Abstract
Lossy image compression can reduce the bandwidth required for image transmission in a network and the storage space of a device, which is of great value in improving network efficiency. With the rapid development of deep learning theory, neural networks have achieved great success in image processing. In this paper, inspired by the diverse extent of attention in human eyes to each region of the image, we propose an image compression framework based on semantic analysis, which creatively combines the application of deep learning in the field of image classification and image compression. We first use a convolutional neural network (CNN) to semantically analyze the image, obtain the semantic importance map, and propose a compression bit allocation algorithm to allow the recurrent neural network (RNN)-based compression network to hierarchically compress the image according to the semantic importance map. Experimental results validate that the proposed compression framework has better visual quality compared with other methods at the same compression ratio.
Highlights
The rapid development of the Internet of Things (IoT) has greatly facilitated people’s lives, and it has led to an explosive increase in the amount of data transmitted by networks
Common lossy compression algorithms can be divided into traditional methods based on mathematical statistics and neural network methods based on deep learning
We combine the application of deep learning in the field of image semantic analysis methods are superior to the other two methods
Summary
The rapid development of the Internet of Things (IoT) has greatly facilitated people’s lives, and it has led to an explosive increase in the amount of data transmitted by networks. An end-to-end deep learning image compression framework based neural on semantic analysis is proposed, containing a semantic analysis network based on a convolutional network (CNN). A superresolution convolutional neural network (SRCNN) network for image compression was proposed in [13] by Chao Dong et al, first applying deep learning methods in solving pixel-level image problems. It uses a three-layer convolution structure to sample a low-resolution image by doubling the cubic difference and reconstructs the image in the pixel domain through the network. In terms of image compression, the authors introduced image compression methods based on the random neural network, convolutional neural network, recurrent neural network, and generative adversarial network methods from the perspective of principle and performance
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
