MorphoCluster: Efficient Annotation of Plankton Images by Clustering.

Schröder, Simon-Martin , Kiko, Rainer and Koch, Reinhard (2020) MorphoCluster: Efficient Annotation of Plankton Images by Clustering. Open Access Sensors, 20 (11). Art.Nr. 3060. DOI 10.3390/s20113060.

[img]
Preview
Text
sensors-20-03060.pdf - Published Version
Available under License Creative Commons: Attribution 4.0.

Download (2454Kb) | Preview
[img]
Preview
Text
sensors-20-03060-s001.pdf - Supplemental Material
Available under License Creative Commons: Attribution 4.0.

Download (97Kb) | Preview

Supplementary data:

Abstract

In this work, we present MorphoCluster, a software tool for data-driven, fast, and accurate annotation of large image data sets. While already having surpassed the annotation rate of human experts, volume and complexity of marine data will continue to increase in the coming years. Still, this data requires interpretation. MorphoCluster augments the human ability to discover patterns and perform object classification in large amounts of data by embedding unsupervised clustering in an interactive process. By aggregating similar images into clusters, our novel approach to image annotation increases consistency, multiplies the throughput of an annotator, and allows experts to adapt the granularity of their sorting scheme to the structure in the data. By sorting a set of 1.2 M objects into 280 data-driven classes in 71 h (16 k objects per hour), with 90% of these classes having a precision of 0.889 or higher. This shows that MorphoCluster is at the same time fast, accurate, and consistent; provides a fine-grained and data-driven classification; and enables novelty detection.

Document Type: Article
Keywords: machine learning; deep learning; clustering; plankton image classification; marine image recognition; marine image annotation
Research affiliation: Kiel University > Kiel Marine Science
OceanRep > The Future Ocean - Cluster of Excellence
OceanRep > SFB 754
OceanRep > GEOMAR > FB3 Marine Ecology > FB3-EOE-B Experimental Ecology - Benthic Ecology
Refereed: Yes
Open Access Journal?: Yes
DOI etc.: 10.3390/s20113060
ISSN: 1424-8220
Related URLs:
Projects: Future Ocean, SFB754, Make our Planet Great Again
Date Deposited: 18 Aug 2020 09:55
Last Modified: 18 Aug 2020 09:55
URI: http://oceanrep.geomar.de/id/eprint/50344

Actions (login required)

View Item View Item

Document Downloads

More statistics for this item...