@article{fdi:010095714,
  title = {{T}owards a deep learning-powered herbarium image analysis platform},
  author = {{S}klab, {Y}oucef and {A}riaout {S}klab, {H}anane and {B}oujydah, {Y}. and {Q}acami, {Y}. and {P}rifti, {E}di and {Z}ucker, {J}ean-{D}aniel and {V}ignes {L}ebbe, {R}. and {C}henin, {E}ric},
  editor = {},
  language = {{ENG}},
  abstract = {{G}lobal digitization efforts have archived millions of specimen scans worldwide in herbarium collections, which are essential for studying plant evolution and biodiversity.



{R}e{C}ol{N}at hosts, at present, over 10 million images. {H}owever, analyzing these datasets poses crucial challenges for botanical research. {T}he application of deep learning in



biodiversity analyses, particularly in analyzing herbarium scans, has shown promising results across numerous tasks ({A}riouat et al. 2023, {A}riouat et al. 2024, {G}room et al. 2023,



{S}ahraoui et al. 2023).},
  keywords = {},
  booktitle = {},
  journal = {{B}iodiversity {I}nformation {S}cience and {S}tandards},
  volume = {8},
  numero = {},
  pages = {e135629 [4 ]},
  ISSN = {2535-0897},
  year = {2024},
  DOI = {10.3897/biss.8.135629},
  URL = {https://www.documentation.ird.fr/hor/fdi:010095714},
}