Neural concurrent subsampling and interpolation for images
Jong-Ok Kim, Byung-Tae Choi, Aldo W. Morales, Sung-Jea Ko · 2003
This paper presents a new method for image subsampling and interpolation based on the feedforward neural network (FNN). The proposed technique employs a single FNN with three hidden layers for both subsampling and interpolation, providing the advantages of high speed, parallel processing capability, and good image reproduction quality. Experimental results show that the proposed technique exhibits an increased performance over conventional ones.