Open Access
ARTICLE
Advanced Feature Fusion Algorithm Based on Multiple Convolutional Neural Network for Scene Recognition
1 School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and
Technology, Shanghai, 200093, China.
2 Algorithm Department, Unisoc, Shanghai, 201203, China.
3 Major of Electrical Engineering and Electronics, Graduate School of Engineering, Kogakuin University,
Sinjuku-ku, Tokyo, 163-8677, Japan.
# Both authors contributed equally to this work.
* Corresponding Authors: Feifei Lee. Email: ;
Qiu Chen. Email: .
Computer Modeling in Engineering & Sciences 2020, 122(2), 505-523. https://doi.org/10.32604/cmes.2020.08425
Received 24 August 2019; Accepted 23 October 2019; Issue published 01 February 2020
Abstract
Scene recognition is a popular open problem in the computer vision field. Among lots of methods proposed in recent years, Convolutional Neural Network (CNN) based approaches achieve the best performance in scene recognition. We propose in this paper an advanced feature fusion algorithm using Multiple Convolutional Neural Network (MultiCNN) for scene recognition. Unlike existing works that usually use individual convolutional neural network, a fusion of multiple different convolutional neural networks is applied for scene recognition. Firstly, we split training images in two directions and apply to three deep CNN model, and then extract features from the last full-connected (FC) layer and probabilistic layer on each model. Finally, feature vectors are fused with different fusion strategies in groups forwarded into SoftMax classifier. Our proposed algorithm is evaluated on three scene datasets for scene recognition. The experimental results demonstrate the effectiveness of proposed algorithm compared with other state-of-art approaches.Keywords
Cite This Article
Citations
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.