Plant identification: man vs. machine LifeCLEF 2014 plant identification challenge

This paper reports a large-scale experiment aimed at evaluating how state-of-art computer vision systems perform in identifying plants compared to human expertise. A subset of the evaluation dataset used within LifeCLEF 2014 plant identification challenge was therefore shared with volunteers of dive...

Full description

Saved in:
Bibliographic Details
Published inMultimedia tools and applications Vol. 75; no. 3; pp. 1647 - 1665
Main Authors Bonnet, Pierre, Joly, Alexis, Goëau, Hervé, Champ, Julien, Vignau, Christel, Molino, Jean-François, Barthélémy, Daniel, Boujemaa, Nozha
Format Journal Article
LanguageEnglish
Published New York Springer US 01.02.2016
Springer Nature B.V
Springer Verlag
SeriesLifeCLEF 2014 plant identification challenge
Subjects
Analysis
Biodiversity
Biodiversity and Ecology
Botany
Collaboration
Computer Communication Networks
Computer Science
Computer Vision and Pattern Recognition
Consortia
Data Structures and Information Theory
Datasets
Environment and Society
Environmental Sciences
Flowers & plants
Identification systems
Image processing systems
Image retrieval
Life Sciences
Multimedia
Multimedia Information Systems
Plant sciences
Social networks
Special Purpose and Application-Based Systems
Studies
Taxonomy
Vegetal Biology
Vision systems
Visual plant identification
Image analysis
Human evaluation
Digital data
Online AccessGet full text

Cover

More Information
Summary:This paper reports a large-scale experiment aimed at evaluating how state-of-art computer vision systems perform in identifying plants compared to human expertise. A subset of the evaluation dataset used within LifeCLEF 2014 plant identification challenge was therefore shared with volunteers of diverse expertise, ranging from the leading experts of the targeted flora to inexperienced test subjects. In total, 16 human runs were collected and evaluated comparatively to the 27 machine-based runs of LifeCLEF challenge. One of the main outcomes of the experiment is that machines are still far from outperforming the best expert botanists at the image-based plant identification competition. On the other side, the best machine runs are competing with experienced botanists and clearly outperform beginners and inexperienced test subjects. This shows that the performances of automated plant identification systems are very promising and may open the door to a new generation of ecological surveillance systems.
ISSN:1380-7501
1573-7721
DOI:10.1007/s11042-015-2607-4