BigSnarf blog

Infosec FTW

Blur affects on Neural Network preception

Screen Shot 2017-11-22 at 10.45.29 AM

Image quality is an important practical challenge that is often overlooked in the design of machine vision systems.

Commonly, machine vision systems are trained and tested on high quality image datasets, yet in practical applications the input images can not be assumed to be of high quality. Recently, deep neural networks have obtained state-of-the-art performance on many machine vision tasks.

In this paper we provide an evaluation of 4 state-of-the-art deep neural network models for image classification under quality distortions. We consider five types of quality distortions: blur, noise, contrast, JPEG, and JPEG2000 compression.

We show that the existing networks are susceptible to these quality distortions, particularly to blur and noise. These results enable future work in developing deep neural networks that are more invariant to quality distortions.

https://arxiv.org/pdf/1604.04004.pdf

https://arxiv.org/pdf/1612.01227.pdf

deblurGAN https://arxiv.org/pdf/1711.07064.pdf

code https://github.com/KupynOrest/DeblurGAN

cGAN https://arxiv.org/abs/1411.1784

pix2pix https://phillipi.github.io/pix2pix/

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: