IPPR of Traditional Wooden Building Section Based on Deep Learning

DOI

10.2991/ahis.k.220601.030How to use a DOI?

Keywords

Deep Learning (DL); Traditional Wooden Architecture; Building Section; Image Recognition

Abstract

In recent years, deep learning (DL) and neural network models have become hot topics in new research directions in the field of machine learning and artificial intelligence. In order to protect our traditional wooden buildings, this paper applies the research of DL in IPPR to traditional wooden building profiles in China through the research of a series of IPPR algorithms such as SSD, SVM, DBN, in several different network training environments such as VGG, DenseNet, and ZF, Research on the IPPR accuracy and recognition speed of traditional wooden building sections. The results show that the SSD algorithm has the highest efficiency when the VGG network training environment and IPPR test cases are about 400, which is higher than before the improvement. The algorithm improves the accuracy by 5-10%, and the recognition speed is also increased by 2-3%.

Copyright

© 2022 The Authors. Published by Atlantis Press International B.V.

Open Access

This is an open access article distributed under the CC BY-NC 4.0 license.

Download article (PDF)

TY  - CONF
AU  - Xiaodan Liang
AU  - Haoming Dong
PY  - 2022
DA  - 2022/06/02
TI  - IPPR of Traditional Wooden Building Section Based on Deep Learning
BT  - Proceedings of the 2021 International conference on Smart Technologies and Systems for Internet of Things (STS-IOT 2021)
PB  - Atlantis Press
SP  - 153
EP  - 159
SN  - 2589-4919
UR  - https://doi.org/10.2991/ahis.k.220601.030
DO  - 10.2991/ahis.k.220601.030
ID  - Liang2022
ER  -