Detection of Vehicle Manufacture Logos Using Contextual Information
| Autor: | Wenting Lu, Honggang Zhang, Jun Guo, Kunyan Lan |
|---|---|
| Rok vydání: | 2010 |
| Předmět: |
ComputingMethodologies_PATTERNRECOGNITION
Discriminative model Computer science Local binary patterns business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Contextual information Scale-invariant feature transform Computer vision Artificial intelligence Logos Bible Software business License |
| Zdroj: | Computer Vision – ACCV 2009 ISBN: 9783642123030 ACCV (2) |
| DOI: | 10.1007/978-3-642-12304-7_51 |
| Popis: | Besides the decorative purposes, vehicle manufacture logos can provide rich information for vehicle verification and classification in many applications such as security and information retrieval. Detection and recognition of vehicle manufacture logos are, however, very challenging because they might lack of discriminative features themselves. In this paper, we propose a method to detect vehicle manufacture logos using contextual information, i.e., the information of surrounding objects near vehicle manufacture logos such as license plates, headlights, and grilles. The experimental results demonstrate that the proposed method is more effective and robust than other methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|