Analisis Kinerja Deteksi Algoritma FAST dan Algoritma MSER pada Citra Digital Berbasis Marker
DOI:
https://doi.org/10.30595/jrst.v5i2.7796Keywords:
Augmented Reality, Feature from Accelerated Segment Test, Maximally Stable Extremal Regions, Penanda ARAbstract
Aungmented Reality (AR) membutuhkan algoritma yang baik dan tahan terhadap gangguan-gangguan yang dapat terjadi saat proses deteksi marker seperti perubahan pencahayaan, perubahan rotasi marker, dan blur pada kamera. Algoritma Feature from Accelerated Segment Test (FAST) dan algoritma Maximally Stable Extremal Regions (MSER)Â merupakan algoritma yang kerap dipakai sebagai metode pendeteksi marker pada AR. Tujuan penelitian ini yaitu untuk menganalisis kinerja algoritma FAST dan algoritma MSER terhadap kemampuan dan kecepatannya untuk mendeteksi dan mengekstraksi fitur-fitur pada citra serta ketahanannya terhadap gangguan pada citra yang digunakan untuk marker pada AR, dan menunjukkan algoritma yang lebih baik untuk aplikasi AR antara algoritma FAST dan algoritma MSER. Penelitian ini menggunakan dua set citra; 2D Template Marker dan Image Marker dengan 10 gambar untuk masing-masing set dan modifikasi pada citra seperti; perubahan intensitas cahaya, rotasi, dan blur dengan parameter : (1) jumlah fitur yang terdeteksi, (2) waktu deteksi dan ekstraksi fitur, (3) persentase banyaknya fitur yang berhasil dicocokkan, dan (4) waktu pencocokan fitur. Berdasarkan keempat parameter, algoritma FAST memiliki pemrosesan yang lebih cepat terhadap deteksi marker, sedangkan algoritma MSER memiliki proses pendeteksian marker yang lebih stabil terhadap perubahan yang terjadi baik pada kamera atau marker.
References
Bhushan Verma, S., & Chandran, S. (2016). Comparative Study of FAST, MSER, and Harris for Palmprint Verification System. International Journal of Scientific & Engineering Research, 7(12), 855–858. Diambil dari http://www.ijser.org
Matas, J., Chum, O., Urban, M., & Pajdla, T. (2004). Robust wide-baseline stereo from maximally stable extremal regions. 22, 761–767. https://doi.org/10.1016/j.imavis.2004.02.006
Purba, A. M., Harjoko, A., & Wibowo, M. E. (2019). Text Detection In Indonesian Identity Card Based On Maximally Stable Extremal Regions. IJCCS (Indonesian Journal of Computing and Cybernetics Systems), 13(2), 177–188. https://doi.org/10.22146/ijccs.41259
Rosten, E., & Drummond, T. (2006). Machine learning for high-speed corner detection. 1–14.
Thanaborvornwiwat, N., & Patanukhom, K. (2018). Marker Registration Technique for Handwritten Text Marker in Augmented Reality Applications. Journal of Physics: Conference Series, 1004(1), 1–7. https://doi.org/10.1088/1742-6596/1004/1/012005
Wahyudi, N., Harianto, R. A., & Setyati, E. (2019). Augmented Reality Marker Based Tracking Visualisasi Drawing 2D ke dalam Bentuk 3D dengan Metode FAST Corner Detection. JOURNAL OF INTELLIGENT SYSTEMS AND COMPUTATION, 1(1), 9–18.
Zafar, Z., Berns, K., & Rodić, A. (2017). Recognizing hand gestures using local features: A comparison study. Advances in Intelligent Systems and Computing, 540, 394–401. https://doi.org/10.1007/978-3-319-49058-8_43
Downloads
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Dwi Anugrahita, Rini Mayasari, Susilawati Susilawati
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access)
JRST (Jurnal Riset Sains dan Teknologi) is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
