论文信息 - UAV Motion-Blurred Image Restoration Using Improved Continuous Hopfield Network Image Restoration Algorithm

UAV Motion-Blurred Image Restoration Using Improved Continuous Hopfield Network Image Restoration Algorithm

The performance of blind detection algorithm based on Hopfield neural network depends on the choice of activation function. According to this principle, we change the activation function of continuous Hopfield image restoration algorithm to improve the performance. Compared with the previous algorithm, the improved algorithm greatly speeds up the convergence rate without reducing the quality of the repaired image. The new algorithm can resolve unmanned aerial vehicle (UAV) motion-blurred image restoration, combining with the estimated point spread function (PSF). The experimental results show the superiority of the new algorithm.

Zhimin Zhang | Yun Zhang | Shujuan Yu | Shaowei Chen

[1] Sun Shi-xin. Fast Image Restoration Algorithm Using Neural Network Based on Harmonic Model , 2007 .

[2] B. K. Jenkins,et al. Image restoration using a neural network , 1988, IEEE Trans. Acoust. Speech Signal Process..

[3] Aggelos K. Katsaggelos,et al. Image restoration using a modified Hopfield network , 1992, IEEE Trans. Image Process..

[4] Wu Cheng-lei. Improvement of Continuous Hopfield Neural Network Based Algorithms for Image Restoration , 2006 .

[5] Zekeriya Uykan,et al. Fast-Convergent Double-Sigmoid Hopfield Neural Network as Applied to Optimization Problems , 2013, IEEE Transactions on Neural Networks and Learning Systems.