Memory-Efficient High-Speed Convolution-based Generic Structure for Multilevel 2-D DWT

被引:49
作者
Mohanty, Basant Kumar [1 ]
Meher, Pramod Kumar [2 ]
机构
[1] Jaypee Univ Engn & Technol, Dept Elect & Commun Engn, Guna 473226, Madhya Pradesh, India
[2] Inst Infocomm Res, Singapore 138632, Singapore
关键词
2-D discrete wavelet transform (DWT); DWT; lifting; systolic array; very large scale integration (VLSI); DISCRETE WAVELET TRANSFORM; VLSI ARCHITECTURE; LIFTING SCHEME; IMPLEMENTATION; ALGORITHM; DESIGN;
D O I
10.1109/TCSVT.2012.2203745
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
In this paper, we have proposed a design strategy for the derivation of memory-efficient architecture for multilevel 2-D DWT. Using the proposed design scheme, we have derived a convolution-based generic architecture for the computation of three-level 2-D DWT based on Daubechies (Daub) as well as biorthogonal filters. The proposed structure does not involve frame-buffer. It involves line-buffers of size 3(K - 2) M/4 which is independent of throughput-rate, where K is the order of Daubechies/biorthogonal wavelet filter and M is the image height. This is a major advantage when the structure is implemented for higher throughput. The structure has regular data-flow, small cycle period T-M and 100% hardware utilization efficiency. As per theoretical estimate, for image size 512 x 512, the proposed structure for Daub-4 filter requires 152 more multipliers and 114 more adders, but involves 82 412 less memory words and takes 10.5 times less time to compute three-level 2-D DWT than the best of the existing convolution-based folded structures. Similarly, compared with the best of the existing lifting-based folded structures, proposed structure for 9/7-filter involves 93 more multipliers and 166 more adders, but uses 85 317 less memory words and requires 2.625 times less computation time for the same image size. It involves 90 (nearly 47.6%) more multipliers and 118 (nearly 40.1%) more adders, but requires 2723 less memory words than the recently proposed parallel structure and performs the computation in nearly half the time of the other. In-spite of having more arithmetic components than the lifting-based structures, the proposed structure offers significant saving of area and power over the other due to substantial reduction in memory size and smaller clock-period. ASIC synthesis result shows that, the proposed structure for Daub-4 involves 1.7 times less area-delay-product (ADP) and consumes 1.21 times less energy per image (EPI) than the corresponding best available convolution-based structure. It involves 2.6 times less ADP and consumes 1.48 times less EPI than the parallel lifting-based structure.(1)
引用
收藏
页码:258 / 268
页数:11
相关论文
共 43 条
  • [31] High Speed and Memory Efficient VLSI Architecture of 2D 5/3 DWT Using Interlaced Scan Algorithm for JPEG2000
    Liu, Wen-song
    Gu, Jing
    Zhai, Hai-tao
    Zhang, Fan
    PROCEEDINGS OF 2012 2ND INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND NETWORK TECHNOLOGY (ICCSNT 2012), 2012, : 180 - 184
  • [32] Memory Efficient High Speed Systolic Array Architecture Design with Multiplexed Distributed Arithmetic for 2D DTCWT Computation on FPGA
    Poornima, B.
    Sumathi, A.
    Raj, Cyril Prasanna P.
    INFORMACIJE MIDEM-JOURNAL OF MICROELECTRONICS ELECTRONIC COMPONENTS AND MATERIALS, 2019, 49 (03): : 119 - 132
  • [33] Extended 2-D Magnetic Field Modeling of Linear Motor to Investigate the Magnetic Force Parameters of High-Speed Superconducting Maglev
    Ozturk, Ufuk Kemal
    Abdioglu, Murat
    Ozkat, Erkan Caner
    Mollahasanoglu, Hakki
    IEEE TRANSACTIONS ON APPLIED SUPERCONDUCTIVITY, 2023, 33 (04)
  • [34] A high-speed long-haul wavelength division multiplexing-based inter-satellite optical wireless communication link using spectral-efficient 2-D orthogonal modulation scheme
    Singh, Mehtab
    Malhotra, Jyoteesh
    INTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS, 2020, 33 (06)
  • [35] High-speed all-optical 2-bit multiplier based on photonic crystal structure
    Liaghati-Rad, M.
    Soroosh, M.
    Kosarian, A.
    PHOTONIC NETWORK COMMUNICATIONS, 2022, 43 (03) : 193 - 203
  • [36] A memory and area-efficient distributed arithmetic based modular VLSI architecture of 1D/2D reconfigurable 9/7 and 5/3 DWT filters for real-time image decomposition
    Chakraborty, Anirban
    Banerjee, Ayan
    JOURNAL OF REAL-TIME IMAGE PROCESSING, 2020, 17 (05) : 1421 - 1446
  • [37] High-Speed, Low-Power, and Area-Efficient 5T4M Memristor-Based Ternary Content Addressable Memory
    Maruf, Md Hasan
    Ali, Syed Iftekhar
    IETE TECHNICAL REVIEW, 2024, 41 (05) : 592 - 601
  • [38] 2-D Joint High-Resolution ISAR Imaging With Random Missing Observations via Cyclic Displacement Decomposition-Based Efficient SBL
    Wang, Yuanyuan
    Dai, Fengzhou
    Liu, Qian
    Lu, Xiaofei
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62
  • [39] An investigation on inner ear operation in sense of hearing: High-speed FPGA-based circuits for digital realization of 2D cochlea modeling
    Chen, Ru
    Xiang, Songjie
    Yu, Die
    Li, Meixuan
    Daoud, Mohammad Sh.
    Chu, Yanling
    Huang, Yideng
    Shao, Minmin
    Mayet, Abdulilah Mohammad
    Ge, Yisu
    Zhang, Guodao
    ALEXANDRIA ENGINEERING JOURNAL, 2025, 118 : 371 - 383
  • [40] A memory and area-efficient distributed arithmetic based modular VLSI architecture of 1D/2D reconfigurable 9/7 and 5/3 DWT filters for real-time image decomposition
    Anirban Chakraborty
    Ayan Banerjee
    Journal of Real-Time Image Processing, 2020, 17 : 1421 - 1446