Co-occurrence Matrix of Oriented Gradients for word script and nature identification

Saïdani, Asma; Kacem, Afef; Belaïd, Abdel

doi:10.1109/icdar.2015.7333717

Cited by 6 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For machine-printed/handwritten and Arabic/Latin word discrimination, we computed black run lengths (BRL) [4], histogram of oriented gradients (HOG), pyramid HOG [5] (PHOG) and cooccurrence matrices of oriented gradients (Co-MOG) [5]. The idea is to exploit the writing orientation as a discriminative descriptor between Arabic and Latin scripts.…”

Section: B Statistical Featuresmentioning

confidence: 99%

“…In [5], we made use of HOG-based features. Being based on shape descriptors, HOG has interesting properties for script characterization.…”

Section: B Statistical Featuresmentioning

confidence: 99%

“…We considered 24000 word images from public databases: IAM database for Latin handwritten, IFN-ENIT and AHTID/MW for Arabic handwritten and APTI for Arabic and Latin printed words. In [5], we took advantage of Co-MOG to express the distribution of gradient information over an image. These feature captures more spatial information than PHOG by counting the frequency of co-occurrences of oriented gradients between pairs of pixels.…”

Section: B Statistical Featuresmentioning

confidence: 99%

See 2 more Smart Citations

Impact of features and classifiers combinations on the performances of Arabic recognition systems

Echi

Belaïd

2017

2017 1st International Workshop on Arabic Script Analysis and Recognition (ASAR)

Self Cite

View full text Add to dashboard Cite

Arabic recognition is a very challenging task that begins to draw the attention of the OCR community. This work presents our latest contributions to this task, exploring the impact of several features and classifiers combinations on the performances of some developed systems. Different types of writings were considered (machine-printed, multi-fonts, handwritten, unconstrained, multi-writers, bi-dimensional, large vocabulary, ancient manuscripts). For each type of writing, we have considered both the most appropriate features and classifiers: contextual primitives to compensate the Arabic morphology variation, statistical features to recognize mathematical symbols and spectral features, mainly run lengths histogram-based features and histogram of oriented gradient-based descriptors to discriminate between machine-printed/handwritten and Arabic/Latin words. We have also used the shape context descriptor, for touching characters segmentation, which has been useful to train the models in the template-based recognition system. We have taken advantage of the Hough generalized transform to spot separator words in ancien arabic manuscripts. Otherwise Bayesian networks are used to apprehend the writing uncertainty and transparent neural networks to exploit the morphological aspect of Arabic language and integrate linguistic knowledge in the recognition process. The proposed systems are designed based on the characteristics, the similarities and the differences of Arabic writings.

show abstract

Section: B Statistical Featuresmentioning

confidence: 99%

“…In [5], we made use of HOG-based features. Being based on shape descriptors, HOG has interesting properties for script characterization.…”

Section: B Statistical Featuresmentioning

confidence: 99%

Section: B Statistical Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Impact of features and classifiers combinations on the performances of Arabic recognition systems

Echi

Belaïd

2017

2017 1st International Workshop on Arabic Script Analysis and Recognition (ASAR)

Self Cite

View full text Add to dashboard Cite

show abstract

“…But, we noted that including co-occurrence with various positional offsets, the features descriptors can express complex shapes of writing with local and global distributions of gradient orientations. That is why we proposed in recent work [12], the use of co-occurrence matrix of oriented gradients. This feature was applied on isolated words and this work is an attempt to use it for an automatic script and type identification in bilingual forms.…”

Section: Introductionmentioning

confidence: 99%

Automatic Script and Type Identification in Bi-lingual Forms

Echi¹

2016

IJCIS

View full text Add to dashboard Cite

Evaluation of Pooling Layers in Convolutional Neural Network for Script Recognition

İbrahim

Isa²,

Idrus

et al. 2019

Communications in Computer and Information Science

View full text Add to dashboard Cite

Co-occurrence Matrix of Oriented Gradients for word script and nature identification

Cited by 6 publications

References 17 publications

Impact of features and classifiers combinations on the performances of Arabic recognition systems

Impact of features and classifiers combinations on the performances of Arabic recognition systems

Automatic Script and Type Identification in Bi-lingual Forms

Evaluation of Pooling Layers in Convolutional Neural Network for Script Recognition

Contact Info

Product

Resources

About