Loading [a11y]/accessibility-menu.js
Restoring Aspect Ratio Distortion of Natural Images With Convolutional Neural Network | IEEE Journals & Magazine | IEEE Xplore

Restoring Aspect Ratio Distortion of Natural Images With Convolutional Neural Network


Abstract:

We propose a method to restore aspect ratio distortion of images using convolutional neural network (CNN). The “aspect ratio,” which is focused on this research, means de...Show More

Abstract:

We propose a method to restore aspect ratio distortion of images using convolutional neural network (CNN). The “aspect ratio,” which is focused on this research, means degree of horizontal stretching of images. Indeed an image can be distorted by vertical or horizontal stretching, which does not maintain the aspect ratio. In the proposed method, we construct an aspect ratio estimator whose input is a (possibly distorted) image and output is a scalar value of aspect ratio. Since estimation of aspect ratio from image can be regarded as regression problem, we modeled the estimator by CNN. Once we have a reliable estimate of aspect ratio of an image, the restoration can be done straightforwardly by inverse stretching. In the experiments, we evaluated performance of the model trained on Pascal VOC natural image dataset. Our method can precisely restore the distortion within 1.4% of stretch from original images on average, which outperforms average human performance (i.e., about 13%). In terms of accuracy, 99.86% of distorted images are successfully restored. We also propose training methods to enhance the robustness of the CNN against particular types of disturbance.
Published in: IEEE Transactions on Industrial Informatics ( Volume: 15, Issue: 1, January 2019)
Page(s): 563 - 571
Date of Publication: 06 February 2018

ISSN Information:

Funding Agency:


References

References is not available for this document.