Improvements of coefficient learning in BPNN for image restoration

In this paper, we propose a method dealing with the problem of image restoration based on the conception of Back propagation Neural Network Algorithm. Conventional Back Propagation Algorithm has its inherited drawbacks, i.e. slow convergence rate, long training time, hard to achieve global minima etc. Recently, several methods introduced the dynamic learning rate and the dynamic momentum coefficient. Our new method applied in this paper improves the effect of learning coefficient η by using a new way to modify the value dynamically. The experimental results show that this helps improving the efficiency overall both in visual effect and quality analysis.