High-speed Memristive Walsh-Hadamard Transform for Image Compression
Image compression has a wide range of applications at the edge and has high requirements for real-time performance. Here, we propose a high-speed memristive Walsh-Hadamard Transform (WHT) system based on the pipeline method for image compression, which performs multiple matrix multiplication operations at the same time. The proposed memristive WHT system improves $4 \times$ time efficiency compared to the system without the pipeline method. Our work suggests a promising hardware solution for image compression in future edge computing.
Authors
- Huai-Zhi Pei
- Sheng‐Guang Ren (ORCID: https://orcid.org/0000-0001-6966-1542)
- Han Bao (ORCID: https://orcid.org/0000-0002-2329-6890)
- Ling Yang (ORCID: https://orcid.org/0000-0002-5727-688X)
- Yi Li (ORCID: https://orcid.org/0000-0003-1930-8550)
- Xiangshui Miao (ORCID: https://orcid.org/0000-0002-3999-7421)
- Jing Tian (ORCID: https://orcid.org/0000-0001-8232-8816)
Institutions
- Huazhong University of Science and Technology (CN)
Publication Details
- Published
- 2024-10-25
- DOI
- https://doi.org/10.1109/icta64028.2024.10860475
- Primary Topic
- Advanced Data Compression Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00