Image Zooming Using a Multi-layer Neural Network

Abstract

This paper presents a novel image zooming method using a neural network. The main issue in any image zooming algorithms is to preserve the main structure of the image. The proposed method uses a multi-layer perceptron for image zooming. For zooming an image, the neural network is initially trained using the same image down-sampled by a factor of 2. In training the network, individual pixels along with their neighborhoods from the down-sampled image and the corresponding pixels in a 2 × 2 block from the original image are used as the input and output data, respectively. The trained neural network is then used to enlarge the original image by a factor of 2. The obtained image can be re-applied to the neural network for further enlarging. The blurring and staircase effects are faint in the zoomed image, and the edges are preserved. Besides, the proposed method is simple and easy to implement. The evaluation results on different images show that the proposed method is more efficient than other recently developed image zooming methods, particularly for high magnification factors.