Next Article in Journal
Combined Recommendation Algorithm Based on Improved Similarity and Forgetting Curve
Previous Article in Journal
A Privacy-Preserving Protocol for Utility-Based Routing in DTNs
Article Menu

Export Article

Open AccessArticle
Information 2019, 10(4), 129; https://doi.org/10.3390/info10040129

Deep Image Similarity Measurement Based on the Improved Triplet Network with Spatial Pyramid Pooling

1
School of Computer, Hunan University of Technology, Zhuzhou 412000, China
2
School of Computer Science and Engineering, Central South University, Changsha 410083, China
*
Author to whom correspondence should be addressed.
Received: 15 March 2019 / Revised: 2 April 2019 / Accepted: 3 April 2019 / Published: 8 April 2019
  |  
PDF [4780 KB, uploaded 18 April 2019]
  |     |  

Abstract

Image similarity measurement is a fundamental problem in the field of computer vision. It is widely used in image classification, object detection, image retrieval, and other fields, mostly through Siamese or triplet networks. These networks consist of two or three identical branches of convolutional neural network (CNN) and share their weights to obtain the high-level image feature representations so that similar images are mapped close to each other in the feature space, and dissimilar image pairs are mapped far from each other. Especially, the triplet network is known as the state-of-the-art method on image similarity measurement. However, the basic CNN can only handle fixed-size images. If we obtain a fixed size image via cutting or scaling, the information of the image will be lost and the recognition accuracy will be reduced. To solve the problem, this paper has proposed the triplet spatial pyramid pooling network (TSPP-Net) through combing the triplet convolution neural network with the spatial pyramid pooling. Additionally, we propose an improved triplet loss function, so that the network model can realize twice distance learning by only inputting three samples at one time. Through the theoretical analysis and experiments, it is proved that the TSPP-Net model and the improved triple loss function can improve the generalization ability and the accuracy of image similarity measurement algorithm. View Full-Text
Keywords: image similarity measurement; triplet network; spatial pyramid pooling; improved triplet loss function image similarity measurement; triplet network; spatial pyramid pooling; improved triplet loss function
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Yuan, X.; Liu, Q.; Long, J.; Hu, L.; Wang, Y. Deep Image Similarity Measurement Based on the Improved Triplet Network with Spatial Pyramid Pooling. Information 2019, 10, 129.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Information EISSN 2078-2489 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top