An application of the Hough transform to automatic recognition of Berber characters

Oulamara, Ammar; Duvernoy, J.

doi:10.1016/0165-1684(88)90045-x

Cited by 10 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Oulamara and Duvernoy [10] extracted features of straight segments using the Hough transform to extract with their attributes (length and orientation). Features vectors were generated by analyzing the characters in the parametric space.…”

Section: Previous Workmentioning

confidence: 99%

Tifinagh handwritten character recognition using optimized convolutional neural network

Niharmine

Outtaj

Azouaoui

2022

IJECE

View full text Add to dashboard Cite

<p><span>Tifinagh handwritten character recognition has been a challenging problem due to the similarity and variability of its alphabets. This paper proposes an optimized convolutional neural network (CNN) architecture for handwritten character recognition. The suggested model of CNN has a multi-layer feed-forward neural network that gets features and properties directly from the input data images. It is based on the newest deep learning open-source Keras Python library. The novelty of the model is to optimize the optical character recognition (OCR) system in order to obtain best performance results in terms of accuracy and execution time. The new optical character recognition system is tested on a customized dataset generated from the amazigh handwritten character database. Experimental results show a good accuracy of the system (99.27%) with an optimal execution time of the classification compared to the previous works.</span></p>

show abstract

Section: Previous Workmentioning

confidence: 99%

Tifinagh handwritten character recognition using optimized convolutional neural network

Niharmine

Outtaj

Azouaoui

2022

IJECE

View full text Add to dashboard Cite

show abstract

“…However, only a few studies are attested on handwritten characters of Amazigh scripts. Recently, some efforts have been reported in literature for Amazigh characters based on the Hough transformation [11], the statistical and geometrical approaches [12], artificial neural network [13], [14], Hidden Markov Models [15], syntactical method based on the finite-state machines [16] and dynamic programming [17]. Besides, as far as we know, there has no standard database for Amazigh characters, which allows objective comparisons between different systems.…”

Section: Introductionmentioning

confidence: 99%

“…Besides, as far as we know, there has no standard database for Amazigh characters, which allows objective comparisons between different systems. All published works in [11][12][13][14][15][16][17] have been tested on local databases, which contain a restricted number of Amazigh characters. With the exception of the database of the Amazigh printed graphic developed in [13], which contains about 20000 printed characters.…”

Section: Introductionmentioning

confidence: 99%

AMHCD: A Database for Amazigh Handwritten Character Recognition Research

Es-Saady¹,

Rachidi²,

Yassa³

et al. 2011

IJCA

View full text Add to dashboard Cite

In this paper, we describe the first version of a database that contains handwritten Amazigh characters (AMHCD). As present the database consists of 25,740 isolated and labeled Amazigh handwritten characters produced by 60 writers. This database has been developed at the IRF-SIC Laboratory of the university Ibn Zohr, Agadir, Morocco. It is designed for training and testing recognition systems for handwritten Amazigh characters. This database is available for researches and academic uses.

show abstract