A Data Mining Approach for Species Co-occurrence Prediction
A Framework for Efficient Matching of Large-Scale Metadata Models
ADOnIS: An ontology-based information system providing seamless integration of structured and unstructured data
BioOntoVis: An Ontology Visualization Tool
Combined Features for Content Based Image Retrieval: A Comparative Study
Combining P-Plan and the REPRODUCE-ME Ontology to Achieve Semantic Enrichment of Scientific Experiments using Interactive Notebooks
Comparison and Evaluation of Ontologies for Units of Measurement
Convective excitation of inertial modes in binary neutron star mergers
Holistic Multiple Ontologies Merging
Issues and Suggestions for the Development of a Biodiversity Data Visualization Support Tool
Ontology ABox Comparison
Proceedings of the ‘10th International Conference on Ecological Informatics: translating ecological data into knowledge and decisions in a rapidly changing world
ProvBook: Provenance-based Semantic Enrichment of Interactive Notebooks for Reproducibility
Querying Heterogeneous Data in an In-situ Unified Agile System
Refined Methodology for Accurately Detecting Objects from Digitized Herbarium Specimens
Research data management in action – demonstrating the full range of features of the BEXIS 2 platform
Specimen-GT tool: Ground Truth Annotation tool for herbarium Specimen images
The Story of an Experiment:A Provenance-based Semantic Approach towards Research Reproducibility
Towards an Ecological Trait-data Standard
Towards FAIR data in Biodiversity Exploratories project
TraitEx: tool for measuring morphological functional traits from digitized herbarium specimens
Visrepo: A Centralized and Open Source Visualization Repository and Knowledgebase
Refined Methodology for Accurately Detecting Objects from Digitized Herbarium Specimens
Title: | Refined Methodology for Accurately Detecting Objects from Digitized Herbarium Specimens |
---|---|
Authors: | Triki, Abdelaziz; Bouaziz, Bassem; Gaikwad, Jitendra |
Source: | https://icei2018.uni-jena.de/ |
Place: | Jena, Germany |
Date: | 2018-12-20 |
Type: | Poster |
Abstract: |
There are global initiatives such as TRY trait database that are making efforts to minimize the paucity of functional trait data. The herbarium specimens provide valuable information on functional traits including length, width, and size of leaves and petiole length. Traditionally, scientists extract such information manually, which is time consuming and prone to errors. To overcome these limitations, worldwide scientists are applying computer vision techniques to automatically extract trait data from digitized specimen images. However, to extract the trait values pre-requisite is to accurately detect objects present on the specimen images. In the Managing Multimedia Data for Science (MAMUDS) project, we have refined a deep learning technique, which is efficiently able to detect objects from the specimen images provided by the herbarium Haussknecht, as compared to other state-of-the-art techniques. The herbarium Haussknecht in Germany provide access to more than 30000 scanned type specimen images to researchers and public. However, the varied placement and diversity of objects such as plant specimen, scale bar, color pallet, specimen label, envelope, barcode and stamp on the specimen sheet make the task of automatic detection challenging. To address this challenge, we have developed a refined methodology RefYOLO, which is based on the pioneer object detection system called You Only Look Once (YOLO). The refinement was done by editing the activation function of VGG16 model using the Parametric ReLu (PReLU). In our study, we observed that YOLO and other state-of-the-art techniques such as Region-based Convolutional Network (RCNN) and its variants are unable to robustly detect objects from digitized specimen images. RefYOLO efficiently localizes object classes located in specimen images and scales by encoding contextual feature information about classes such as shape, contours and their appearance. After training, the performance of RefYOLO was enhanced using Average-Max pooling method (AM-PM). Overall, RefYOLO provides higher detection accuracy and need less processing time. |
URL: | https://doi.org/10.22032/dbt.37908 |