Deep Convolutional AutoEncoder-based Lossy Image Compression

被引:0
|
作者
Cheng, Zhengxue [1 ]
Sun, Heming
Takeuchi, Masaru [1 ]
Katto, Jiro [1 ]
机构
[1] Waseda Univ, Grad Sch Fundamental Sci & Engn, Tokyo, Japan
关键词
Convolutional autoencoder; Image compression; Deep learning; Principal component analysis;
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Image compression has been investigated as a fundamental research topic for many decades. Recently, deep learning has achieved great success in many computer vision tasks, and is gradually being used in image compression. In this paper, we present a lossy image compression architecture, which utilizes the advantages of convolutional autoencoder (CAE) to achieve a high coding efficiency. First, we design a novel CAE architecture to replace the conventional transforms and train this CAE using a rate-distortion loss function. Second, to generate a more energy-compact representation, we utilize the principal components analysis (PCA) to rotate the feature maps produced by the CAE, and then apply the quantization and entropy coder to generate the codes. Experimental results demonstrate that our method outperforms traditional image coding algorithms, by achieving a 13.7% BD-rate decrement on the Kodak database images compared to JPEG2000. Besides, our method maintains a moderate complexity similar to JPEG2000.
引用
收藏
页码:253 / 257
页数:5
相关论文
共 50 条
  • [1] A Generic Real Time Autoencoder-Based Lossy Image Compression
    Tawfik, Abdelrahman
    Hosny, Shehab
    Hisham, Sara
    Farouk, Ali Amr
    Mustafa, Doha
    Moaty, Samaa Abdel
    Gamal, Ahmed
    Salah, Khaled
    2022 5TH INTERNATIONAL CONFERENCE ON COMMUNICATIONS, SIGNAL PROCESSING, AND THEIR APPLICATIONS (ICCSPA), 2022,
  • [2] Convolutional Autoencoder-Based Multispectral Image Fusion
    Azarang, Arian
    Manoochehri, Hafez E.
    Kehtarnavaz, Nasser
    IEEE ACCESS, 2019, 7 : 35673 - 35683
  • [3] Memristor-based storage system with convolutional autoencoder-based image compression network
    Yulin Feng
    Yizhou Zhang
    Zheng Zhou
    Peng Huang
    Lifeng Liu
    Xiaoyan Liu
    Jinfeng Kang
    Nature Communications, 15
  • [4] Memristor-based storage system with convolutional autoencoder-based image compression network
    Feng, Yulin
    Zhang, Yizhou
    Zhou, Zheng
    Huang, Peng
    Liu, Lifeng
    Liu, Xiaoyan
    Kang, Jinfeng
    NATURE COMMUNICATIONS, 2024, 15 (01)
  • [5] Autoencoder-based joint image compression and encryption
    Wang, Benxuan
    Lo, Kwok-Tung
    JOURNAL OF INFORMATION SECURITY AND APPLICATIONS, 2024, 80
  • [6] Dual Autoencoder-based Framework for Image Compression and Decompression
    Patel, Bhargav
    FIFTEENTH INTERNATIONAL CONFERENCE ON MACHINE VISION, ICMV 2022, 2023, 12701
  • [7] Autoencoder-based image compression for wireless sensor networks
    Lungisani, Bose Alex
    Zungeru, Adamu Murtala
    Lebekwe, Caspar
    Yahya, Abid
    SCIENTIFIC AFRICAN, 2024, 24
  • [8] An Aquatic Image Compression Scheme based on Optimized Deep Convolutional Autoencoder
    Paul, Raj Kumar
    Vishwakarmaw, Ankit
    Chandran, Saravanan
    IAENG International Journal of Computer Science, 2024, 51 (02) : 83 - 90
  • [9] Deep Convolutional Asymmetric Autoencoder-Based Spatial-Spectral Clustering Network for Hyperspectral Image
    Liu, Baisen
    Kong, Weili
    Wang, Yan
    WIRELESS COMMUNICATIONS & MOBILE COMPUTING, 2022, 2022
  • [10] EFFICIENT DEEP LEARNING-BASED LOSSY IMAGE COMPRESSION VIA ASYMMETRIC AUTOENCODER AND PRUNING
    Kim, Jun-Hyuk
    Choi, Jun-Ho
    Chang, Jaehyuk
    Lee, Jong-Seok
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 2063 - 2067