Plant leaves morphological categorization with shared nearest neighbours clustering
- 2 November 2012
- conference paper
- conference paper
- Published by Association for Computing Machinery (ACM) in Proceedings of the 1st ACM International Workshop on Cyber-Physical Systems for Smart Water Networks
Abstract
This paper presents an original experiment aimed at evaluating if state-of-the-art visual clustering techniques are able to automatically recover morphological classifications built by the botanists themselves. The clustering phase is based on a recent Shared-Nearest Neighbours (SNN) clustering algorithm, which allows to combine effectively heterogeneous visual information sources at the category level. Each resulting cluster is associated with an optimal selection of visual similarities, allowing to discover diverse and meaningful morphological categories even if we use a blind set of visual sources as input. Experiments are performed on ImageCLEF 2011 plant identification dataset, that was specifically enriched in this work with morphological attributes tags (annotated by expert botanists). The results are very promising, since all clusters discovered automatically can be easily matched to one node of the morphological tree built by the botanists.Keywords
This publication has 5 references indexed in Scilit:
- Visual-based plant species identification from crowdsourced dataPublished by Association for Computing Machinery (ACM) ,2011
- Multi-source shared nearest neighbours for multi-modal image clusteringMultimedia Tools and Applications, 2010
- New local descriptors based on dissociated dipolesPublished by Association for Computing Machinery (ACM) ,2007
- A Fast Matching Method for Color Uncalibrated Images using Differential InvariantsPublished by British Machine Vision Association and Society for Pattern Recognition ,1998
- Random sample consensusCommunications of the ACM, 1981