Plant identification in an open-world (LifeCLEF 2016)

TL;DR

This paper discusses the 2016 LifeCLEF plant identification challenge, which evaluated large-scale, open-set recognition methods for identifying plant species from over 110,000 images, emphasizing robustness to unknown categories.

Contribution

It introduces an open-set recognition framework for plant identification and provides a comprehensive analysis of methods and results from the challenge.

Findings

Systems achieved improved accuracy on known species

Effective rejection of unknown species was demonstrated

Open-set recognition remains a key challenge in biodiversity monitoring

Abstract

The LifeCLEF plant identification challenge aims at evaluating plant identification methods and systems at a very large scale, close to the conditions of a real-world biodiversity monitoring scenario. The 2016-th edition was actually conducted on a set of more than 110K images illustrating 1000 plant species living in West Europe, built through a large-scale participatory sensing platform initiated in 2011 and which now involves tens of thousands of contributors. The main novelty over the previous years is that the identification task was evaluated as an open-set recognition problem, i.e. a problem in which the recognition system has to be robust to unknown and never seen categories. Beyond the brute-force classification across the known classes of the training set, the big challenge was thus to automatically reject the false positive classification hits that are caused by the unknown classes. This overview presents more precisely the resources and assessments of the challenge, summarizes the approaches and systems employed by the participating research groups, and provides an analysis of the main outcomes.