Namespace match

Class Human as default export

Index

Type aliases

Functions

Type aliases

Descriptor

Descriptor: number[]

Face descriptor type as number array

MatchOptions

MatchOptions: { max?: number; min?: number; multiplier?: number; order?: number; threshold?: number } | undefined

Functions

distance

distance(descriptor1: Descriptor, descriptor2: Descriptor, options?: MatchOptions): number

- Defined in src/face/match.ts:12
Calculates distance between two descriptors

Parameters
- descriptor1: Descriptor
- descriptor2: Descriptor
- options: MatchOptions = ...
  calculation options
  - order - algorithm to use Euclidean distance if order is 2 (default), Minkowski distance algorithm of nth order if order is higher than 2
  - multiplier - by how much to enhance difference analysis in range of 1..100 default is 20 which normalizes results to similarity above 0.5 can be considered a match
Returns number

match

match(descriptor: Descriptor, descriptors: Descriptor[], options?: MatchOptions): { distance: number; index: number; similarity: number }

- Defined in src/face/match.ts:56
Matches given descriptor to a closest entry in array of descriptors

Parameters
- descriptor: Descriptor
  
  face descriptor
- descriptors: Descriptor[]
  
  array of face descriptors to commpare given descriptor to
- options: MatchOptions = ...
  see similarity method for options description Returns
  - index index array index where best match was found or -1 if no matches
  - distance calculated distance of given descriptor to the best match
  - similarity calculated normalized similarity of given descriptor to the best match
Returns { distance: number; index: number; similarity: number }
- distance: number
- index: number
- similarity: number

similarity

similarity(descriptor1: Descriptor, descriptor2: Descriptor, options?: MatchOptions): number

- Defined in src/face/match.ts:42
Calculates normalized similarity between two face descriptors based on their distance

Parameters
- descriptor1: Descriptor
- descriptor2: Descriptor
- options: MatchOptions = ...
  calculation options
  - order - algorithm to use Euclidean distance if order is 2 (default), Minkowski distance algorithm of nth order if order is higher than 2
  - multiplier - by how much to enhance difference analysis in range of 1..100 default is 20 which normalizes results to similarity above 0.5 can be considered a match
  - min - normalize similarity result to a given range
  - max - normalzie similarity resutl to a given range default is 0.2...0.8 Returns similarity between two face descriptors normalized to 0..1 range where 0 is no similarity and 1 is perfect similarity
Returns number