Multi-sensory based novel household object categorization system by using interactive behaviours
| Autor: | Haojun Guan, Jianwei Zhang |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
0301 basic medicine
Artificial neural network Computer science business.industry 3D single-object recognition Feature extraction Cognitive neuroscience of visual object recognition Pattern recognition Machine learning computer.software_genre Convolutional neural network 03 medical and health sciences 030104 developmental biology 0302 clinical medicine Categorization Mel-frequency cepstrum Artificial intelligence business Classifier (UML) computer 030217 neurology & neurosurgery |
| Zdroj: | ROBIO |
| Popis: | Human beings have an excellent ability which can form and recognise object categories. In this paper, a novel system of multimodal object recognition and categorization by performing interactive behaviours is introduced. Video clips are filmed as the raw input of the system. A dataset of 100 objects with 18 categories and five different interactions is used to evaluated the performance. The convolutional neural network is used to train the classifier and learn the categories. The result shows the highest, lowest and average recognition accuracies of every specific object in every category and the receiver operating characteristic for every category. The connection between the presented system and human cognitive system is discussed in the conclusion and future works. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|