loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Abdelaziz Triki 1 ; Bassem Bouaziz 1 ; Walid Mahdi 2 ; 1 and Jitendra Gaikwad 3

Affiliations: 1 MIRACL/CRNS, University of Sfax, Sfax, Tunisia ; 2 College of Computers and Information Technology, Taif University, Saudi Arabia ; 3 Friedrich Schiller University Jena, German Centre for Integrative Biodiversity Research (iDiv) Halle-Jena-Leipzig, Leipzig, Germany

Keyword(s): Functional Traits, Digitized Plant Specimens, Deep Learning, Improved YOLO V3, Object Detection, Herbarium Haussknecht.

Abstract: Automatic measurement of functional trait data from digitized herbarium specimen images is of great interest as traditionally, scientists extract such information manually, which is time-consuming and prone to errors. One challenging task in the automated measurement process of functional traits from specimen images is the existence of other objects such as scale-bar, color pallet, specimen label, envelopes, bar-code and stamp, which are mostly placed at different locations on the herbarium-mounting sheet and require special detection method. To detect automatically all these objects, we train a model based on an improved YOLO V3 full-regression deep neural network architecture, which has gained obvious advantages in both speed and accuracy through capturing deep and high-level features. We made some improvements to adjust YOLO V3 for detecting object from digitized herbarium specimen images. A new scale of feature map is added to the existing scales to improve the detection effect o n small targets. At the same time, we adopted the fourth detection layer by a 4* up-sampled layer instead of 2* to get a feature map with higher resolution deeper level. The experimental results indicate that our model performed better with mAP-50 of 93.2% compared to 90.1% mean IoU trained by original YOLO V3 model on the test set. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.118.208.127

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Triki, A. ; Bouaziz, B. ; Mahdi, W. and Gaikwad, J. (2020). Objects Detection from Digitized Herbarium Specimen based on Improved YOLO V3. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP; ISBN 978-989-758-402-2; ISSN 2184-4321, SciTePress, pages 523-529. DOI: 10.5220/0009170005230529

@conference{visapp20,
author={Abdelaziz Triki and Bassem Bouaziz and Walid Mahdi and Jitendra Gaikwad},
title={Objects Detection from Digitized Herbarium Specimen based on Improved YOLO V3},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP},
year={2020},
pages={523-529},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009170005230529},
isbn={978-989-758-402-2},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP
TI - Objects Detection from Digitized Herbarium Specimen based on Improved YOLO V3
SN - 978-989-758-402-2
IS - 2184-4321
AU - Triki, A.
AU - Bouaziz, B.
AU - Mahdi, W.
AU - Gaikwad, J.
PY - 2020
SP - 523
EP - 529
DO - 10.5220/0009170005230529
PB - SciTePress