Distribution Distance Measures Applied to 3-D Object Recognition – A Case Study
| Autor: | Michael Nölle |
|---|---|
| Rok vydání: | 2003 |
| Předmět: |
Computer science
business.industry Pattern recognition (psychology) Feature (machine learning) Cognitive neuroscience of visual object recognition Probability distribution Image processing Computer vision Artificial intelligence Object (computer science) Divergence (statistics) business Distance measures |
| Zdroj: | Lecture Notes in Computer Science ISBN: 9783540408611 DAGM-Symposium |
| DOI: | 10.1007/978-3-540-45243-0_12 |
| Popis: | In this paper we analyse dissimilarity measures for probability distributions which are frequently used in the area of pattern recognition, image processing, -indexing and registration, amongst others. Namely χ 2, Jenson-Shannon divergence, Fidelity and Trace are discussed. We use those measures to tackle the task of recognising three dimensional objects from two dimensional images. The object reference model is defined by (several) feature distributions derived from multiple two dimensional views of each object. The experiments performed on the Columbia Object Image Library indicate that derivatives of Fidelity used as distance measures perform well in terms of recognition rate. If enough views can be provided for modelling (roughly one view per 20°-30°), up to a 100% recognition rate is achievable. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|