How Do You Tell a Blackbird from a Crow?
Authors:
- Thomas BergTBThomas Berg
- Peter N. BelhumeurPBPeter N. Belhumeur
- 1 December 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 9-16
Abstract
How do you tell a blackbird from a crow? There has been great progress toward automatic methods for visual recognition, including fine-grained visual categorization in which the classes to be distinguished are very similar. In a task such as bird species recognition, automatic recognition systems can now exceed the performance of non-experts - most people are challenged to name a couple dozen bird species, let alone identify them. This leads us to the question, "Can a recognition system show humans what to look for when identifying classes (in this case birds)?" In the context of fine-grained visual categorization, we show that we can automatically determine which classes are most visually similar, discover what visual features distinguish very similar classes, and illustrate the key features in a way meaningful to humans. Running these methods on a dataset of bird images, we can generate a visual field guide to birds which includes a tree of similarity that displays the similarity relations between all species, pages for each species showing the most similar other species, and pages for each pair of similar species illustrating their differences.Keywords
This publication has 16 references indexed in Scilit:
- The global diversity of birds in space and timeNature, 2012
- Face-recognition-based dog-breed classification using size and position of each local part, and PCA2012
- Data-driven visual similarity for cross-domain image matchingACM Transactions on Graphics, 2011
- Multiclass recognition and part localization with humans in the loop2011
- Interactively building a discriminative vocabulary of nameable attributes2011
- Learning Models for Object Recognition from Natural Language Descriptions2009
- Automated Flower Classification over a Large Number of Classes2008
- Interactive Tree Of Life (iTOL): an online tool for phylogenetic tree display and annotationBioinformatics, 2006
- Image region entropy2005
- Objects, parts, and categories.Journal of Experimental Psychology: General, 1984