Image Representation Method Based on Relative Layer Entropy for Insulator Recognition
Deep convolutional neural networks (DCNNs) with alternating convolutional, pooling and decimation layers are widely used in computer vision, yet current works tend to focus on deeper networks with many layers and neurons, resulting in a high computational complexity. However, the recognition task is...
Main Authors: | Zhenbing Zhao, Hongyu Qi, Xiaoqing Fan, Guozhi Xu, Yincheng Qi, Yongjie Zhai, Ke Zhang |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-04-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/22/4/419 |
Similar Items
-
Using Non-Additive Entropy to Enhance Convolutional Neural Features for Texture Recognition
by: Joao Florindo, et al.
Published: (2021-09-01) -
Aggregated Deep Local Features for Remote Sensing Image Retrieval
by: Raffaele Imbriaco, et al.
Published: (2019-02-01) -
Adding spatial distribution clue to aggregated vector in image retrieval
by: Pingping Liu, et al.
Published: (2018-02-01) -
Covariance Representations and Coherent Measures for Some Entropies
by: Baishuai Zuo, et al.
Published: (2023-11-01) -
Mineral aggregate thermal roof insulation
by: 9740 Canadian Standards Association