Hash-based appearance search

A method comprising using a processor to:

• obtain a hash vector training set that comprises training hash vectors representing respective examples of a search target common to training images, each of the training hash vectors comprising one or more hashes as a respective one or more components of the training hash vector;
• determine which of the one or more hashes satisfy a threshold criterion;
• and
• generate a scoring database based on the one or more hashes that satisfy the threshold criterion.

A system, comprising:

• a camera;
• a server, comprising:
• a processor communicatively coupled to the camera;
• and
• a non-transitory computer readable medium having stored thereon computer program code that is executable by the processor and that, when executed by the processor, causes the processor to perform a method comprising using the processor to:
• obtain a hash vector representing a search subject depicted in an image, the hash vector comprising one or more hashes as a respective one or more components of the hash vector;
• determine which one or more of the hashes satisfy a threshold criterion;
• determine which one or more of the components of the hash vector qualify as a scoring component, wherein the one or more components that qualify as a scoring component correspond to a respective one or more hashes that satisfy the threshold criterion and that are represented in a scoring database that is generated based on different examples of a search target;
• and
• determine a score representing a similarity of the search subject to the different examples of the search target used to generate the scoring database, wherein the processor determines the score based on the one or more components of the hash vector that qualify as a scoring component.

A non-transitory computer readable medium having stored thereon computer program code that is executable by a processor and that, when executed by the processor, causes the processor to perform a method comprising using the processor to:

• obtain a hash vector representing a search subject depicted in an image, the hash vector comprising one or more hashes as a respective one or more components of the hash vector;
• determine which one or more of the hashes satisfy a threshold criterion;
• determine which one or more of the components of the hash vector qualify as a scoring component, wherein the one or more components that qualify as a scoring component correspond to a respective one or more hashes that satisfy the threshold criterion and that are represented in a scoring database that is generated based on different examples of a search target;
• and
• determine a score representing a similarity of the search subject to the different examples of the search target used to generate the scoring database, wherein the processor determines the score based on the one or more components of the hash vector that qualify as a scoring component.