A New Re-Ranking Method Based on Convolutional Neural Network and Two Image-to-Class Distances for Remote Sensing Image Retrieval
With the rapid growth of remote sensing image data, it has become necessary to effectively and efficiently retrieve images from a big image database for managing and exploiting such data. This paper presents a novel method for content-based remote sensing image retrieval (CBRSIR) that re-ranks the i...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8851193/ |
| _version_ | 1818622028614205440 |
|---|---|
| author | Famao Ye Meng Dong Wei Luo Xiaoyong Chen Weidong Min |
| author_facet | Famao Ye Meng Dong Wei Luo Xiaoyong Chen Weidong Min |
| author_sort | Famao Ye |
| collection | DOAJ |
| description | With the rapid growth of remote sensing image data, it has become necessary to effectively and efficiently retrieve images from a big image database for managing and exploiting such data. This paper presents a novel method for content-based remote sensing image retrieval (CBRSIR) that re-ranks the initial retrieval result using two image-to-class distances, which are the similarity between an image and an image class. One is the image-to-training-class distance between an image and each image class of the training dataset, which uses the information included in the train samples with known-label. It is used to calculate the weight of the image classes and estimating the class of an image. The other is the image-to-query-class distance between an image and the query class that is obtained using the k-nearest neighbor (k NN) method. The proposed method first obtains the initial retrieval results via sorting the distances of the CNN feature between the query image and each retrieved image in ascending order. Then, the image-to-query-class distance is calculated according to the initial result, and the weight of each class is calculated according to the class probability of images obtained by CNN and the image-to-training-class distances. Finally, the initial result is re-ranked to get the final retrieval result via the weighted image-to-class distances. The performance of the proposed method is tested on UCMD and PatternNet databases. Experimental results show the effectiveness of the proposed re-ranking scheme in image retrieval in comparison to other state-of-the-art techniques. |
| first_indexed | 2024-12-16T18:18:39Z |
| format | Article |
| id | doaj.art-5f1e5fc17d2548a98602e78d2c714efb |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T18:18:39Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-5f1e5fc17d2548a98602e78d2c714efb2022-12-21T22:21:38ZengIEEEIEEE Access2169-35362019-01-01714149814150710.1109/ACCESS.2019.29442538851193A New Re-Ranking Method Based on Convolutional Neural Network and Two Image-to-Class Distances for Remote Sensing Image RetrievalFamao Ye0https://orcid.org/0000-0003-1983-7954Meng Dong1Wei Luo2Xiaoyong Chen3Weidong Min4https://orcid.org/0000-0003-2526-2181School of Surveying and Mapping Engineering, East China University of Technology, Nanchang, ChinaSchool of Information Engineering, Nanchang University, Nanchang, ChinaSchool of Information Engineering, Nanchang University, Nanchang, ChinaSchool of Surveying and Mapping Engineering, East China University of Technology, Nanchang, ChinaSchool of Information Engineering, Nanchang University, Nanchang, ChinaWith the rapid growth of remote sensing image data, it has become necessary to effectively and efficiently retrieve images from a big image database for managing and exploiting such data. This paper presents a novel method for content-based remote sensing image retrieval (CBRSIR) that re-ranks the initial retrieval result using two image-to-class distances, which are the similarity between an image and an image class. One is the image-to-training-class distance between an image and each image class of the training dataset, which uses the information included in the train samples with known-label. It is used to calculate the weight of the image classes and estimating the class of an image. The other is the image-to-query-class distance between an image and the query class that is obtained using the k-nearest neighbor (k NN) method. The proposed method first obtains the initial retrieval results via sorting the distances of the CNN feature between the query image and each retrieved image in ascending order. Then, the image-to-query-class distance is calculated according to the initial result, and the weight of each class is calculated according to the class probability of images obtained by CNN and the image-to-training-class distances. Finally, the initial result is re-ranked to get the final retrieval result via the weighted image-to-class distances. The performance of the proposed method is tested on UCMD and PatternNet databases. Experimental results show the effectiveness of the proposed re-ranking scheme in image retrieval in comparison to other state-of-the-art techniques.https://ieeexplore.ieee.org/document/8851193/Remote sensing image retrieval (RSIR)re-rankingconvolutional neural network (CNN)image-to-class distance |
| spellingShingle | Famao Ye Meng Dong Wei Luo Xiaoyong Chen Weidong Min A New Re-Ranking Method Based on Convolutional Neural Network and Two Image-to-Class Distances for Remote Sensing Image Retrieval IEEE Access Remote sensing image retrieval (RSIR) re-ranking convolutional neural network (CNN) image-to-class distance |
| title | A New Re-Ranking Method Based on Convolutional Neural Network and Two Image-to-Class Distances for Remote Sensing Image Retrieval |
| title_full | A New Re-Ranking Method Based on Convolutional Neural Network and Two Image-to-Class Distances for Remote Sensing Image Retrieval |
| title_fullStr | A New Re-Ranking Method Based on Convolutional Neural Network and Two Image-to-Class Distances for Remote Sensing Image Retrieval |
| title_full_unstemmed | A New Re-Ranking Method Based on Convolutional Neural Network and Two Image-to-Class Distances for Remote Sensing Image Retrieval |
| title_short | A New Re-Ranking Method Based on Convolutional Neural Network and Two Image-to-Class Distances for Remote Sensing Image Retrieval |
| title_sort | new re ranking method based on convolutional neural network and two image to class distances for remote sensing image retrieval |
| topic | Remote sensing image retrieval (RSIR) re-ranking convolutional neural network (CNN) image-to-class distance |
| url | https://ieeexplore.ieee.org/document/8851193/ |
| work_keys_str_mv | AT famaoye anewrerankingmethodbasedonconvolutionalneuralnetworkandtwoimagetoclassdistancesforremotesensingimageretrieval AT mengdong anewrerankingmethodbasedonconvolutionalneuralnetworkandtwoimagetoclassdistancesforremotesensingimageretrieval AT weiluo anewrerankingmethodbasedonconvolutionalneuralnetworkandtwoimagetoclassdistancesforremotesensingimageretrieval AT xiaoyongchen anewrerankingmethodbasedonconvolutionalneuralnetworkandtwoimagetoclassdistancesforremotesensingimageretrieval AT weidongmin anewrerankingmethodbasedonconvolutionalneuralnetworkandtwoimagetoclassdistancesforremotesensingimageretrieval AT famaoye newrerankingmethodbasedonconvolutionalneuralnetworkandtwoimagetoclassdistancesforremotesensingimageretrieval AT mengdong newrerankingmethodbasedonconvolutionalneuralnetworkandtwoimagetoclassdistancesforremotesensingimageretrieval AT weiluo newrerankingmethodbasedonconvolutionalneuralnetworkandtwoimagetoclassdistancesforremotesensingimageretrieval AT xiaoyongchen newrerankingmethodbasedonconvolutionalneuralnetworkandtwoimagetoclassdistancesforremotesensingimageretrieval AT weidongmin newrerankingmethodbasedonconvolutionalneuralnetworkandtwoimagetoclassdistancesforremotesensingimageretrieval |