Synthetic feature pairs dataset and siamese convolutional model for image matching
In a previous publication [1], we created a dataset of feature patches for detection model training. In this paper, we use the same patches to create a new large synthetic dataset of feature pairs, similar and different, in order to perform, thanks to a siamese convolutional model, the description a...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-04-01
|
| Series: | Data in Brief |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352340922001767 |
| _version_ | 1818358000541237248 |
|---|---|
| author | Houssam Halmaoui Abdelkrim Haqiq |
| author_facet | Houssam Halmaoui Abdelkrim Haqiq |
| author_sort | Houssam Halmaoui |
| collection | DOAJ |
| description | In a previous publication [1], we created a dataset of feature patches for detection model training. In this paper, we use the same patches to create a new large synthetic dataset of feature pairs, similar and different, in order to perform, thanks to a siamese convolutional model, the description and matching of the detected features. We thus complete the entire matching pipeline. The accurate manual labeling of image features being very difficult because of their large number and the various associated parameters of position, scale and rotation, recent deep learning models use the result of handcrafted methods for training. Compared to existing datasets, ours avoids model training with false detections of the extraction of feature patches by other algorithms, or with inaccuracy errors of manual labeling. The other advantage of synthetic patches is that we can control their content (corners, edges, etc.), as well as their geometric and photometric parameters, and therefore we control the invariance of the model. The proposed datasets thus allow a new approach to train the different matching modules without using traditional methods. To our knowledge, these are the first feature datasets based on generated synthetic patches for image matching. |
| first_indexed | 2024-12-13T20:22:03Z |
| format | Article |
| id | doaj.art-da789e171ef44fca97b01ed0c626bac7 |
| institution | Directory Open Access Journal |
| issn | 2352-3409 |
| language | English |
| last_indexed | 2024-12-13T20:22:03Z |
| publishDate | 2022-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Data in Brief |
| spelling | doaj.art-da789e171ef44fca97b01ed0c626bac72022-12-21T23:32:40ZengElsevierData in Brief2352-34092022-04-0141107965Synthetic feature pairs dataset and siamese convolutional model for image matchingHoussam Halmaoui0Abdelkrim Haqiq1Corresponding authors.; ISMAC - Higher Institute of Audiovisual and Film Professions, Rabat, Morocco; Hassan First University of Settat, Faculty of Sciences and Techniques, Computer, Networks, Mobility and Modeling laboratory: IR2M, Settat 26000, MoroccoCorresponding authors.; Hassan First University of Settat, Faculty of Sciences and Techniques, Computer, Networks, Mobility and Modeling laboratory: IR2M, Settat 26000, MoroccoIn a previous publication [1], we created a dataset of feature patches for detection model training. In this paper, we use the same patches to create a new large synthetic dataset of feature pairs, similar and different, in order to perform, thanks to a siamese convolutional model, the description and matching of the detected features. We thus complete the entire matching pipeline. The accurate manual labeling of image features being very difficult because of their large number and the various associated parameters of position, scale and rotation, recent deep learning models use the result of handcrafted methods for training. Compared to existing datasets, ours avoids model training with false detections of the extraction of feature patches by other algorithms, or with inaccuracy errors of manual labeling. The other advantage of synthetic patches is that we can control their content (corners, edges, etc.), as well as their geometric and photometric parameters, and therefore we control the invariance of the model. The proposed datasets thus allow a new approach to train the different matching modules without using traditional methods. To our knowledge, these are the first feature datasets based on generated synthetic patches for image matching.http://www.sciencedirect.com/science/article/pii/S2352340922001767Learned featuresInterest pointsKeypointsMatching modelMatching pipelineFeature descriptors |
| spellingShingle | Houssam Halmaoui Abdelkrim Haqiq Synthetic feature pairs dataset and siamese convolutional model for image matching Data in Brief Learned features Interest points Keypoints Matching model Matching pipeline Feature descriptors |
| title | Synthetic feature pairs dataset and siamese convolutional model for image matching |
| title_full | Synthetic feature pairs dataset and siamese convolutional model for image matching |
| title_fullStr | Synthetic feature pairs dataset and siamese convolutional model for image matching |
| title_full_unstemmed | Synthetic feature pairs dataset and siamese convolutional model for image matching |
| title_short | Synthetic feature pairs dataset and siamese convolutional model for image matching |
| title_sort | synthetic feature pairs dataset and siamese convolutional model for image matching |
| topic | Learned features Interest points Keypoints Matching model Matching pipeline Feature descriptors |
| url | http://www.sciencedirect.com/science/article/pii/S2352340922001767 |
| work_keys_str_mv | AT houssamhalmaoui syntheticfeaturepairsdatasetandsiameseconvolutionalmodelforimagematching AT abdelkrimhaqiq syntheticfeaturepairsdatasetandsiameseconvolutionalmodelforimagematching |