PENGEMBANGAN ALGORITMA DENOISING DENGAN KONSEP DEEP BACK-PROJECTION
DOI:
https://doi.org/10.25124/jett.v9i1.4984Abstract
Penelitian ini mengangkat salah satu permasalahan umum pada citra digital, terutama pada smartphone, yaitu noise yang disebabkan oleh kecilnya aperture dan ukuran sensor pada kamera digital. Untuk menyelesaikan permasalahan tersebut, peneliti mengembangkan metode denoising untuk mentransformasi citra kotor menjadi citra bersih. Terinspirasi dari konsep deep back-projection, penelitian ini melakukan modifikasi terhadap implementasi asli deep back-projection, menggunakan down-projection layer sebagai tahapan untuk menghilangkan noise dengan intuisi menggunakan bahwa proses down-sampling mampu menghilangkan noise pada input citra. Lalu citra kembali diperbesar sesuai ukuran aslinya. Pada eksperimen yang dilakukan, penelitian ini membuktikan bahwa teknik yang diajukan mampu memperoleh hasil terbaik dibandingkan metode lainnya pada dataset SIDD. Hasil eksperimen memperlihatkan peningkatan kualitas sebesar 6 dB dibandingan model lainnya.
Downloads
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright Notice
An author who publishes in the Jurnal Elektro dan Telekomunikasi Terapan agrees to the following terms:
- Author retains the copyright and grants the journal the right of first publication of the work simultaneously licensed under the Creative Commons Attribution-NonCommercial 4.0 International License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal
- Author is 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 the acknowledgement of its initial publication in this journal.
- Author is permitted and encouraged to post his/her 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 the published work (See The Effect of Open Access).
Read more about the Creative Commons Attribution-NonCommercial 4.0 International License. here: http://creativecommons.org/licenses/by-nc/4.0/.
Privacy Statement
The names and email addresses entered in this journal site will be used exclusively for the stated purposes of this journal and will not be made available for any other purpose or to any other party.
