Local binary pattern based features for sign language recognition
| Autor: | Miloš Železný, Marek Hrúz, Jana Trojanova |
|---|---|
| Rok vydání: | 2011 |
| Předmět: |
Landmark
Local binary patterns Computer science Geometric moments business.industry Speech recognition Detector znaková řeč Model fitting Pattern recognition Sign language Computer Graphics and Computer-Aided Design Robustness (computer science) Active shape model local binary patterns sign language Computer Vision and Pattern Recognition Artificial intelligence business |
| Zdroj: | Pattern Recognition and Image Analysis. 21:398-401 |
| ISSN: | 1555-6212 1054-6618 |
| DOI: | 10.1134/s1054661811020416 |
| Popis: | In this paper we focus on appearance features describing the manual component of Sign Language particularly the Local Binary Patterns. We compare the performance of these features with geometric moments describing the trajectory and shape of hands. Since the non-manual component is also very important for sign recognition we localize facial landmarks via Active Shape Model combined with Landmark detector that increases the robustness of model fitting. We test the recognition performance of individual features and their combinations on a database consisting of 11 signers and 23 signs with several repetitions. Local Binary Patterns outperform the geometric moments. When the features are combined we achieve a recognition rate up to 99.75% for signer dependent tests and 57.54% for signer independent tests. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink