Arabic Handwriting Recognition Using Concavity Features and Classifier Fusion

Azeem, Sherif Abdel; Meseery, Maha El

doi:10.1109/icmla.2011.36

Cited by 4 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, to improve the performance of the classification, complementary features, like concavities, have been explored [1,18,14].…”

Section: Introductionmentioning

confidence: 99%

Handwritten Digit Recognition Based on Pooling SVM-Classifiers Using Orientation and Concavity Based Features

Saavedra¹

2014

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

In order to increase the performance in the handwritten digit recognition field, researchers commonly combine a variety of features to represent a pattern. This approach has showed to be very effective in practice. The classical approach to combine features is by concatenating the underlying feature vectors. A drawback of this approach is that it could generate high-dimensional descriptors, which increases the complexity of the training process. Instead, we propose to use a pooling based classifier, that allow us to get not only a faster training process but also outperforming results. For evaluation, we used two state-of-the-art handwritten digit datasets: CVL and MNIST. In addition, we show that a simple rectangular spatial division, that characterize our descriptors, yields competitive results and a smaller computation cost with respect to other more complex zoning techniques.

show abstract

“…In addition, to improve the performance of the classification, complementary features, like concavities, have been explored [1,18,14].…”

Section: Introductionmentioning

confidence: 99%

Handwritten Digit Recognition Based on Pooling SVM-Classifiers Using Orientation and Concavity Based Features

Saavedra¹

2014

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

show abstract

“…One of two approaches has, commonly, been followed in most of thinning algorithms, the iterative approach and noniterative approach [2][3][4][5][6][7]. In the iterative approach, pixels on the boundary are examined (either in sequential or parallel) and successively deleted until a skeleton of one pixel width is obtained.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Thinning Algorithm for Arabic OCR Systems

Ali¹

2012

SIPIJ

View full text Add to dashboard Cite

This paper address an efficient iterative thinning algorithm based on boundary pixels deletion using colour coding for different pixel types. A black pixel is tested by observing neighbouring pixels, and it gives us an efficient way to decide whether the pixel is deleted or not. In the propose algorithm number of 3x3 templates were used to make good deleting decision, then we delete the pixels which satisfy the deletion templates until there is no pixel that can be deleted. Other templates were used for discontinuity recovery. This algorithm allows us to deal with typical troublesome handwritten text efficiently. Without smoothing before thinning, the algorithm produces robust skeleton even in the presence of noises. The algorithm produces skeletons that are more representative of the shape of the original patterns and with less noise spurs. The algorithm is considered fast enough to be used in Arabic OCR systems.

show abstract

New Segmentation Method for Analytical Recognition of Arabic Handwriting Using a Neural-Markovian Method

Fergani

Bennia

2018

IJET

View full text Add to dashboard Cite

A new hybrid system of off-line analytical recognition of Arabic handwriting combining a neural network type multi-layer perceptron (MLP) and hidden Markov models (HMM) is presented. We propose a way to cooperate HMM and MLP neural network in a probabilistic architecture taking advantage of both tools dedicated to the recognition of Arabic literal amounts. This description is based on statistical and structural characteristics extraction of the significant character of the handwritten Arabic words, which can be used in the MLP classification module to estimate probabilities used as the observations to perform a recognition by the HMM. The originality of our approach is based on the segmentation into characters taking into account diacritics with the characters that match them. The experiments show the convergence of the global system, even with a random initialization of the neural network.Keywords - Recognition of Arabic handwriting, hidden Markov models, fast K-means, Arabic literal amounts, multi-layer perceptron. * E-mail: khaoula_1190@hotmail.com

show abstract

Arabic Handwriting Recognition Using Concavity Features and Classifier Fusion

Cited by 4 publications

References 8 publications

Handwritten Digit Recognition Based on Pooling SVM-Classifiers Using Orientation and Concavity Based Features

Handwritten Digit Recognition Based on Pooling SVM-Classifiers Using Orientation and Concavity Based Features

An Efficient Thinning Algorithm for Arabic OCR Systems

New Segmentation Method for Analytical Recognition of Arabic Handwriting Using a Neural-Markovian Method

Contact Info

Product

Resources

About