Fruits Classification from Image using MPEG-7 Visual Descriptors and Extreme Learning Machine
| Main Authors: | Siswantoro, Joko, Arwoko, Heru, Siswantoro, M. Z. F. N |
|---|---|
| Format: | Proceeding PeerReviewed application/pdf |
| Bahasa: | eng |
| Terbitan: |
, 2020
|
| Subjects: | |
| Online Access: |
http://repository.ubaya.ac.id/38789/ https://ieeexplore.ieee.org/document/9315523 |
Daftar Isi:
- Fruit image classification has several applications and can be used as alternative to traditionally fruit classification performed by human expert. This paper aims to propose fruits classification method from image using extreme learning machine (ELM), MPEG-7 visual descriptors, and principal component analysis (PCA). The optimum parameters of ELM and PCA were determined using grid search optimization. The best classification performance of 97.33% has been achieved in classifying Indonesian fruit images consisted of 15 classes. By applying the ensemble of ELMs, the classification accuracy was increased to 98.03%. This result shows that the proposed method produces high classification performance.