@inproceedings{31d9943b1ddc41138b004eec675c6ba8,
title = "Direct Application of Convolutional Neural Network Features to Image Quality Assessment",
abstract = "We take advantage of the popularity of deep con-volutional neural networks (CNNs) and have developed a very simple image quality assessment method that rivals state of the art. We show that convolutional layer outputs (deep features) of a CNN compute the local structural information of spatial regions of different sizes in the input image. The learned convolutional kernels contain a much richer set of weights thus capturing much more local structural information than hand crafted ones. As the deep features learned from large datasets already contain very rich multi-resolutional structural image information, they can be directly used to calculate visual distortion of an image and it is not necessary to introduce further complicated computational process. We will present experimental results to demonstrate that this is indeed the case, and that simple cosine distance of the deep features is as good as state the art methods for full reference image quality assessment.",
keywords = "CNN, Deep features, Image quality assessment",
author = "Xianxu Hou and Ke Sun and Bozhi Liu and Yuanhao Gong and Jonathan Garibaldi and Guoping Qiu",
note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 33rd IEEE International Conference on Visual Communications and Image Processing, VCIP 2018 ; Conference date: 09-12-2018 Through 12-12-2018",
year = "2018",
month = jul,
day = "2",
doi = "10.1109/VCIP.2018.8698726",
language = "English",
series = "VCIP 2018 - IEEE International Conference on Visual Communications and Image Processing",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "VCIP 2018 - IEEE International Conference on Visual Communications and Image Processing",
}