SealID_seq

Ringed seal image sequences dataset (SealID_seq) provides a challenging identification task. General purpose animal re-identification methods that utilize fur, feather, skin patterns of animals could be evaluated on that dataset. Large variation in illumination, seal poses, limited size of identifiable region, low contrast between the ring pattern and the rest of the pelage, substantial differences between wet and dry fur and low image quality of automatic camera traps all contribute to the difficulty of the re-identification task of Saimaa ringed seals. We have compiled an extensive dataset, consisting of 32077 images in 120 separate sequences, and made it publicly available. All animal individuals were identified by experts. We are making the SealID_seq available to the research community free of charge. If you use this database in your research, we kindly ask that you reference our papers listed below: Nepovinnykh, E., Vilkman, A., Eerola, T. and Kälviäinen, H., 2023. Re-identification of Saimaa ringed seals from image sequences. Proceedings of 22nd Scandinavian Conference, SCIA Nepovinnykh, E., Eerola, T., Biard, V., Mutka, P., Niemi, M., Kunnasranta, M. and Kälviäinen, H., 2022. SealID: Saimaa ringed seal re-identification dataset. Sensors, 22(19), p.7602. By downloading the data, it is assumed that you agree to the copyright notice (see below). The dataset contains archived images and an "annotation.csv" file: The full non-segmented query images united in sequences contain the same individuals as in the database from SealID dataset: https://doi.org/10.23729/0f4a3296-3b10-40c8-9ad3-0cf00a5a4a53. Query images are ensured to contain some part of a pattern that could be matched to the patterns from the database. SealID database is needed to test re-identification methods. - Annotation: - Contains seal id, sequence_id, image file name. - Format: seal_id, sequence_id, file name, Task for the re-identification algorithm is to search for the best match from the database for the given query image. The SealID database is Copyright © 2023 by Computer Vision and Pattern Recognition Laboratory, LUT University and University of Eastern Finland (UEF). The images in the database are Copyright © 2023 by UEF. The database can be freely downloaded and used for non-profitable scientific purposes, but you are not allowed to redistribute or modify it. Proper citing of this resource is expected if the database is used in research or other reporting. The database is meant to be useful, but it is distributed WITHOUT ANY WARRANTY, and without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Inclusion of this database or even parts of it in a proprietary program is not allowed without a written permission from the owners of the copyright. If you wish to obtain such a permission, you should contact. Computer Vision and Pattern Recognition Laboratory LUT University PO Box 20 FI-53851 Lappeenranta FINLAND If you find any errors or bugs, or have comments related to the database contents, please contact the authors. The research was carried out in the CoExist project (Project ID: KS1549) funded by the European Union, the Russian Federation and the Republic of Finland via The South-East Finland -- Russia CBC 2014-2020 programme.