Jurnal SINTA 2
Sistem Temu Kembali Citra Berbasis Konten Menggunakan Haar Wavelet Transform Dan K-Means Clustering
Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK) · Vol. 3 No. 1 (2016) · pp. 27–34
- ISSN
- 2528-6579, 2355-7699
- Published
- 2016-03-17
- Publisher
- Fakultas Ilmu Komputer, Universitas Brawijaya
- Language
- en
Abstract
AbstrakKombinasi haar wavelet transform, F-Norm, dan progressive retrieval strategy dapat digunakan sebagai metode temu kembali citra berbasis konten yang menghasilkan hasil pencarian yang efektif. Haar wavelet digunakan untuk mendekomposisi citra warna. F-Norm digunakan untuk melakukan ekstraksi fitur. Progressive retrieval strategy digunakan untuk mendapatkan akurasi hasil pencarian yang lebih baik. Pencocokan citra menggunakan progressive retrieval strategy dilakukan terhadap setiap citra yang ada dalam database sehingga menyebabkan waktu pencarian yang lama jika jumlah citra yang ada di database sangat banyak. Dalam penelitian ini diusulkan kombinasi antara haar wavelet transform, F-Norm, progressive retrieval strategy, dan K-Means clustering untuk mempercepat waktu dan nilai precision pencarian. Dari hasil uji coba diperoleh peningkatan nilai precision sebesar 40% serta kecepatan 1,6 – 2,7 kali lebih cepat daripada tanpa menggunakan metode K-Means clustering.Kata kunci: Temu Kembali Informasi, CBIR, Haar Wavelet, Fnorm, K-Means, Progressive Retrieval StrategyAbstractThe combination haar wavelet transform, F-Norm, and progressive retrieval strategy can be used in content-based image retrieval that produces effective results. Haar wavelet is used to decompose the color image. F-Norm is used to perform feature extraction. Progressive retrieval strategy is used to gain better precision value. Image matching using progressive retrieval strategy is carried out on each image in the database, this causing a long search time if there are lots of images in the database. In this study, we proposed a method based on wavelet transform, F-Norm, progressive retrieval strategy, and K-Means clustering to speed up the search time and increase precision value. From the experiment we obtained precision value increased by 40% and retrieval speed 1.6 to 2.7 times faster than without using the K-Means clustering.Keywords: Information Retrieval, CBIR, Haar Wavelet, Fnorm, K-Means, Progressive Retrieval Strategy
Collaboration network of the authors
14 authors · 27 co-authorship links
Hover or tap a name to highlight its co-authors. Double-click to open the author's page.
- University of Brawijaya
- Different organisations
- Same organisation
- Affiliation unknown
- Thicker line = more joint articles · bigger circle = more articles
Show as table
| Co-author | Organisation | Joint articles |
|---|---|---|
| Heru Nurwarsito | University of Brawijaya | 1 |
| Barlian Henryranu Prasetio | University of Brawijaya | 1 |
| Imam Cholissodin | University of Brawijaya | 1 |
| Bayu Rahayudi | University of Brawijaya | 1 |
| Willyan Eka Ksatria | University of Brawijaya | 1 |
| Annisa Sukmawati | University of Brawijaya | 1 |
| Muhammad Farid Muzayyani | University of Brawijaya | 1 |
| Tri Afirianto | University of Brawijaya | 1 |
| Abdiel Wahyu Ramadhyono | University of Brawijaya | 1 |
| Muhammad Aminul Akbar | University of Brawijaya | 1 |
| Erico Silitonga | University of Brawijaya | 1 |
| Achmad Arwan | University of Brawijaya | 1 |
Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.