Recognition of Arabic Handwritten Text by Integrating N-gram Model

Lamsaf, Asmae; Aitkerroum, Mounir; Boulaknadel, Siham; Fakhri, Yadolah

doi:10.1007/978-3-030-66840-2_112

Cited by 2 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the system of CNN, the database images should be the same size. It is known, the operation of normalization make the images in the same forms related to size [29]. In the present investigation, the size 100x100 was selected and presented in the same size.…”

Section: Normalizationmentioning

confidence: 99%

“…While in a recent paper, authors proposed method for recognizing Arabic handwritten word without segment them into sub letters merging the scale invariant feature transform (SIFT) as feature extractor and SVMs as classifer [28]. Likewise, in our previous work [29], we have proposed an amethod for recogning Arabic handwritten text using an integration of n-gram model.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recognition of Arabic handwritten words using convolutional neural network

Lamsaf

Kerroum

Boulaknadel

et al. 2022

IJEECS

Self Cite

View full text Add to dashboard Cite

<span>A new method for recognizing automatically Arabic handwritten words was presented using convolutional neural network architecture. The proposed method is based on global approaches, which consists of recognizing all the words without segmenting into the characters in order to recognize them separately. Convolutional neural network (CNN) is a particular supervised type of neural network based on multilayer principle; our method needs a big dataset of word images to obtain the best result. To optimize our system, a new database was collected from the benchmarking Arabic handwriting database using the pre-processing such as rotation transformation, which is applied on the images of the database to create new images with different features. The convolutional neural network applied on our database that contains 40320 of Arabic handwritten words (26880 images for training set and 13440 for test set). Thus, different configurations on a public benchmark database were evaluated and compared with previous methods. Consequently, it is demonstrated a recognition rate with a success of 96.76%.</span>

show abstract

Section: Normalizationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%