×
Sep 25, 2018 · This paper proposes a new deep convolutional neural network to improve image classification using extra light-field angular information.
This paper proposes a new deep convolutional neural network to improve image classification using extra light-field angular information. The proposed network ...
This paper proposes a new deep convolutional neural network to improve image classification using extra light-field angular information. The proposed network ...
Improved image classification with 4D light-field and interleaved convolutional neural network ... Authors: Zhicheng Lu; Henry W. F. Yeung; Qiang Qu; Yuk Ying ...
Connected Papers is a visual tool to help researchers and applied scientists find academic papers relevant to their field of work.
People also ask
This paper proposes a new deep convolutional neural network to improve image classification using extra light-field angular information.
A new light-field dataset of materials is introduced, and the best performing CNN architecture achieves a 7 % boost compared with 2D image classification, ...
In our work, the feature extraction and angular alignment are performed to improve the image quality, reducing noise effects, and a soft activation function was ...
Improved image classification with 4D light-field and interleaved convolutional neural network ... Image Processing. HWF Yeung. University of Sydney, 2020.
Therefore, one of the main goals of this paper is to investigate whether 4D light-field information improves the performance of ma- terial recognition over 2D ...