94,920 Sightings
|
The Sharkbook photo-identification library is an award-winning visual database of shark encounters and of individually catalogued sharks. The library is maintained and used by marine biologists to collect and analyze shark sighting data for multiple species to learn more about these amazing creatures.
|
sharkbook.ai Partners
Algorithms
PIE
Pose Invariant Embeddings (or PIE) is a deep learning approach to individual ID. PIE is trained to learn embeddings that are useful for distinguishing among individuals in a wildlife population. Unlike HotSpotter, which is a “static” pattern matcher (i.e. a fixed algorithm not trained for each separate species), PIE can be trained on a per-species basis. Wild Me has generated separate PIE models optimized for manta rays, humpback whales, orcas, right whales, and so on. And unlike fixed-catalog classifiers like Deepsense or Kaggle7, PIE can gracefully add new individuals to its catalog without being retrained: it learns the general task of mapping images into embeddings that represent individuals, rather than the specific task of sorting images into a fixed number of IDs. PIE strikes a lovely balance between a flexible general-purpose identifier and one that can be trained and refined on a given problem. In summary, PIE is a very powerful, reusable machine learning technique that can be trained to identify individuals across many species. Learn more about PIE.
MODIFIED GROTH
In 1986, Dr. Edward Groth published a pattern-matching algorithm for comparing coordinates of stars in the night sky. We use an adaptation of this algorithm to match whale sharks using the coordinates of their spots. Learn more about Modified Groth.
I3S
The I3S algorithm was developed in 2007 for pattern-matching of the spotted ragged-tooth shark (Carcharias taurus). Since then, the algorithm has proven effective for other species with spots. Learn more about I3S.
CURVRANK V2
CurvRank v2 is a machine learning-based approach to matching a curvature or an “edge”, such as the trailing edge of a cetacean fluke or a dorsal fin. Specifically, machine learning is employed to weight sections of a fin or fluke that contain individually identifying information and to represent the curvature in a comparable format less subject to deformation from changes in the pose of the animal in the image. Learn more about Curvrank v2.
FINFINDR
finFindR is a machine learning-based approach to matching a curvature or an “edge”, such as the leading and trailing edges of a dorsal fin. More specifically, machine learning is employed to identify cetacean bodies and dorsal fins in an image, extract a fin edge, create a feature matrix representing that edge, and then compare that edge to others in the catalog. Learn more about finFindR.
Pose Invariant Embeddings (or PIE) is a deep learning approach to individual ID. PIE is trained to learn embeddings that are useful for distinguishing among individuals in a wildlife population. Unlike HotSpotter, which is a “static” pattern matcher (i.e. a fixed algorithm not trained for each separate species), PIE can be trained on a per-species basis. Wild Me has generated separate PIE models optimized for manta rays, humpback whales, orcas, right whales, and so on. And unlike fixed-catalog classifiers like Deepsense or Kaggle7, PIE can gracefully add new individuals to its catalog without being retrained: it learns the general task of mapping images into embeddings that represent individuals, rather than the specific task of sorting images into a fixed number of IDs. PIE strikes a lovely balance between a flexible general-purpose identifier and one that can be trained and refined on a given problem. In summary, PIE is a very powerful, reusable machine learning technique that can be trained to identify individuals across many species. Learn more about PIE.
MODIFIED GROTH
In 1986, Dr. Edward Groth published a pattern-matching algorithm for comparing coordinates of stars in the night sky. We use an adaptation of this algorithm to match whale sharks using the coordinates of their spots. Learn more about Modified Groth.
I3S
The I3S algorithm was developed in 2007 for pattern-matching of the spotted ragged-tooth shark (Carcharias taurus). Since then, the algorithm has proven effective for other species with spots. Learn more about I3S.
CURVRANK V2
CurvRank v2 is a machine learning-based approach to matching a curvature or an “edge”, such as the trailing edge of a cetacean fluke or a dorsal fin. Specifically, machine learning is employed to weight sections of a fin or fluke that contain individually identifying information and to represent the curvature in a comparable format less subject to deformation from changes in the pose of the animal in the image. Learn more about Curvrank v2.
FINFINDR
finFindR is a machine learning-based approach to matching a curvature or an “edge”, such as the leading and trailing edges of a dorsal fin. More specifically, machine learning is employed to identify cetacean bodies and dorsal fins in an image, extract a fin edge, create a feature matrix representing that edge, and then compare that edge to others in the catalog. Learn more about finFindR.
Species
|
RHINCODON TYPUS
Whale shark CARCHARIAS TAURUS Sand tiger shark STEGOSTOMA TIGRINUM Leopard (or zebra) shark |
CARCHARODON CARCHARIAS
White shark GALEOCERDO CUVIER Tiger shark NOTORYNCHUS CEPEDIANUS Broadnose Sevengill shark |
