DPCM with a recurrent neural network predictor for image compression

A new predictor for DPCM based on a recurrent neural network is proposed. The proposed predictor which uses the bilinear recurrent neural network (BLRNN), has shown good performance for time-series prediction problems, and it is applied to DPCM for image compression with predictive coding. The performance of DPCM with BLRNN predictor is compared with the conventional DPCM with different predictors, such as the linear predictor and median predictor. The results show that the proposed method gives improved results over the conventional DPCM with linear predictor or median predictor in terms of PSNR or reconstructed images.