当前位置: X-MOL 学术Microprocess. Microsyst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Image Art Design Based on Image Compression Sensing System and Embedded Device
Microprocessors and Microsystems ( IF 1.9 ) Pub Date : 2021-02-15 , DOI: 10.1016/j.micpro.2021.104079
Jingnan Chen

The image Compressed Sensing (CS), two main challenges is to develop the design and reconstruction of the sample matrix. In one aspect, a random sample matrix is generally used and signal characteristics of the signal independent negligible. On the other hand, the most advanced art design image CS method made a very good performance. High computational complexity to meet two challenges recommend using convolution neuroimaging CS architecture. Network includes sampling network (called Convolutional Neural Network (CNN)) Joint Optimization of network reconstruction. Adaptation sampling learning image samples from a training matrix, which can accommodate a plurality of images of the configuration information, better reconstruction CS measurements. Reconstruction network, the network including linear and nonlinear initial reconstructed depth reconstruction networks, learning measuring terminal between CS and the reconstructed image to the end of the map. While achieving high speed of operation, the experimental results show that the most advanced reconstruction quality provided by the state. In addition, the results also show that the trained sample matrix can significantly improve the traditional CS image reconstruction method.



中文翻译:

基于图像压缩传感系统和嵌入式设备的图像艺术设计

图像压缩感测(CS)的两个主要挑战是开发样本矩阵的设计和重构。一方面,通常使用随机样本矩阵,并且与信号无关的信号特性可忽略不计。另一方面,最先进的艺术设计图像CS方法取得了很好的性能。建议使用卷积神经成像CS体系结构来满足两个挑战的高计算复杂性。网络包括采样网络(称为卷积神经网络(CNN))的联合优化网络重构。来自训练矩阵的适应采样学习图像样本可以适应配置信息的多个图像,从而可以更好地重构CS测量。重建网络 该网络包括线性和非线性初始重建深度重建网络,学习CS和重建图像之间的测量终端到地图的末端。实验结果表明,在实现高速运行的同时,国家提供了最先进的重建质量。此外,结果还表明,训练后的样本矩阵可以显着改善传统的CS图像重建方法。

更新日期:2021-02-15
down
wechat
bug