TLThéo Léger

Théo Léger

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Théo Léger has a total of 61 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Addendum to a New Genus and Species of Crambinae (Lepidoptera, Crambidae) from South-Western U.S.A., with New Insights into the Phylogeny of the Subfamily, Landry, B., T. Léger, J. Bilat and J. Gauthier, 2025, Proceedings of the Entomological Society of Washington 127(4): 719–732.

    by Bernard Landry, Théo Léger, Lars G. Crabo, Jérémy Gauthier

    Proceedings of the Entomological Society of Washington publishes research in entomology such as systematics, taxonomy, biology, ecology, and morphology.

  • Open Access

    High‐throughput information extraction of printed specimen labels from large‐scale digitization of entomological collections using a semi‐automated pipeline

    by Margot Belot, Joël Tuberosa, Leonardo Preuss, Olha Svezhentseva, Magdalena Claessen, Christian Bölling, Franziska Schuster, Théo Léger

    Natural history museums curate billions of insect specimens, representing an unparalleled record of biodiversity. Although large‐scale digitization has expanded access to specimen images, extracting label metadata remains a major bottleneck, typically requiring time‐intensive manual transcription. We developed ELIE (Entomological Label Information Extraction), a modular, semi‐automated pipeline that integrates computer vision methods (including convolutional neural networks), Optical Character Recognition (OCR), and clustering algorithms to streamline label data extraction. The workflow proceeds in three stages: (1) label detection and text‐type classification (printed vs. handwritten), (2) OCR‐based text extraction from printed labels using Tesseract or Google Vision, and (3) clustering of extracted text for deduplication and targeted human validation. Benchmarking across three institutional data sets demonstrated that ELIE accurately extracted and clustered up to 98% of printed labels, achieving 94% detection accuracy and reducing manual transcription effort by up to 87%. The pipeline markedly improves the efficiency of digitization workflows while maintaining high data integrity. By integrating AI‐driven automation with minimal human oversight, ELIE enables scalable, cross‐institutional digitization of entomological collections. Its implementation holds the potential to unlock large volumes of biodiversity data for research in ecology, systematics, and conservation worldwide.


  • Open Access

    KIEBIDS: A Modular Framework for Scalable Information Extraction from Written Records in Natural History Collections

    by Christian Bölling, Théo Léger, Joachim Snellings, Margot Belot, Franziska Schuster

    Natural history collections preserve invaluable records of biodiversity across time and space. Each specimen is typically accompanied by one or more labels documenting provenance, locality, and contextual data. Mobilizing this information is crucial for research on biodiversity change, biogeography, and taxonomy. To date, much of this data remains inaccessible for computational knowledge engineering approaches because manually processing and converting the sources into structured, interoperable data formats is a labor-intensive challenge due to the volume, heterogeneity, and complexity of the documents—and curatorial resources for fulfilling these tasks are generally insufficient. Artificial Intelligence (AI)-based methodologies can significantly accelerate this process and make it economically scalable. We present KIEBIDS*1, an open-source framework for specifying and executing AI-based workflows for information extraction from specimen label images. Following a linear data-pipeline architecture, workflows comprise five sequential functional steps for information extraction: image pre-processing (to prepare input images for subsequent analysis), layout analysis (to identify image regions that are relevant for information extraction), optical character recognition (to identify text on the syntactical level), semantic parsing (to identify text that references categories of interest), entity linking (to identify entities of interest mentioned in the text with authority records). image pre-processing (to prepare input images for subsequent analysis), layout analysis (to identify image regions that are relevant for information extraction), optical character recognition (to identify text on the syntactical level), semantic parsing (to identify text that references categories of interest), entity linking (to identify entities of interest mentioned in the text with authority records). Modularity and adaptability are central design principles for the framework's architecture. Each function can be realized by one or more modules that operate independently through file-based input and output, enabling substitution or extension as new technologies emerge. This ensures flexible adaptation to various information extraction goals or new data domains. In the current release, image pre-processing is implemented using the OpenCV framework with steps for resizing, grayscale conversion, noise reduction, and binarization. Layout analysis, based on the Segment Anything Model, identifies image regions that depict labels. Character recognition is implemented using two alternative modules. Besides EasyOCR, Moondream is used to leverage locally-deployable vision-language model (VLM) technology. Semantic parsing is implemented using spaCy and regular expressions, as rule-based parsing has proven efficient for syntactically well-defined entities, such as dates or coordinates, given the sparse context of label texts. Entity linking, in the current release, is realized for geographical place names using the GeoNames application programming interface (API). The input for a given workflow run consists of document images and configuration parameters. The configuration parameters encompass settings for the pipeline as a whole, such as location of input and output files and execution mode, the configurable settings for each functional step of the pipeline, e.g., models to be used, model parameters or the tag selection for the semantic tagging. settings for the pipeline as a whole, such as location of input and output files and execution mode, the configurable settings for each functional step of the pipeline, e.g., models to be used, model parameters or the tag selection for the semantic tagging. The workflow's output are PAGE-XML files containing image annotations, including the extracted and annotated text. Optionally, intermediate data and evaluation metrics can be assessed. Integrating seamlessly with Python codebases, Prefect is used for scheduling, monitoring, and graphical user interaction. By combining existing open frameworks rather than developing new components, the project leverages recent advances in computer vision and natural language processing to mobilize biodiversity data. Future developments will focus on improving user experience, integrating better models for handwritten text, and expanding semantic analysis capabilities. KIEBIDS' source code*2 is openly available and locally deployable with moderate hardware requirements.

  • A New Genus and Species of Crambinae (Lepidoptera Crambidae) from South-Western U.S.A., with New Insights into the Phylogeny of the Subfamily

    by Bernard Landry, Théo Léger, Julia Bilat, Jérémy Gauthier

    Nevadapteryx Landry, new genus (Crambidae; Crambinae) is described based on two new species also described here: N. albui Landry, new species and N. esmeraldensis Landry and Léger, new species. The genus is restricted in distribution to southern California and Nevada. The phylogenetic position of Nevadapteryx in the Ancylolomiini is ascertained based on a whole genome sequencing effort and a phylogenetic analysis of six genes compared with the available molecular data. A specimen each of Eufernaldia cadarella (Druce) and Hemiplatytes prosenes (Dyar) were also sequenced. Eufernaldia cadarella is recovered in the Ancylolomiini as sister to Mesolia incertella (Zincken), while Hemiplatytes prosenes is recovered as sister to Chilo quirimbellus Błeszyński and hence moved back to Chiloini.

  • Open Access

    High Throughput Information Extraction of Printed Specimen Labels from Large-Scale Digitization of Entomological Collections using a Semi-Automated Pipeline

    by Margot Belot, Joël Tuberosa, Leonardo Preuss, Olha Svezhentseva, Magdalena Claessen, Christian Bölling, Franziska Schuster, Théo Léger

    Natural history museums curate billions of insect specimens, forming a vast but underutilized resource for biodiversity research. While digitization efforts have increased the availability of high-resolution specimen images, extracting metadata from labels remains a major bottleneck, often requiring manual transcription. We developed a semi-automated pipeline, ELIE (Entomological Label Information Extraction), which combines computer vision, convolutional neural networks (CNNs), optical character recognition (OCR), and clustering algorithms to streamline label data extraction. Our pipeline operates in three stages: (1) label detection and classification (printed vs. handwritten), (2) OCR-based text extraction from printed labels using Tesseract or Google Vision, and (3) clustering of extracted text for human validation of outliers. Benchmarking on diverse datasets from multiple museum collections showed that our approach successfully extracted and clustered up to 98% of printed labels, significantly reducing manual effort. The pipeline improves efficiency in digitization workflows while maintaining high accuracy in label data capture. Our approach demonstrates the potential of integrating AI-driven methods with human validation to accelerate specimen digitization. By reducing manual transcription workload and enabling scalable extraction of insect label metadata, it unlocks biodiversity data for research in ecology, systematics, and conservation globally.

  • Open Access

    New and poorly known Pleurota Hübner, [1825] species from peninsular Spain, the Balearic Islands, and the Canary Islands (Lepidoptera: Oecophoridae, Pleurotinae)

    by Jukka Tabell, Martin Honey, Théo Leger, Marko Mutanen, Timo Nupponen, Pasi Sihvonen

    Four new Pleurota Hübner, [1825] species from peninsular Spain, one species from the Balearic Islands and one species from the Canary Islands are described: P. rondaensis Tabell & Nupponen, sp. nov., P. pyrenaella Tabell, sp. nov., P. balearica Tabell & Honey, sp. nov., P. malagaensis Tabell & Nupponen, sp. nov., P. grancanariella Tabell, sp. nov. and P. subnobilella Tabell, sp. nov. In addition, adults, and genitalia of seven poorly known Spanish Pleurota species are illustrated, most of them for the first time, and photos of several type specimens are presented. Lectotypes for P. protasella Staudinger, 1883, P. glitzella (Staudinger, 1883), P. pleurotella (Staudinger, 1871), P. sobriella (Staudinger, 1859) and P. nobilella Rebel, 1901 are designated. DNA barcodes of the aforementionedspecies are compared with those of all other Pleurotinae available to us in the BOLD database. Each of the species studied herein has a unique BIN (Barcode Index Number).


  • Taxonomic revision of the Crambinae (Lepidoptera, Pyralidae sensu lato) of the Galápagos Islands, Ecuador

    by Bernard Landry, Théo Léger

    The Crambinae (Lepidoptera, Pyralidae s. l.) of the Galápagos Islands, Ecuador are revised. Whereas only Argyria lacteella (Fabricius, 1794), Diatraea saccharalis (Fabricius, 1794), and Euchromius galapagosalis Capps, 1966 had previously been recorded from the archipelago, seven species are described as new: Mesolia christinae sp. nov., La florenciae sp. nov., La grisea sp. nov., La galapagensis sp. nov., La paquitae sp. nov, La wagneuri sp. nov., and Parapediasia galapagensis sp. nov., thus bringing the total number of Crambinae species recorded from the Galapagós Islands to ten. Euchromius galapagosalis and the seven new species are presumed endemic to the Galápagos. The habitus and genitalia of all ten species are illustrated.


  • The riodinid taxa described by Rudolf Emil Mell (Lepidoptera, Papilionoidea, Riodinidae), with notes on related ones

    by Si-Yao Huang, Yutaka Inayoshi, Théo Léger, Marianne Espeland

    The two riodinid taxa described by Rudolf Emil Mell were reviewed. Lectotypes have been designated for Sospita sobrina Mell, 1923 and Hipporion chauchowensis Mell, 1923. Abisara freda Bennett, 1957 syn. n. and A. freda daliensis Sugiyama, 1992 syn. n. are synonymized with A. sobrina (Mell, 1923) and Polycaena chauchowensis pallidior Forster, 1951 syn. n. is synonymized with P. chauchowensis (Mell, 1923). The adult and genitalia of the lectotypes and related specimens of the aforementioned taxa are illustrated.

  • Open Access

    First pyraloid (Insecta, Lepidoptera) caterpillar from Dominican amber

    by M. Alma Solis, Théo Léger, Christian Neumann

    Only three fossils in the Pyraloidea (Insecta, Lepidoptera) have been confirmed to date, two adults and one larva. The first confirmed larva, in the subfamily Pyraustinae (Crambidae), was described from Baltic amber. Recently, another pyraloid larva from Dominican amber has come to our attention. We describe this second confirmed larval fossil as Penestola wichardi Solis, Léger & Neumann, sp. nov., based on larval morphological characters, such as setal patterns and the shape of their sclerotized bases or pinacula, and place it in the subfamily Spilomelinae (Crambidae).