Development of Pose Estimation Algorithm for Quranic Arabic Word

Luqman Naim Mohd Esa, Malik Arman Morshidi, Syarah Munirah Mohd Zailani

Abstract


The study carried out in this report proposes the best keypoint detection, description, and pose estimation algorithm combination for Quranic Arabic words. Oriented-FAST Rotated-BRIEF (ORB) and Accelerated-KAZE (AKAZE) are used as the keypoint detection and description algorithms while Random Sample Consensus (RANSAC) and Least Median Squares (LMEDS) are used to evaluate the homography for pose estimation algorithms. The algorithms are combined with each other to provide four different techniques to estimate the pose of Quranic Arabic words. The algorithms are tested on a limited dataset chosen from a phrase within the Quran. Performance of each algorithm is measured in real-time through inlier to keypoint ratio which determines pose accuracy.


Keywords


pose estimation; ORB; AKAZE; RANSAC; LMEDS;

Full Text:

PDF


DOI: http://dx.doi.org/10.12928/telkomnika.v16i4.9048

Article Metrics

Abstract view : 46 times
PDF - 34 times

Refbacks

  • There are currently no refbacks.


Copyright (c) 2018 Universitas Ahmad Dahlan

TELKOMNIKA Telecommunication, Computing, Electronics and Control
ISSN: 1693-6930, e-ISSN: 2302-9293
Universitas Ahmad Dahlan, 4th Campus, 9th Floor, LPPI Room
Jl. Ringroad Selatan, Kragilan, Tamanan, Banguntapan, Bantul, Yogyakarta, Indonesia 55191
Phone: +62 (274) 563515, 511830, 379418, 371120 ext. 4902, Fax: +62 274 564604

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

View TELKOMNIKA Stats