An End-to-End Deep Learning Image Compression Framework Based on Semantic Analysis

• Main Authors: Cheng Wang, Yifei Han, Weidong Wang
• Format: Article
• Language: English
• Published: MDPI AG 2019-09-01
• Series: Applied Sciences
• Subjects: lossy image compression; deep learning; semantic analysis; visual quality
• Online Access: https://www.mdpi.com/2076-3417/9/17/3580

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.