Adonis fucensis is herein described as a new species based on morphological and molecular analyses. It is endemic to one locality of the Central Apennines between Amplero and Fucino plains within the NATURA 2000 network in the SAC IT7110205 (Central Italy). The only discovered population is composed of 65 individuals and is at risk of extinction. The conservation status assessment according to IUCN categories and criteria is proposed and discussed. The new species belongs to A. sect. Adonanthe and is morphologically similar to A. volgensis (incl. A. transsilvanica), a species distributed in Hungary, Romania, Bulgaria, and Turkey as well as eastward to SW Siberia and Central Asia. Adonis fucensis can be distinguished from A. volgensis by larger cauline leaves, pentagonal with lobes lanceolate, larger stipules with more lobes and teeth, and larger flowers. Finally, an analytical key to Adonis species belonging to sect. Adonanthe distributed in Europe is presented.

Premise: The generation of morphological data in evolutionary, taxonomic, and ecological studies of plants using herbarium material has traditionally been a labor‐intensive task. Recent progress in machine learning using deep artificial neural networks (deep learning) for image classification and object detection has facilitated the establishment of a pipeline for the automatic recognition and extraction of relevant structures in images of herbarium specimens.Methods and Results: We implemented an extendable pipeline based on state‐of‐the‐art deep‐learning object‐detection methods to collect leaf images from herbarium specimens of two species of the genus Leucanthemum. Using 183 specimens as the training data set, our pipeline extracted one or more intact leaves in 95% of the 61 test images.Conclusions: We establish GinJinn as a deep‐learning object‐detection tool for the automatic recognition and extraction of individual leaves or other structures from herbarium specimens. Our pipeline offers greater flexibility and a lower entrance barrier than previous image‐processing approaches based on hand‐crafted features.