现场可编程门阵列
计算机科学
图像压缩
数据压缩
压缩(物理)
图像(数学)
嵌入式系统
计算机视觉
图像处理
材料科学
复合材料
作者
Bingrui Liu,Min Xie,Zihan Guan,Bolin Yang,Zehuan Yang
标识
DOI:10.1109/ainit61980.2024.10581611
摘要
Image compression is an important research direction in the field of image processing, playing a crucial role in many fields such as mobile communication, cloud storage, and medical imaging. Currently, most hardware implementations of image compression are based on traditional image compression algorithms, such as JPEG. In order to improve the performance of image compression, this design proposes an image compression system based on Variational Auto-Encoder. Meanwhile, by using high-level synthesis tools, the optimized system can achieve image compression more quickly. The experimental results show that this design has certain improvements compared to JPEG2000 in terms of PSNR and MS-SSIM.
科研通智能强力驱动
Strongly Powered by AbleSci AI