting stroke information from characters for use as features for character recognition [24]. Basically, Gabor filters are applied to an image at different orientations to extract orientation information.…”

Section: Gabor Filtersmentioning

confidence: 99%

“…The approach used to create Gabor filter-based features is the same as that of Chen at al [5] and is briefly described here. For a frequency f , which is based on the width of a handwriting stroke, and a stroke orientation angle θ, a Gabor filter is applied to an image.…”

Section: Gabor Filtersmentioning

confidence: 99%

See 3 more Smart Citations

A comparison of machine learning techniques for handwritten |Xam word recognition

Williams

Suleman

Paihama

2013

Proceedings of the South African Institute for Computer Scientists and Information Technologists Conference

View full text Add to dashboard Cite

The Bleek and Lloyd collection contains 19th century handwritten notebooks that document the language and culture of the |Xam-speaking people who lived in Southern Africa. Access to this rich data could be enhanced by transcriptions of the text; however, the complex diacritics used in the notebooks complicate the process of transcription. Machine learning techniques could be used to perform this transcription, but it is not known which techniques would produce the best results. This paper thus reports on a comparison of 3 popular techniques applied to this problem: artificial neural networks (ANN); hidden Markov models (HMM); and support vector machines (SVM). It was found that an SVM-based classifier using histograms of oriented gradients as features resulted in the best word recognition accuracy of 58.4%. Furthermore, it was found that most feature extraction parameters did not have a large effect on recognition accuracy and that the SVM-based recognisers outperform both ANN-and HMM-based recognisers.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Gabor Filtersmentioning

confidence: 99%

Section: Gabor Filtersmentioning

confidence: 99%

Section: Gabor Filtersmentioning

confidence: 99%

See 2 more Smart Citations

A comparison of machine learning techniques for handwritten |Xam word recognition

Williams

Suleman

Paihama

2013

Proceedings of the South African Institute for Computer Scientists and Information Technologists Conference

View full text Add to dashboard Cite

show abstract

“…They used the concept of reservoir for the recognition of curved document text B. B. Chaudhuri and U. Pal [24] have proposed different methods for skew angle detection in the scanned documented Bangla script. They obtained mean and standard deviation of given skewed document and apply Hough transform, to find connected components in the binary document image .…”

Section: Introductionmentioning

confidence: 99%

Conversion and Recognition of Handwritten Devnagari Character String into Printed Character String Using KNN

Pilawan¹,

Bhalerao²,

Nandedkar³

et al. 2017

IJERT

View full text Add to dashboard Cite

Abstract-This paper presents a system for the conversion of handwritten string of Devnagari character to printed character string by using character segmentation approach. 11 different statistical features of segmented characters are extracted which are compared with features extracted from printed string of characters available in training data for cross validation purpose using K-nearest neighborhood (kNN) algorithm.Use of handwritten string of Devnagari characters written in different styles and converting it into printed string makes the system more prone to real life application. System mainly works on segmentation of characters using bounding box, after segmentation, features are extracted which is compared with training feature set. We have analyzed our system with existing Devnagari handwritten character recognition systems. In given framework, we have focused on a creating database in different styles and recognizing them as printed characters.

show abstract

Continuous Handwritten Script Recognition

Frinken

Bunke²

2014

Handbook of Document Image Processing and Recognition

View full text Add to dashboard Cite

Gabor features for offline Arabic handwriting recognition

Cited by 58 publications

References 14 publications

A comparison of machine learning techniques for handwritten |Xam word recognition

A comparison of machine learning techniques for handwritten |Xam word recognition

Conversion and Recognition of Handwritten Devnagari Character String into Printed Character String Using KNN

Continuous Handwritten Script Recognition

Contact Info

Product

Resources

About