Classification of Computer Generated and Natural Images Based on Efficient Deep Convolutional Recurrent Attention Model
Abstract
Most state-of-the-art techniques of distinguishing natural images and computer generated images based on hand-crafted feature and Convolutional Neural Network require processing of the entire input image pixels uniformly. As a result, such techniques usually require extensive computation time and memory, that scale linearly with the size of the input image in terms of number of pixels. In this paper, we deploy an efficient Deep Convolutional Recurrent Attention model with relatively less number of parameters, to distinguish between natural and computer generated images. The proposed model uses a glimpse network to locally process a sequence of selected image regions; hence, the number of parameters and computation time can be controlled effectively. We also adopt a local-to-global strategy by training image patches and classifying full-sized images using the simple majority voting rule. The proposed approach achieves superior classification accuracy compared to recently proposed approaches based on deep learning.
Cite
Text
Tariang et al. "Classification of Computer Generated and Natural Images Based on Efficient Deep Convolutional Recurrent Attention Model." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.Markdown
[Tariang et al. "Classification of Computer Generated and Natural Images Based on Efficient Deep Convolutional Recurrent Attention Model." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/tariang2019cvprw-classification/)BibTeX
@inproceedings{tariang2019cvprw-classification,
title = {{Classification of Computer Generated and Natural Images Based on Efficient Deep Convolutional Recurrent Attention Model}},
author = {Tariang, Diangarti Bhalang and Senguptab, Prithviraj and Roy, Aniket and Chakraborty, Rajat Subhra and Naskar, Ruchira},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2019},
pages = {146-152},
url = {https://mlanthology.org/cvprw/2019/tariang2019cvprw-classification/}
}