REDUCED-REFERENCE HIGH DYNAMIC RANGE IMAGE QUALITY ASSESSMENT USING FALSE COUNTOUR INFORMATION

Febriani, Rizcy Hafivah (2023) REDUCED-REFERENCE HIGH DYNAMIC RANGE IMAGE QUALITY ASSESSMENT USING FALSE COUNTOUR INFORMATION. Tugas Akhir (S1) - thesis, UNIVERSITAS BAKRIE.

[thumbnail of Cover]
Preview
Text (Cover)
00 Cover.pdf - Submitted Version

Download (579kB) | Preview
[thumbnail of BAB I-III] Text (BAB I-III)
01 BAB I-III.pdf - Submitted Version
Restricted to Registered users only

Download (584kB) | Request a copy
[thumbnail of BAB IV] Text (BAB IV)
02 BAB IV.pdf - Submitted Version
Restricted to Registered users only

Download (3MB) | Request a copy
[thumbnail of BAB V] Text (BAB V)
03 BAB V.pdf - Submitted Version
Restricted to Registered users only

Download (73kB) | Request a copy
[thumbnail of Daftar Pustaka]
Preview
Text (Daftar Pustaka)
04 Daftar Pustaka.pdf - Submitted Version

Download (141kB) | Preview
[thumbnail of Lampiran] Text (Lampiran)
05 Lampiran.pdf - Submitted Version
Restricted to Registered users only

Download (59kB) | Request a copy

Abstract

In recent times, various methods have been developed to produce high quality images that closely resemble real-world scenes as captured by the human eye. One such method is High Dynamic Range (HDR) technology, which has seen the development of many techniques over the past few decades, although each method still has its limitations. This study discusses an objective approach to evaluating the quality of HDR images using reference data. Generally, the image processing approach to HDR can be divided into two algorithms: Multi-exposure Fusion (MEF) and Inverse Tone Mapping Operator (ITMO). MEF involves combining multiple images with different exposure levels to create a more informative output image, while ITMO recovers HDR data from Low Dynamic Range (LDR) or Standard Dynamic Range (SDR) images, although this method may introduce artifacts that can affect the image quality. The focus of this research is to develop a Reduced-Reference (RR) data model for HDR-based image quality. The aim is to identify data overhead that can improve the predictability of the model using spatial data and information, specifically False Contours. Features are extracted from the original image and processed independently, then combined to obtain a single score that corresponds to the predicted subjective score. This approach can be evaluated using a publicly available HDR image quality rating database.

Item Type: Thesis (Tugas Akhir (S1) - )
Uncontrolled Keywords: Image Quality Assessment (IQA) High Dynamic Range (HDR), Reduce-Reference (RR), Multi Exposure Fusion (MEF), Inverse Tone Mapping Operator (ITMO). High Dynamic Range.
Subjects: Computer Science > Image Processing
Thesis > Thesis (S1)
Divisions: Fakultas Teknik dan Ilmu Komputer > Program Studi Informatika
Depositing User: Rizcy Hafivah Febriani
Date Deposited: 01 Mar 2023 05:31
Last Modified: 01 Mar 2023 05:31
URI: https://repository.bakrie.ac.id/id/eprint/7594

Actions (login required)

View Item View Item