Research On JPEG Compression Artifacts Reduction Algorithm Based On Deep Learning

In the case of high compression rates,the JPEG decompressed image can produce blocking artifacts,ringing effects and blurring,which affect seriously the visual effect of the image.In order to effectively remove JPEG compression artifacts,this paper studies the JPEG compression artifacts reduction algorithm based on deep learning.The specific research contents are as follows:Firstly,the prior of JPEG compression is combined with a convolutional neural network,which adds quantization constraint after a simple convolutional neural network to ensure a more reliable estimate of the image output by the convolutional neural network.The output image of the network is quantization constrained when it converges,and the image obtained by the quantization constraint is once again used as a training sample of the convolutional neural network.Experiments demonstrate that the proposed algorithm has higher performance than the single training convolutional neural network.Secondly,in order to further remove JPEG compression artifacts,a multi-scale dense residual network is proposed.Firstly,the proposed network introduces the dilate convolution into a dense block and uses different dilation factors to form multi-scale dense blocks.Then,the proposed network uses four multi-scale dense blocks to design the network into a structure with two branches,and the latter branch is used to supplement the features that are not extracted by the previous branch.Finally,the proposed network uses residual learning to improve network performance.In order to improve the versatility of the network,the network is trained by a joint training method with different compression quality factors,and a general model is trained for different compression quality factors.Experiments demonstrate that the proposed algorithm not only has high JPEG compression artifacts reduction performance,but also has strong generalization ability.Finally,in order to further speed up the network,the JPEG compressed image is wavelet transformed,and the four images with high and low frequency information are used as the input of the network.A wavelet multi-scale dense residual network is proposed.The proposed network introduces the dilate convolution into a dense residual block and uses different dilation factors to form multi-scale dense residual blocks,and designs the network through multi-scale dense residual blocks.Experiments demonstrate that the proposed algorithm is comparable in performance to the multi-scale dense residual network,but the running speed is further accelerated.