The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.

Type: Package
Title: An Interface for Face Recognition
Version: 0.1.0
Date: 2018-05-14
URL: https://github.com/methodds/facerec
BugReports: https://github.com/methodds/facerec/issues
Description: Provides an interface to the 'Kairos' Face Recognition API https://kairos.com/face-recognition-api. The API detects faces in images and returns estimates for demographics like gender, ethnicity and age.
License: MIT + file LICENSE
Encoding: UTF-8
LazyData: true
RoxygenNote: 6.0.1
Imports: magrittr (≥ 1.5.0), dplyr (≥ 0.7.0), httr (≥ 1.3.0), jsonlite (≥ 1.5.0), knitr (≥ 1.2.0), stringr (≥ 1.2.0), snakecase (≥ 0.9.0), rlang
Suggests: magick (≥ 1.9.0), ggplot2 (≥ 2.2.0), purrr (≥ 0.2.0), rmarkdown (≥ 1.9.0)
VignetteBuilder: knitr
NeedsCompilation: no
Packaged: 2018-05-14 11:45:43 UTC; cs
Author: Carsten Schwemmer ORCID iD [aut, cre]
Maintainer: Carsten Schwemmer <c.schwem2er@gmail.com>
Repository: CRAN
Date/Publication: 2018-05-14 12:19:21 UTC

Pipe operator

Description

Pipe operator

Usage

lhs %>% rhs

detect faces

Description

Detect faces in an input image and return annotations from the 'Kairos' API.

Usage

detect(image, min_head_scale = 0.015)

Arguments

image

An image of file type 'JPG', 'PNG', or 'BMP'. Can either be an url string or a local image processed with prep_image.

min_head_scale

Set the ratio of the smallest face to look for in the input image. Accepts a value between .015 (1:64 scale) and .5 (1:2 scale).

Value

A data frame with annotations for each detected face.

Examples



 facerec_init()

 # one image
 finn_image <- 'https://upload.wikimedia.org/wikipedia/en/2/2a/Finn-Force_Awakens_%282015%29.png'
 faces <- detect(image = finn_image)

 # multiple images
 sw_image <- 'https://upload.wikimedia.org/wikipedia/en/8/82/Leiadeathstar.jpg'
 padme_image <- 'https://upload.wikimedia.org/wikipedia/en/e/ee/Amidala.png'

 faces <- c(finn_image, sw_image, padme_image) %>%
 purrr::map(detect) %>% dplyr::bind_rows()
 




enroll faces

Description

Enroll face in an input image to a gallery and assign a subject id.

Usage

enroll(image, subject_id, gallery, min_head_scale = 0.015)

Arguments

image

An image of file type 'JPG', 'PNG', or 'BMP'. Can either be an url string or a local image processed with prep_image.

subject_id

A string containing the id to assign for the person in the enrolled image.

gallery

A string containing the name of the gallery in which the image will be enrolled.

min_head_scale

Set the ratio of the smallest face to look for in the input image. Accepts a value between .015 (1:64 scale) and .5 (1:2 scale).

Value

A data frame with annotations for the enrolled image.

Examples



facerec_init()

finn_image <- 'https://upload.wikimedia.org/wikipedia/en/2/2a/Finn-Force_Awakens_%282015%29.png'
finn_enroll <- enroll(image = finn_image, subject_id = 'finn', gallery = 'starwars')




authorization

Description

Initializes the authorization credentials for the 'Kairos' Face Recognition API. Needs to be called before using any other functions of facerec and requires kairos_id and kairos_key as environment variables.

Usage

facerec_init()

Value

nothing.

Examples

## Not run: 
Sys.setenv(kairos_id = "Your Kairos API id")
Sys.setenv(kairos_key = "Your Kairos API key")

facerec_init()

## End(Not run)





list galleries

Description

Returns identifiers for all galleries associated with a 'Kairos' application.

Usage

get_galleries()

Value

A vector of gallery id's.

Examples



facerec_init()

# enroll
finn_image <- 'https://upload.wikimedia.org/wikipedia/en/2/2a/Finn-Force_Awakens_%282015%29.png'
first_gallery <- enroll(image = finn_image, subject_id = 'finn', gallery = 'starwars')
second_gallery <- enroll(image = finn_image, subject_id = 'finn', gallery = 'more_starwars')

# get_galleries
get_galleries()




Description

Returns all subject id's associated with a gallery.

Usage

get_gallery_subjects(gallery)

Arguments

gallery

The gallery in which the subjects are enrolled.

Value

A vector of subject id's

Examples



facerec_init()

# enroll
finn_image <- 'https://upload.wikimedia.org/wikipedia/en/2/2a/Finn-Force_Awakens_%282015%29.png'
finn_enroll <- enroll(image = finn_image, subject_id = 'finn', gallery = 'starwars')

# view subjects
get_gallery_subjects(gallery = 'starwars')




prepare local image

Description

Prepares a local image for an upload the 'Kairos' API via detect, enroll, recognize and verify.

Usage

prep_image(img_file)

Arguments

img_file

Path to an image of file type 'JPG', 'PNG', or 'BMP'.

Value

The prepared image object.

Examples

 

 facerec_init()

 # download example image
 finn_image <- 'https://upload.wikimedia.org/wikipedia/en/2/2a/Finn-Force_Awakens_%282015%29.png'
 temp_img_path <- tempfile(fileext = '.png')
 download.file(finn_image, temp_img_path, mode = 'wb', quiet = TRUE)

 # prepare image
 finn_local <- prep_image(temp_img_path)

 # use prepared image
 faces <- detect(image = finn_local)
 


recognize face

Description

Recognize faces in an image and return the most likely matches from a gallery.

Usage

recognize(image, gallery, min_head_scale = 0.015, threshold = 0.6,
  max_num_results = 10, show_candidate_images = TRUE)

Arguments

image

An image of file type JPG, PNG, or BMP. Can either be an url string or a local image processed with prep_image.

gallery

A string containing the name of the gallery in which the image will be enrolled.

min_head_scale

Set the ratio of the smallest face to look for in the input image. Accepts a value between .015 (1:64 scale) and .5 (1:2 scale).

threshold

Likelihood (between 0 and 1) used to determine a valid facial match. Defaults to 0.6.

max_num_results

The maximum number of potential matches that are returned. Defaults to 10.

show_candidate_images

Whether to return temporary URLs for each potential match. Defaults to TRUE.

Value

A dataframe with the potential matches for the input image. The likelihood of matches is given in column confidence.

Examples

 

facerec_init()

# enroll
finn_image <- 'https://upload.wikimedia.org/wikipedia/en/2/2a/Finn-Force_Awakens_%282015%29.png'
padme_image <- 'https://upload.wikimedia.org/wikipedia/en/e/ee/Amidala.png'
finn_face <- enroll(image = finn_image, subject_id = 'finn', gallery = 'starwars')
padme_face <- enroll(image = padme_image, subject_id = 'padme', gallery = 'starwars')

# recognize
finn_2 <- 'https://upload.wikimedia.org/wikipedia/commons/b/b6/John_Boyega_by_Gage_Skidmore.jpg'
finn_rec <- recognize(image = finn_2, gallery = 'starwars')



Description

Removes a gallery and all included subjects.

Usage

remove_gallery(gallery)

Arguments

gallery

The name of the gallery to be removed.

Value

nothing.

Examples




facerec_init()

# enroll
finn_image <- 'https://upload.wikimedia.org/wikipedia/en/2/2a/Finn-Force_Awakens_%282015%29.png'
finn_enroll <- enroll(image = finn_image, subject_id = 'finn', gallery = 'starwars')

# remove gallery
remove_gallery(gallery = 'starwars')




remove subject

Description

Removes a subject from a gallery.

Usage

remove_subject(subject_id, gallery)

Arguments

subject_id

The subject id for the subject to be removed.

gallery

The name of the gallery in which the subject is enrolled.

Value

nothing.

Examples



facerec_init()

# enroll
finn_image <- 'https://upload.wikimedia.org/wikipedia/en/2/2a/Finn-Force_Awakens_%282015%29.png'
finn_enroll <- enroll(image = finn_image, subject_id = 'finn', gallery = 'starwars')

# remove subject
remove_subject(subject_id = 'finn', gallery = 'starwars')




verify face

Description

Verify whether face in an input image belongs to a subject in a gallery.

Usage

verify(image, subject_id, gallery)

Arguments

image

An image of file type 'JPG', 'PNG', or 'BMP'. Can either be an url string or a local image processed with prep_image.

subject_id

A string containing the id for the person in the gallery to be verified.

gallery

A string containing the name of the gallery in which the subject will be verified.

Value

A data frame with the verification annotations for the input image. The likelihood of a match is given in column confidence.

Examples




facerec_init()

# enroll
padme_image <- 'https://upload.wikimedia.org/wikipedia/en/e/ee/Amidala.png'
padme_face <- enroll(image = padme_image, subject_id = 'padme', gallery = 'starwars')

# verify
amidala_img <- 'https://upload.wikimedia.org/wikipedia/it/5/5e/Padm%C3%A9_Amidala.png'
verified <- verify(image = amidala_img, subject_id = 'padme', gallery = 'starwars')




view subject

Description

Returns all face id's for each image enrolled for a given subject in a gallery.

Usage

view_subject(subject_id, gallery)

Arguments

subject_id

The subject id for which to return all face id's.

gallery

The gallery in which the subject is enrolled.

Value

A dataframe with face id's and enrollment timestamps associated with the input subject.

Examples



facerec_init()

# enroll
finn_image <- 'https://upload.wikimedia.org/wikipedia/en/2/2a/Finn-Force_Awakens_%282015%29.png'
finn_enroll <- enroll(image = finn_image, subject_id = 'finn', gallery = 'starwars')

# view subject
view_subject(subject_id = 'finn', gallery = 'starwars')



These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.