ITHILDIN
Integrated Tool for Homologous Image Landmark Detection in Insects using Neural networks
This tool is designed for female Diptera species identification using geometric morphometric analysis on uploaded images of wings. We refer to this preprint for further information. This is still a demonstrator. Currently the application is focused on female mosquito species identification. Glossinidae and Drosophilidae are also available for landmark annotation but these were trained with relatively few samples and are therefore less reliable. If you want to change that or use the application for research or monitoring purposes please contact us, we are happy to support you!
Search Previous Results
Already processed images? Enter your session ID to retrieve your results.
Read this, before you upload!
Before you upload your first images, please inspect the Image Capture Guidelines. Wings must be mounted between glass slides so the wing is flat. Please only image wings that are undamaged. Image the wings with good lighting on a neutral background. If you cannot identify the veins on the image neither can the AI! The wing should be placed with round boundary at the lower part of the image. Species classification only works for female mosquitoes!
Acceptable file formats include JPG, JPEG, PNG, TIF and TIFF. You can upload up to 256 MB per upload, for large or regular uploads we recommend to install the application locally. You can find the repository and installation instructions here. The model takes on average 3 to 5 seconds per image to classify. You will receive a unique identifier for each submission for future reference, please use it if you contact us regarding issues. Click here to get an example prediction.
Contact Us
K. Nolte, F. G. Sauer, R. LühkenBernhard-Nocht Institute for Tropical Medicine
Bernhard-Nocht-Straße 74
20359 Hamburg, Germany
