A Recognition Method of Ancient Architectures Based on the Improved Inception V3 Model

被引:12
作者
Wang, Xinyang [1 ,2 ]
Li, Jiaxun [1 ]
Tao, Jin [3 ]
Wu, Ling [1 ]
Mou, Chao [1 ,2 ]
Bai, Weihua [4 ]
Zheng, Xiaotian [1 ]
Zhu, Zirui [1 ]
Deng, Zhuohong [1 ,5 ]
机构
[1] Beijing Forestry Univ, Sch Informat Sci & Technol, Beijing 100083, Peoples R China
[2] Natl Forestry & Grassland Adm, Engn Res Ctr Forestry Oriented Intelligent Informa, Beijing 100083, Peoples R China
[3] South China Univ Technol, Sch Architecture, Guangzhou 510641, Peoples R China
[4] Zhaoqing Univ, Sch Comp Sci, Zhaoqing 526061, Peoples R China
[5] Shanghai Jiao Tong Univ, Sch Elect Informat & Elect Engn, Shanghai 200240, Peoples R China
来源
SYMMETRY-BASEL | 2022年 / 14卷 / 12期
关键词
deep learning; Inception V3; transfer learning; ancient architecture classification; dropout layer;
D O I
10.3390/sym14122679
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Traditional ancient architecture is a symbolic product of cultural development and inheritance, with high social and cultural value. An automatic recognition model of ancient building types is one possible application of asymmetric systems, and it will be of great significance to be able to identify ancient building types via machine vision. In the context of Chinese traditional ancient buildings, this paper proposes a recognition method of ancient buildings, based on the improved asymmetric Inception V3 model. Firstly, the improved Inception V3 model adds a dropout layer between the global average pooling layer and the SoftMax classification layer to solve the overfitting problem caused by the small sample size of the ancient building data set. Secondly, migration learning and the ImageNet dataset are integrated into model training, which improves the speed of network training while solving the problems of the small scale of the ancient building dataset and insufficient model training. Thirdly, through ablation experiments, the effects of different data preprocessing methods and different dropout rates on the accuracy of model recognition were compared, to obtain the optimized model parameters. To verify the effectiveness of the model, this paper takes the ancient building dataset that was independently constructed by the South China University of Technology team as the experimental data and compares the recognition effect of the improved Inception V3 model proposed in this paper with several classical models. The experimental results show that when the data preprocessing method is based on filling and the dropout rate is 0.3, the recognition accuracy of the model is the highest; the accuracy rate of identifying ancient buildings using our proposed improved Inception V3 model can reach up to 98.64%. Compared with other classical models, the model accuracy rate has increased by 17.32%, and the average training time has accelerated by 2.29 times, reflecting the advantages of the model proposed in this paper. Finally, the improved Inception V3 model was loaded into the ancient building identification system to prove the practical application value of this research.
引用
收藏
页数:19
相关论文
共 27 条
[1]   Xception: Deep Learning with Depthwise Separable Convolutions [J].
Chollet, Francois .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :1800-1807
[2]  
Di H., 2018, Identif. Apprec. Cult. Relics, V3, P130
[3]   Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs [J].
Ding, Xiaohan ;
Zhang, Xiangyu ;
Han, Jungong ;
Ding, Guiguang .
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, :11953-11965
[4]   THE DESIGN AND USE OF STEERABLE FILTERS [J].
FREEMAN, WT ;
ADELSON, EH .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1991, 13 (09) :891-906
[5]  
Hasan M. S., 2020, P INT C INFORM COMMU, V1183, P631
[6]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[7]  
Hinton GE., 2012, COMPUT SCI, V3, P212
[8]  
Ioffe Sergey, 2015, P MACHINE LEARNING R, V37, P448
[9]   ImageNet Classification with Deep Convolutional Neural Networks [J].
Krizhevsky, Alex ;
Sutskever, Ilya ;
Hinton, Geoffrey E. .
COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90
[10]  
Kun G., 2017, THESIS WUHAN U TECHN