Towards Author Recognition of Ancient Arabic Manuscripts Using Deep Learning: A Transfer Learning Approach

Khayyat, Manal M.; Elrefaei, Lamiaa A.

doi:10.12785/ijcds/090502

Cited by 7 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The salaf pesantren are not merely a medium for the internal transformation of students' self but are also related to the creation of communal ethics that determine how a santri navigates teachings, society, and religious identity (Chaplin, 2020). When discussing pesantren concerning learning, several models are needed to study ancient Arabic writing and see the importance of these manuscripts to enrich historical information (Khayyat & Elrefaei, 2020). This learning can improve Arabic language competence (Wahdan et al, 2020).…”

Section: Figure 2 Javanese Pegonmentioning

confidence: 99%

Learning Arabic Pegon for Non-Javanese Santri at Pesantren

Aziz

Sebgag

Zuana³

et al. 2022

Jurn. Pend. Islam

View full text Add to dashboard Cite

The difficulty of non-Javanese students learning Arabic and Islam using the Pegon method is a research topic that has yet to receive much attention from academics. This article aims to analyze the difficulties of non-Javanese students in the Pegon Method. Data were obtained through interviews, observation, and document analysis. The results of this study indicate that the difficulties of non-Javanese students are caused by the Javanese language used in the Pegon method. Furthermore, the Arabic or Hijaiyah letters used to write Pegon Javanese are slightly different from the original Arabic, and the scientific foundation of Arabic for students needs to be improved. Preparatory class programs, peer tutoring, and literature translation using the Pegon script into Indonesian are some strategies for anticipating student difficulties.

show abstract

Section: Figure 2 Javanese Pegonmentioning

confidence: 99%

Learning Arabic Pegon for Non-Javanese Santri at Pesantren

Aziz

Sebgag

Zuana³

et al. 2022

Jurn. Pend. Islam

View full text Add to dashboard Cite

show abstract

“…One of the feature extraction methods is using transfer learning techniques, namely using a pre-trained model [17]. The pre-trained architectural FaceNet model identifies one's facial identity for employee attendance [18] and class attendance [19] which results in accuracy above 95%.…”

Section: Introductionmentioning

confidence: 99%

Gender Classification on Video Using FaceNet Algorithm and Supervised Machine Learning

Adhinata¹,

Junaidi²

2022

IJCDS

View full text Add to dashboard Cite

Gender classification using human face data becomes a trending topic for researchers in the field of image processing and computer vision. The human face is biometric information that can be used to differentiate gender using a computer-aided system. Previous research utilised a local feature algorithm for extracting features on the face. However, the processing speed for one image was more than 2 seconds, making it unsuitable for real-time processing using video data. Processing video data requires a fast feature extraction algorithm because video data collects sequential images (frames). Moreover, the gender classification system's success is also measured by its accuracy, consequently it is necessary to choose the correct classification method to divide the two classes of men and women. In this research, we propose the FaceNet algorithm for feature extraction and explore several supervised machine learning methods (KNN, SVM, and Decision tree) appropriate for gender classification on video data. This study used 23,000 training data on each gender. From the experiment, combination of the FaceNet algorithm and KNN method resulted in the best accuracy of 95.75% with a processing speed of 0.059 seconds on each frame.

show abstract