identify: Identify plants

In BiologicalRecordsCentre/plantnet: Automated Plant Identification with PlantNet

Identify plants

Description

This function is used to classify images using the PlantNet API.

Usage

identify(
  key,
  imageURL,
  simplify = TRUE,
  organs = rep("auto", length(imageURL)),
  lang = "en",
  no_reject = "false"
)

Arguments

key	character, your API key (get from https://my.plantnet.org/)
imageURL	character, the URL path to the image you want to identify. You can provide up to 5 images as a vector of URLs. These images must be of the SAME plant. Make sure this URL is correct, if it is wrong and does not link to your image, or if the link cannot be accessed from the API because, for example, a login is needed, you will get a 'Species not found' error.
simplify	logical, if 'TRUE' the output will be simplified into a data.frame
organs	character, the organ in the image. Must be one of, auto, leaf, flower, fruit, or bark. Must be the same length as 'imageURL'. You can also use the tags habit (the overall form of the plant), or other, but you can only have an image labelled as one of these if you also have an image labelled as one of the primary organs (i.e. auto, leaf, flower, fruit, bark).
lang	can be one of 'en' (English), 'fr' (French), 'de' (German)
no_reject	character, can be one of 'true' or 'false' (default), if 'true' 'no results' are disabled in case of reject class match

Details

The function uses the PlantNet API. To use this service you need to have registered an account and generated an API key. All this can be done here: https://my.plantnet.org/.

Value

If 'simplify' is set to 'FALSE' then a list is returned. The structure of this list can be explored using the tool at https://my-api.plantnet.org. If 'simplify' is set to 'TRUE' (default) then a data.frame is with three columns for the score, latin name, and common name. There are as many rows as there are species predictions from the API.

Examples

## Not run: 
# Get your key from https://my.plantnet.org/
key <- "YOUR_SUPER_SECRET_KEY"
imageURL <- 'https://upload.wikimedia.org/wikipedia/commons/thumb/6/60/Single_lavendar_flower02.jpg/800px-Single_lavendar_flower02.jpg'

# A simple search with one image
classifications <- identify(key, imageURL)
classifications

# Turning simplify to FALSE you can get more infomation
classifications <- identify(key, imageURL, simplify = FALSE)
str(classifications,1)
classifications$results[[1]]

# We can search using up to five images
# Here are three picture of Quercus robur
imageURL1 <- 'https://content.eol.org/data/media/55/2c/a8/509.1003460.jpg'
imageURL2 <- 'https://content.eol.org/data/media/89/88/4c/549.BI-image-16054.jpg'
imageURL3 <- 'https://content.eol.org/data/media/8a/77/9b/549.BI-image-76488.jpg'

classifications <- identify(key, imageURL = c(imageURL1, imageURL2, imageURL3))
classifications

# The classification is better if we assign an organ to each image
classifications <- identify(key,
                            imageURL = c(imageURL1, imageURL2, imageURL3),
                            organs = c('habit','bark','fruit'))
classifications

## End(Not run)

BiologicalRecordsCentre/plantnet documentation built on April 1, 2022, 12:25 a.m.