Power Constrained Contrast Enhancement by Joint L2,1-norm Regularized Sparse Coding for OLED Display

被引:2
|
作者
Lai, En-Hung [1 ]
Chen, Bo-Hao [1 ,2 ]
Shi, Ling-Feng [1 ,3 ]
机构
[1] Yuan Ze Univ, Dept Comp Sci & Engn, Taoyuan 320, Taiwan
[2] Yuan Ze Univ, Innovat Ctr Big Data & Digital Convergence, Taoyuan 320, Taiwan
[3] Fuzhou Univ, Coll Math & Comp Sci, Fuzhou 350116, Fujian, Peoples R China
关键词
emissive display panel; power-constrained image; battery life; IMAGE; ALGORITHM;
D O I
10.1109/MIPR.2018.00071
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Power-constrained image contrast enhancement is a fundamental step for improving the battery life in many modern consumer devices embedded an emissive-display panel, such as organic light emitting diode. Conventional power-constrained image contrast enhancement approaches in OLED displays are usually performed by histogram-relevant priors or heuristic curve-fitted techniques. Often, this results in either underexposure effects or color tone changes in the enhanced image. Different from the existing approaches, this paper proposes a novel power-constrained sparse representation model by joint l2,1-norm regularized sparse coding in order for gaining in power-saving and perceptible visual-quality on OLED display, simultaneously. Experiments on both quantitative and qualitative evaluations demonstrate that the proposed PCSR approach noticeably outperforms the state-of-the-art power-constrained contrast-enhancement approaches.
引用
收藏
页码:309 / 314
页数:6
相关论文
共 45 条
  • [31] Mass classification of benign and malignant with a new twin support vector machine joint l2,1-norm
    Liu, Xiaoming
    Zhu, Ting
    Zhai, Leilei
    Liu, Jun
    INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2019, 10 (01) : 155 - 171
  • [32] Power-Constrained Image Contrast Enhancement Through Sparse Representation by Joint Mixed-Norm Regularization
    Yin, Jia-Li
    Chen, Bo-Hao
    Lai, En-Hung
    Shi, Ling-Feng
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2020, 30 (08) : 2477 - 2488
  • [33] Power-Constrained Contrast Enhancement Algorithm Using Multiscale Retinex for OLED Display
    Nam, Yeon-Oh
    Choi, Dong-Yoon
    Song, Byung Cheol
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2014, 23 (08) : 3308 - 3320
  • [34] Classifying fabric defects with evolving Inception v3 by improved L2,1-norm regularized extreme learning machine
    Zhou, Zhiyu
    Yang, Xingfan
    Ji, Jiangfei
    Wang, Yaming
    Zhu, Zefei
    TEXTILE RESEARCH JOURNAL, 2023, 93 (3-4) : 936 - 956
  • [35] L2,1-norm Regularization Based Sparse SAR Imaging From Periodic Block Sampling Data: Initial Result
    Bi, Hui
    Zhu, Daiyin
    Bi, Guoan
    2020 21ST INTERNATIONAL RADAR SYMPOSIUM (IRS 2020), 2020, : 57 - 61
  • [36] Learning Robust Distance Metric with Side Information via Ratio Minimization of Orthogonally Constrained l2,1-Norm Distances
    Liu, Kai
    Brand, Lodewijk
    Wang, Hua
    Nie, Feiping
    PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 3008 - 3014
  • [37] Low-resolution face recognition and feature selection based on multidimensional scaling joint L2,1-norm regularisation
    Li, Fei
    Jiang, Mingyan
    IET BIOMETRICS, 2019, 8 (03) : 198 - 205
  • [38] ENSEMBLE PREDICTION OF LONGITUDINAL SCORES OF ALZHEIMER'S DISEASE BASED ON l2,1-NORM REGULARIZED CORRENTROPY WITH SPATIAL-TEMPORAL CONSTRAINT
    Hou, Wen
    Lei, Baiying
    Zou, Wenbin
    Li, Xia
    Zhang, Cishen
    2017 IEEE 14TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2017), 2017, : 891 - 894
  • [39] Robust Feature Selection Method Based on Joint L2,1 Norm Minimization for Sparse Regression
    Yang, Libo
    Zhu, Dawei
    Liu, Xuemei
    Cui, Pei
    ELECTRONICS, 2023, 12 (21)
  • [40] Typical reconstruction performance for distributed compressed sensing based on l2,1-norm regularized least square and Bayesian optimal reconstruction: influences of noise
    Shiraki, Yoshifumi
    Kabashima, Yoshiyuki
    JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT, 2016,