Effects of Image Degradations to CNN-based Image Classification
By Yanting Pei, Yaping Huang, Qi Zou, Hao Zang, Xingyuan Zhang, Song Wang. 2018
23 citations recorded by the source corpus.
Just like many other topics in computer vision, image classification has achieved significant progress recently by using deep-learning neural networks, especially the Convolutional Neural Networks (CNN). Most of the existing works are focused on classifying very clear natural images, evidenced by the widely used image databases such as Caltech-256, PASCAL VOCs and ImageNet. However, in many real applications, the acquired images may contain certain degradations that lead to various kinds of blurring, noise, and distortions. One important and interesting problem is the effect of such degradations to the performance of CNN-based image classification. More specifically, we wonder whether image-classification performance drops with each kind of degradation, whether this drop can be avoided by including degraded images into training, and whether existing computer vision algorithms that attempt to remove such degradations can help improve the image-classification performance. In this paper, we empirically study this problem for four kinds of degraded images -- hazy images, underwater images, motion-blurred images and fish-eye images. For this study, we synthesize a large number of such degraded images by applying respective physical models to the clear natural images and collect a new hazy image dataset from the Internet. We expect this work can draw more interests from the community to study the classification of degraded images.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Li Fei-Fei
- Xiaogang Wang
- Andrew Zisserman
- Trevor Darrell
- Dacheng Tao
- Yi Yang
- Andrea Vedaldi
Citations in the corpus
- Effects of Degradations on Deep Neural Network Architectures (2018, background): “Also, the authors [3], [15] have not proposed any defensive mechanism in the network architectures to mitigate such performance degradations.”
- A Study of Face Obfuscation in ImageNet (2021, methodology): “Researchers have studied visual recognition in the presence of various image degradation, including blurring (Vasiljevic et al., 2016), lens distortions (Pei et al., 2018), and low resolution (Ryoo et al., 2016).”
- Federated Learning in Vehicular Edge Computing: A Selective Model Aggregation Approach (2020, methodology): “In this paper, we consider image classification as a typical AI application in VEC [5].”