Penerapan Transformasi Wavelet Daubechies Untuk Reduksi noise Hujan Pada Video

Khotijah, Siti (2018) Penerapan Transformasi Wavelet Daubechies Untuk Reduksi noise Hujan Pada Video. Masters thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 06111450012004-Master_Thesis.pdf]
Preview
Text
06111450012004-Master_Thesis.pdf - Accepted Version

Download (4MB) | Preview

Abstract

Saat ini penggunaan video digital di bidang ilmu komputer semakin luas, seperti proses tracking object, penghitungan jumlah kendaraan, klasifikasi jenis kendaraan, estimasi kecepatan kendaraan dan sebagainya. Proses pengambilan video digital tersebut seringkali dipengaruhi oleh cuaca buruk, seperti pengambilan pada saat hujan. Hujan dalam video digital dianggap noise karena mampu menghalangi objek yang sedang di amati. Oleh karena itu, dibutuhkan suatu proses reduksi noise hujan yang terdapat pada video tersebut.
Pada penelitian ini reduksi noise hujan pada video digital dilakukan dengan menerapkan Transformasi wavelet Daubechies yang melewati beberapa proses yaitu: Dekomposisi wavelet, proses fusi, proses thresholding dan proses rekonstruksi. Nilai threshold yang digunakan dalam proses thresholding yaitu VishuShrink, BayesShrink, dan NormalShrink dan diuji coba menggunakan data hujan deras, sedang dan rendah. Hasil Implementasi dan uji coba diperoleh bahwa reduksi noise untuk data hujan deras, perbandingan nilai PSNR tertinggi yaitu 27,3138 dB dengan waktu komputasi 29,4475 detik menggunakan wavelet Daubechies db2 level 3 VishuShrink. Untuk data hujan sedang, perbandingan nilai PSNR tertinggi yaitu 34,6985 dB dengan waktu komputasi 38,3172 detik menggunakan wavelet Daubechies db4 level 3 VishuShrink. Sedangkan untuk data hujan rendah, perbandingan nilai PSNR tertinggi yaitu 38,7916 dB dengan waktu komputasi 34,5306 detik. =============== Currently the use of digital video in the field of computer science increasingly widespread, such as the process of tracking objects, the calculation of the number of vehicles, classification of vehicle types, vehicle speed estimates and so forth. The process of taking digital video is often influenced by bad weather, such as taking in the rain. Rain in digital video is considered noise because it is able to block objects being observed. Therefore, a rainfall noise reduction process is required in the video.
In this study, the reduction of rain noise in digital video is done by applying Daubechies wavelet transformation through several processes, namely: wavelet decomposition, fusion process, thresholding process and reconstruction process. The threshold values used in the thresholding process are VishuShrink, BayesShrink, and NormalShrink and are tested using heavy, medium and low rainfall data. The results of the implementation and test show that noise reduction for rainfall data, the highest PSNR value is 27.3138 dB with computation time of 29.4475 seconds using Daubechies db2 level 3 VishuShrink wavelet. For moderate rainfall data, the highest PSNR score was 34.6985 dB with computation time 38.3172 sec using Daubechies db4 level 3 VishuShrink wavelet. As for the low rainfall data, the highest PSNR value is 38.7916 dB with computation time of 34.5306 seconds

Item Type: Thesis (Masters)
Additional Information: RTMa 515.243 3 Kho p
Uncontrolled Keywords: Transformasi wavelet daubechies; fusi; VishuShrink; BayesShrink NormalShrink; Daubechies Wavelet Transformation; fusion; VishuShrink; BayesShrink; NormalShrink
Subjects: Q Science
Q Science > QA Mathematics > QA403.3 Wavelets (Mathematics)
Q Science > QA Mathematics > QA75 Electronic computers. Computer science. EDP
T Technology > TD Environmental technology. Sanitary engineering > TD892 Noise control
Divisions: Faculty of Mathematics and Science > Mathematics
Depositing User: Khotijah Siti
Date Deposited: 01 Mar 2018 05:04
Last Modified: 20 Jul 2020 03:59
URI: http://repository.its.ac.id/id/eprint/51043

Actions (login required)

View Item View Item