期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 26, 期 12, 页码 6034-6045出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2017.2749148
关键词
Chroma reconstruction; chroma subsampling; color gradient-based structure similarity index (CGSS); color peak signal-to-noise ratio (CPSNR); high efficiency video coding (HEVC); screen content images (SCIs); winner-first voting strategy
资金
- Ministry of Science and Technology of China [MOST-104-2221-E-011-004-MY3, MOST-105-2221-E-011-118-MY3]
In this paper, we propose a novel adaptive chroma subsampling-binding and luma-guided (ASBLG) chroma reconstruction method for screen content images (SCIs). After receiving the decoded luma and subsampled chroma image from the decoder, a fast winner-first voting strategy is proposed to identify the used chroma subsampling scheme prior to compression. Then, the decoded luma image is subsampled as the identified subsampling scheme was performed on the chroma image such that we are able to conclude an accurate correlation between the subsampled decoded luma image and the decoded subsampled chroma image. Accordingly, an adaptive sliding window-based and luma-guided chroma reconstruction method is proposed. The related computational complexity analysis is also provided. We take two quality metrics, the color peak signalto- noise ratio (CPSNR) of the reconstructed chroma images and SCIs and the gradient-based structure similarity index (CGSS) of the reconstructed SCIs to evaluate the quality performance. Let the proposed chroma reconstruction method be denoted as 'ASBLG'. Based on 26 typical test SCIs and 6 JCT-VC test screen content video sequences (SCVs), several experiments show that on average, the CPSNR gains of all the reconstructed UV images by 4: 2: 0(A)-ASBLG, SCIs by 4: 2: 0(MPEG-B)-ASBLG, and SCVs by 4: 2: 0(A)-ASBLG are 2.1, 1.87, and 1.87 dB, respectively, when compared with that of the other combinations. Specifically, in terms of CPSNR and CGSS, CSBILINEAR-ASBLG for the test SCIs and CSBICUBIC-ASBLG for the test SCVs outperform the existing state-of-the-art comparative combinations, where CSBILINEAR and CSBICUBIC denote the luma-aware based chroma subsampling schemes by Wang et al.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据