EDEN: Deep Feature Distribution Pooling for Saimaa Ringed Seals Pattern Matching

• Main Authors: Chelak, Ilia, Nepovinnykh, Ekaterina, Eerola, Tuomas, Kälviäinen, Heikki, Belykh, Igor
• Other Authors: Lappeenrannan-Lahden teknillinen yliopisto LUT, Lappeenranta-Lahti University of Technology LUT, fi=School of Engineering Science|en=School of Engineering Science|
• Format: Conference Object
• Language: English
• Published: Springer, Cham 2023
• Subjects: Pattern matching; Global pooling; Animal biometrics; Saimaa ringed seals; ringed seal
• Online Access: https://lutpub.lut.fi/handle/10024/166589

In this paper, pelage pattern matching is considered to solve the individual re-identification of the Saimaa ringed seals. Animal reidentification, together with the access to a large amount of image material through camera traps and crowd-sourcing, provides novel possibilities for animal monitoring and conservation. Image retrieval techniques, such as global pooling, can be used to solve the individual re-identification. However, current global pooling methods incorporate only value distribution of features, losing spatial information. To overcome the problem, we propose a novel pooling approach that allows aggregating the local pattern features to get a fixed size embedding vector that incorporates global features by taking into account their spatial distribution. This is obtained by eigen decomposition of covariances computed for probability mass functions representing feature maps. Embedding vectors can then be used to find the best match in the database of known individuals allowing animal re-identification. The results show that the proposed pooling technique outperforms the existing methods on the challenging Saimaa ringed seal image data. Post-print / Final draft