Multiple Sequential Regularized Extreme Learning Machines for Single Image Super Resolution

Abstract

In this letter, we propose an example-based super-resolution algorithm based on multiple neural networks trained sequentially using the method online sequential regularized extreme learning machine. In order to train multiple networks, we divide the training samples into clusters using local gradient information, and a distinct network is trained for each cluster. We add another layer of learning by training linear kernels to reshape the network output patches into full images. Also, we employ a fast reconstruction scheme before and after the learning stage. Experiments show that the proposed method generates comparable or better results when compared to important works of the literature, without the need for specialized hardware, large training datasets, and extensive training time.