eprintid: 4197
rev_number: 9
eprint_status: archive
userid: 311
dir: disk0/00/00/41/97
datestamp: 2020-12-08 15:31:12
lastmod: 2020-12-08 15:31:12
status_changed: 2020-12-08 15:31:12
type: article
metadata_visibility: show
creators_name: Tung, Pham Thanh
creators_name: Xiem, Van Hoang
creators_name: Nghia, Nguyen Trung
creators_name: Duong, Dinh Trieu
creators_name: Ha, Le Thanh
creators_id: tung@vinafire.com.vn
creators_id: xiemhoang@vnu.edu.vn
title: End-to-end Image Patch Quality Assessment for Image/Video with Compression Artifacts
ispublished: pub
subjects: ECE
subjects: ElectronicsandComputerEngineering
subjects: isi
divisions: fac_fet
abstract: In this paper, we present an experimental image quality assessment (IQA) method for image/ video patches with compression artifacts. Using the High Efficiency Video Coding (HEVC) standard, we create a new database of image patches with compression artifacts. Then, we conduct a completed subjective testing process to obtain the ‘ground truth’ quality scores for the mentioned database. Finally, we employ an end-to-end learning method to estimate the IQA model for the patches with HEVC compression artifacts. In such proposed method, a modified convolutional neural network (CNN) architecture is exploited for feature extraction while an adaptive moment estimation optimizer solution is used to perform the training process. Experimental results show that the proposed end-to-end IQA method significantly outperforms the relevant IQA benchmarks, especially when the compression artifacts are strongly realized.
date: 2020-11
date_type: published
publisher: IEEE
full_text_status: public
publication: IEEE Access
refereed: TRUE
issn: 2169-3536
citation:   Tung, Pham Thanh and Xiem, Van Hoang and Nghia, Nguyen Trung and Duong, Dinh Trieu and Ha, Le Thanh  (2020) End-to-end Image Patch Quality Assessment for Image/Video with Compression Artifacts.  IEEE Access .    ISSN 2169-3536     
document_url: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/4197/1/IEEE%20ACCESS_TUNG_XIEM_paper.pdf