Abstract: A method for retrieving footprint images is provided, comprising: pre-training models; cleaning footprint data and conducting expansion pre-processing by using the pre-trained models, dividing the footprint data into multiple data sets; adjusting full connection layers and classification layers of the models; training the models again by using the data sets through the parameters of the pre-trained models; saving the models trained twice, removing the classification layer, executing a feature extraction for images in an image library and a retrieval library to form a feature index library; connecting the features extracted by three models to form fused features, establishing a fused feature vector index library; extracting the features of the images in the image library to be retrieved in advance, and establishing a feature vector library; calculating distances in the retrieval library and the image library when a single footprint image is inputted, thereby outputting the image with the highest similarity.
Type:
Grant
Filed:
November 25, 2020
Date of Patent:
November 7, 2023
Assignees:
SUZHOU UNIVERSITY OF SCIENCE AND TECHNOLOGY, KUNSHAN PUBLIC SECURITY BUREAU
Inventors:
Xuefeng Xi, Yang Chen, Cheng Zeng, Qian Zhang, Cheng Cheng, Baochuan Fu, Zhiming Cui
Abstract: A method for retrieving footprint images is provided, comprising: pre-training models; cleaning footprint data and conducting expansion pre-processing by using the pre-trained models, dividing the footprint data into multiple data sets; adjusting full connection layers and classification layers of the models; training the models again by using the data sets through the parameters of the pre-trained models; saving the models trained twice, removing the classification layer, executing a feature extraction for images in an image library and a retrieval library to form a feature index library; connecting the features extracted by three models to form fused features, establishing a fused feature vector index library; extracting the features of the images in the image library to be retrieved in advance, and establishing a feature vector library; calculating distances in the retrieval library and the image library when a single footprint image is inputted, thereby outputting the image with the highest similarity.
Type:
Application
Filed:
November 25, 2020
Publication date:
March 31, 2022
Applicants:
SUZHOU UNIVERSITY OF SCIENCE AND TECHNOLOGY, KUNSHAN PUBLIC SECURITY BUREAU
Inventors:
Xuefeng XI, Yang CHEN, Cheng ZENG, Qian ZHANG, Cheng CHENG, Baochuan FU, Zhiming CUI