Features for HMM-Based Arabic Handwritten Word Recognition Systems

Likforman-Sulem, Laurence; Mohammad, Ramy Al Hajj; Mokbel, Chafic; Menasri, F.; Bianne-Bernard, Anne-Laure; Kermorvant, Christopher

doi:10.1007/978-1-4471-4072-6_6

Cited by 9 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Applying this technique to the 'Institut fur Nachrichtentechnik' and 'Ecole Nationale d'Ingénieurs de Tunis' (IFN/ENIT) dataset [19], which involves 32,492 handwritten words, achieved an accuracy of 95.15%. Likforman-Sulem, et al [20] proposed sliding window-based feature extractions without implementing any segmentation on the input text. Statistical and structural features are extracted from each window, and the HMM classifier is implemented.…”

Section: Literature Reviewmentioning

confidence: 99%

A Deep Learning Approach for Arabic Manuscripts Classification

Al-homed,

Jambi,

Al-Barhamtoshy

2023

Sensors

View full text Add to dashboard Cite

For centuries, libraries worldwide have preserved ancient manuscripts due to their immense historical and cultural value. However, over time, both natural and human-made factors have led to the degradation of many ancient Arabic manuscripts, causing the loss of significant information, such as authorship, titles, or subjects, rendering them as unknown manuscripts. Although catalog cards attached to these manuscripts might contain some of the missing details, these cards have degraded significantly in quality over the decades within libraries. This paper presents a framework for identifying these unknown ancient Arabic manuscripts by processing the catalog cards associated with them. Given the challenges posed by the degradation of these cards, simple optical character recognition (OCR) is often insufficient. The proposed framework uses deep learning architecture to identify unknown manuscripts within a collection of ancient Arabic documents. This involves locating, extracting, and classifying the text from these catalog cards, along with implementing processes for region-of-interest identification, rotation correction, feature extraction, and classification. The results demonstrate the effectiveness of the proposed method, achieving an accuracy rate of 92.5%, compared to 83.5% with classical image classification and 81.5% with OCR alone.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A Deep Learning Approach for Arabic Manuscripts Classification

Al-homed,

Jambi,

Al-Barhamtoshy

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In the case of Arabic handwriting, the sliding window is shifted a small distance from the right to the left, and for each position. a feature vector is extracted [ 20 ]. When using sliding window-based features, typically, a large number of features are primarily extracted.…”

Section: Shape Descriptions Features For Arabic Handwriting Recognmentioning

confidence: 99%

Generative vs. Discriminative Recognition Models for Off-Line Arabic Handwriting

Elzobi

Al-Hamadi

2018

Sensors

View full text Add to dashboard Cite

The majority of handwritten word recognition strategies are constructed on learning-based generative frameworks from letter or word training samples. Theoretically, constructing recognition models through discriminative learning should be the more effective alternative. The primary goal of this research is to compare the performances of discriminative and generative recognition strategies, which are described by generatively-trained hidden Markov modeling (HMM), discriminatively-trained conditional random fields (CRF) and discriminatively-trained hidden-state CRF (HCRF). With learning samples obtained from two dissimilar databases, we initially trained and applied an HMM classification scheme. To enable HMM classifiers to effectively reject incorrect and out-of-vocabulary segmentation, we enhance the models with adaptive threshold schemes. Aside from proposing such schemes for HMM classifiers, this research introduces CRF and HCRF classifiers in the recognition of offline Arabic handwritten words. Furthermore, the efficiencies of all three strategies are fully assessed using two dissimilar databases. Recognition outcomes for both words and letters are presented, with the pros and cons of each strategy emphasized.

show abstract

“…Features extraction is a very important process in every OCR system; a lot of techniques have been adopted by searchers [8,9,21,37,55], some of which are: geometrical features (moments, histograms, and direction features), structural features (line element features, Fourier descriptors, topological features) and transformation methods [principal The last phase of a OCRS is building a recognizer. This stage is achieved in two steps.…”

Section: Related Workmentioning

confidence: 99%

“…The most common approaches are: neural networks (NN), support vector machine (SVM), hidden Markov models (HMM), decision tree, and more recently combined classifiers approaches [8,37,[40][41][42].…”

Section: Related Workmentioning

confidence: 99%

A novel fuzzy approach for handwritten Arabic character recognition

Kef

Chergui

Chikhi

2015

Pattern Anal Applic

View full text Add to dashboard Cite

The aim of our work is to present a new method based on structural characteristics and a fuzzy classifier for off-line recognition of handwritten Arabic characters in all their forms (beginning, end, middle and isolated). The proposed method can be integrated in any handwritten Arabic words recognition system based on an explicit segmentation process. First, three preprocessing operations are applied on character images: thinning, contour tracing and connected components detection. These operations extract structural characteristics used to divide the set of characters into five subsets. Next, features are extracted using invariant pseudo-Zernike moments. Classification was done using the Fuzzy ARTMAP neural network, which is very fast in training and supports incremental learning. Five Fuzzy ARTMAP neural networks were employed; each one is designed to recognize one subset of characters. The recognition process is achieved in two steps: in the first one, a clustering method affects characters to one of the five character subsets. In the second one, the pseudo-Zernike features are used by the appropriate Fuzzy ARTMAP classifier to identify the character. Training process and tests were performed on a set of character images manually extracted from the IFN/ENIT database. A height recognition rate was reported.

show abstract

Features for HMM-Based Arabic Handwritten Word Recognition Systems

Cited by 9 publications

References 15 publications

A Deep Learning Approach for Arabic Manuscripts Classification

A Deep Learning Approach for Arabic Manuscripts Classification

Generative vs. Discriminative Recognition Models for Off-Line Arabic Handwriting

A novel fuzzy approach for handwritten Arabic character recognition

Contact Info

Product

Resources

About