End-to-End Deep ROI Image Compression

Hiroaki AKUTSU
Takahiro NARUKO

IEICE TRANSACTIONS on Information and Systems   Vol.E103-D    No.5    pp.1031-1038
Publication Date: 2020/05/01
Publicized: 2020/01/24
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2019EDP7264
Type of Manuscript: PAPER
Category: Artificial Intelligence, Data Mining
deep image compression,  ROI,  quality control,  

Full Text: PDF(2.2MB)>>
Buy this Article

In this paper, we present the effectiveness of image compression based on a convolutional auto encoder (CAE) with region of interest (ROI) for quality control. We propose a method that adapts image quality for prioritized parts and non-prioritized parts for CAE-based compression. The proposed method uses annotation information for the distortion weights of the MS-SSIM-based loss function. We show experimental results using a road damage image dataset that is used to check damaged parts and an image dataset with segmentation data (ADE20K). The experimental results reveals that the proposed weighted loss function with CAE-based compression from F. Mentzer et al. learns some characteristics and preferred bit allocations of the prioritized parts by end-to-end training. In the case of using road damage image dataset, our method reduces bpp by 31% compared to the original method while meeting quality requirements that an average weighted MS-SSIM for the road damaged parts be larger than 0.97 and an average weighted MS-SSIM for the other parts be larger than 0.95.

open access publishing via