Ott, Tankred and Lautenschlager, Ulrich (2022) GinJinn2: Object detection and segmentation for ecology and evolution. METHODS IN ECOLOGY AND EVOLUTION, 13 (3). pp. 603-610. ISSN 2041-210X, 2041-2096
Full text not available from this repository. (Request a copy)Abstract
Collection and preparation of empirical data still represent one of the most important, but also expensive steps in ecological and evolutionary/systematic research. Modern machine learning approaches, however, have the potential to automate a variety of tasks, which until recently could only be performed manually. Unfortunately, the application of such methods by researchers outside the field is hampered by technical difficulties. Here, we present GinJinn2, a user-friendly toolbox for deep learning-based object detection and instance segmentation on image data. Besides providing a convenient command-line interface to existing software libraries, it comprises several additional tools for data handling, pre- and postprocessing, and building advanced analysis pipelines. We demonstrate the application of GinJinn2 for biological purposes using four exemplary analyses, namely the evaluation of seed mixtures, detection of insects on glue traps, segmentation of stomata and extraction of leaf silhouettes from herbarium specimens. GinJinn2, by providing a coding-free environment, will enable users with a primary background in biology to apply deep learning-based methods for object detection and segmentation in order to automate feature extraction from image data.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | IMAGE; automation; computer vision; deep learning; instance segmentation; machine learning; morphometrics; object detection; trait extraction |
| Subjects: | 500 Science > 590 Zoological sciences |
| Divisions: | Biology, Preclinical Medicine > Institut für Pflanzenwissenschaften > Group Plant Systematics and Evolution (Prof. Dr. Christoph Oberprieler) |
| Depositing User: | Dr. Gernot Deinzer |
| Date Deposited: | 27 Nov 2023 06:38 |
| Last Modified: | 27 Nov 2023 06:38 |
| URI: | https://pred.uni-regensburg.de/id/eprint/56798 |
Actions (login required)
 |
View Item |
