Research Article
Automatic Focus Fusion Method of Concrete Crack Image Based on Deep Learning
@INPROCEEDINGS{10.1007/978-3-031-50574-4_14, author={Chuang Wang and Jiawei Pang and Xiaolu Deng and Yangjie Xia and Ruiyang Li and Caihui Wu}, title={Automatic Focus Fusion Method of Concrete Crack Image Based on Deep Learning}, proceedings={Multimedia Technology and Enhanced Learning. 5th EAI International Conference, ICMTEL 2023, Leicester, UK, April 28-29, 2023, Proceedings, Part II}, proceedings_a={ICMTEL PART 2}, year={2024}, month={2}, keywords={Deep learning Artificial intelligence Image autofocus Image fusion}, doi={10.1007/978-3-031-50574-4_14} }- Chuang Wang
Jiawei Pang
Xiaolu Deng
Yangjie Xia
Ruiyang Li
Caihui Wu
Year: 2024
Automatic Focus Fusion Method of Concrete Crack Image Based on Deep Learning
ICMTEL PART 2
Springer
DOI: 10.1007/978-3-031-50574-4_14
Abstract
The algorithm used in the traditional image auto focus fusion method is easy to fall into local iteration, resulting in poor quality of image fusion results. A depth learning based concrete crack image auto focus fusion method is designed. Extract the features in the digital image to obtain the template feature set of the concrete crack image, match, and use the filter function to reduce noise, optimize the image auto focus fusion algorithm, and improve the quality of the fused image after transformation. In order to verify the effectiveness of the design method, comparative experiments are designed to compare the results of the design method and the traditional methods. In terms of fusion focusing results, output signal to noise ratio and image histogram, the results of the design method are better than the traditional methods. The image quality and output signal to noise ratio obtained are higher, and the histogram distribution is more uniform, indicating that the image quality is better.
