Papers session #2, 3D Web for Hyperconnected Applications
Authors
- Ha-Seong Kim, University of Suwon
- Myeong Won Lee, University of Suwon
Keywords. 3D object recognition, 3D machine learning, 3D deep learning, 3D training data, 3D data preprocessing
Abstract. In this paper, a method of recognizing a 3D object using a machine learning algorithm is described. 3D object data sets consisting of geometric polygons are analyzed by Keras, a deep learning API that learns composition rules of data sets. A 3D object can be recognized by applying a composition rule to the object. Data sets for various types of objects have been experimented with. 100 objects per shape were used to learn the rules and different objects were used for evaluating the rules. Eight types of 3D objects were experimented with. In addition, evaluation results for different numbers of 3D objects were compared.
TODO
- Link to calendar event via Session Title
- Display Featured Image
- Link to Presentation Slideset
- Link to Presentation and Demo Videos (if any)
- Link to Representative 3D (if any)
- Link to references and other assets (if any)