Next Article in Journal
A Pseudo-Random Beamforming Technique for Improving Physical-Layer Security of MIMO Cellular Networks
Next Article in Special Issue
Impact of Misclassification Rates on Compression Efficiency of Red Blood Cell Images of Malaria Infection Using Deep Learning
Previous Article in Journal
On the Definition of Energy Flux in One-Dimensional Chains of Particles
Previous Article in Special Issue
Investigating Detectability of Infrared Radiation Based on Image Evaluation for Engine Flame
Open AccessArticle

Fusing Feature Distribution Entropy with R-MAC Features in Image Retrieval

1
College of Computer Science and Technology, Jilin University, Changchun 130012, China
2
Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China
3
School of Mechanical Science and Engineering, Jilin University, Changchun 130025, China
4
College of Communication Engineering, Jilin University, Changchun 130012, China
*
Author to whom correspondence should be addressed.
Entropy 2019, 21(11), 1037; https://doi.org/10.3390/e21111037
Received: 22 September 2019 / Revised: 17 October 2019 / Accepted: 23 October 2019 / Published: 25 October 2019
(This article belongs to the Special Issue Entropy in Image Analysis II)
Image retrieval based on a convolutional neural network (CNN) has attracted great attention among researchers because of the high performance. The pooling method has become a research hotpot in the task of image retrieval in recent years. In this paper, we propose the feature distribution entropy (FDE) to measure the difference of regional distribution information in the feature maps from CNNs. We propose a novel pooling method, which fuses our proposed FDE with region maximum activations of convolutions (R-MAC) features to improve the performance of image retrieval, as it takes the advantage of regional distribution information in the feature maps. Compared with the descriptors computed by R-MAC pooling, our proposed method considers not only the most significant feature values of each region in feature map, but also the distribution difference in different regions. We utilize the histogram of feature values to calculate regional distribution entropy and concatenate the regional distribution entropy into FDE, which is further normalized and fused with R-MAC feature vectors by weighted summation to generate the final feature descriptors. We have conducted experiments on public datasets and the results demonstrate that our proposed method could produce better retrieval performances than existing state-of-the-art algorithms. Further, higher performance could be achieved by performing these post-processing on the improved feature descriptors. View Full-Text
Keywords: image retrieval; pooling method; convolutional neural network; feature distribution entropy image retrieval; pooling method; convolutional neural network; feature distribution entropy
Show Figures

Figure 1

MDPI and ACS Style

Liu, P.; Gou, G.; Guo, H.; Zhang, D.; Zhao, H.; Zhou, Q. Fusing Feature Distribution Entropy with R-MAC Features in Image Retrieval. Entropy 2019, 21, 1037.

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.

Article Access Map by Country/Region

1
Back to TopTop