The LifeCLEF lab (www.lifeclef.org) proposes to evaluate the performance of multimedia analysis techniques on collections of multimedia records (for Birds, Plants and Fish species). This challenge was initially conducted during an image-based plant identification task, that was run within ImageCLEF lab during the last three years. The Plant task, called PlantCLEF, is based on large and real-world data collected within Tela Botanica network. The full dataset mobilized during the 2013 campaign is presented here, in order to give an overview of this challenge, to any potential participant. It can be dowload at the following urls : http://www.imageclef.org/2013/plant
Plant Observations 5820 entities
- SheetAsBackground (42%): exclusively pictures of leaves in front of a uniform background produced with a scanner or a camera with a sheet.
- NaturalBackground (58%): free natural photographs of different views on different subparts of a plant into the wild.
- SheetAsBackground Scan (22%): scan of a single leaf.
- SheetAsBackground Scan-like (22%): photograph of a single leaf in front of an uniform artificial background.
- NaturalBackground Leaf (16%): photograph of one leaf directly on the plant.
- NaturalBackground Flower (18%): photograph of one flower or a group of flowers.
- NaturalBackground Fruit (8%): photograph of one fruit or a group of fruits.
- NaturalBackground Stem (8%): photograph of the stalk, or a stipe, or the bark of the trunk.
- NaturalBackground Entire (8%): photograph of the entire plant, from the floor to the top.
Another important additional information in the meta-data is IndividualPlantId, an unique identifier for one single individual plant observed by one same person the same day with the same device with the same lightening conditions. Each individual plant observed may thus be associated to several pictures.