Entity identification using machine learning
Methods, systems, and apparatus, including computer programs encoded on computer storage media for identification and re-identification of fish. In some implementations, first media representative of aquatic cargo is received. Second media based on the first media is generated, wherein a resolution of the second media is higher than a resolution of the first media. A cropped representation of the second media is generated. The cropped representation is provided to the machine learning model. In response to providing the cropped representation to the machine learning model, an embedding representing the cropped representation is generated using the machine learning model. The embedding is mapped to a high dimensional space. Data identifying the aquatic cargo is provided to a database, wherein the data identifying the aquatic cargo comprises an identifier of the aquatic cargo, the embedding, and a mapped region of the high dimensional space.
1. A computer-implemented method comprising:
receiving multiple images of a particular fish;
generating a set of features from the multiple images, the set of features including values that represent distances between different pairs of key points on the particular fish;
providing the set of features including the values that represent distances between different pairs of key points on the particular fish to a machine learning model obtaining an embedding from the machine learning model;
generating a cluster identifier for the particular fish based on at least on the embedding; and
storing data identifying the cluster identifier for the particular fish in a database.
2. The method of claim 1 , wherein generating the cluster identifier comprises:
determining that the embedding matches a previously-generated embedding, then that the particular fish associated with the embedding has been re-identified.
3. The method of claim 1 , wherein generating the cluster identifier comprises:
determining, by the one or more processors, that the embedding does not match any previously-generated embedding, then determining that the particular fish associated with the embedding is newly identified.
4. The method of claim 1 , wherein the cluster identifier is associated with a cluster of fish that share one or more characteristics associated with fish.
5. The method of claim 1 , wherein the set of features comprises distances between pairs of key points of the particular fish, and the key points comprise a dorsal fin of the particular fish, a pectoral fin of the particular fish, and an eye of the particular fish.
6. The method of claim 1 , comprising:
generating positive training data representative of a fish type;
generating negative training data representative of other fish types; and
training the machine learning model to generate embeddings using the positive training data and the negative training data.
7. The method of claim 1 , wherein the embedding comprises a 128-or-more dimensional vector.
8. A system comprising one or more processors and one or more storage devices storing instructions that are operable, when executed by the one or more processors, to cause the one or more processors to perform operations comprising:
receiving multiple images of a particular fish;
generating a set of features from the multiple images, the set of features including values that represent distances between different pairs of key points on the particular fish;
providing the set of features including the values that represent distances between different pairs of key points on the particular fish to a machine learning model
obtaining an embedding from the machine learning model;
generating a cluster identifier for the particular fish based on at least on the embedding; and
storing data identifying the cluster identifier for the particular fish in a database.
9. The system of claim 8 , wherein generating the cluster identifier comprises:
determining that the embedding matches a previously-generated embedding, then that the particular fish associated with the embedding has been re-identified.
10. The system of claim 8 , wherein generating the cluster identifier comprises:
determining, by the one or more processors, that the embedding does not match any previously-generated embedding, then determining that the particular fish associated with the embedding is newly identified.
11. The system of claim 8 , wherein the cluster identifier is associated with a cluster of fish that share one or more characteristics associated with fish.
12. The system of claim 8 , wherein the set of features comprises distances between pairs of key points of the particular fish, and the key points comprise a dorsal fin of the particular fish, a pectoral fin of the particular fish, and an eye of the particular fish.
13. The system of claim 8 , wherein the operations comprise:
generating positive training data representative of a fish type;
generating negative training data representative of other fish types; and
training the machine learning model to generate embeddings using the positive training data and the negative training data.
14. The system of claim 8 , wherein the embedding comprises a 128-or-more dimensional vector.
15. One or more non-transitory computer-readable media comprising instructions stored thereon that are executable by one or more processing devices and upon such execution cause the one or more processing devices to perform operations comprising:
receiving multiple images of a particular fish;
generating a set of features from the multiple images, the set of features including values that represent distances between different pairs of key points on the particular fish;
providing the set of features including the values that represent distances between different pairs of key points on the particular fish to a machine learning model
obtaining an embedding from the machine learning model;
generating a cluster identifier for the particular fish based on at least on the embedding; and
storing data identifying the cluster identifier for the particular fish in a database.
16. The media of claim 15 , wherein generating the cluster identifier comprises:
determining that the embedding matches a previously-generated embedding, then that the particular fish associated with the embedding has been re-identified.
17. The media of claim 15 , wherein generating the cluster identifier comprises:
determining, by the one or more processors, that the embedding does not match any previously-generated embedding, then determining that the particular fish associated with the embedding is newly identified.
18. The media of claim 15 , wherein the cluster identifier is associated with a cluster of fish that share one or more characteristics associated with fish.
19. The media of claim 15 , wherein the set of features comprises distances between pairs of key points of the particular fish, and the key points comprise a dorsal fin of the particular fish, a pectoral fin of the particular fish, and an eye of the particular fish.
20. The media of claim 15 , wherein the operations comprise:
generating positive training data representative of a fish type;
generating negative training data representative of other fish types; and
training the machine learning model to generate embeddings using the positive training data and the negative training data.