The ZooProcess v10 accelerates the processing of images of plankton samples produced by the ZooScan instrument through the combined use of classical image segmentation and measurement methods with automated classification and panoptic segmentation by neural network models.
This artificial intelligence approach allows the automatic separation of objects touching each other in the original image, to enable their exploitation in the future.
The new pipeline supersedes the current versions of the ZooProcess software. It efficiently handles metadata recording, image acquisition from the scanner, image processing, segmentation, feature extraction and data formatting. The resulting data is imported and managed into EcoTaxa, a web application coupling a database with AI tools to accelerate the labelling of large quantities of plankton images by human operators, who are trained biologists. The operational environment provided by the iMagine AI platform as well as dedicated training material and support will promote further uptake of this new pipeline to enhance research efficiency.
ZooScan is a waterproof scanner dedicated to zooplankton samples, developed by the Laboratoire d’Océanographie de Villefranche (LOV). Over 300 units are currently being used in research laboratories and environment assessment companies worldwide. EcoTaxa is a web application that stores images and metadata associated with one individual imaged object and uses AI to accelerate their labelling; it currently hosts over 400M images from more than 700 organisations worldwide.
