Paper Status Tracking
Contact us
[email protected]
Click here to send a message to me 3275638434
Paper Publishing WeChat

Article
Affiliation(s)

Institute of Computer Vision, Nanchang Hang Kong University, Nanchang, China

ABSTRACT

Flower Image Classification is a Fine-Grained Classification problem. The main difficulty of Fine-Grained Classification is the large inter-class similarity and the inner-class difference. In this paper, we propose a new algorithm based on Saliency Map and PCANet to overcome the difficulty. This algorithm mainly consists of two parts: flower region selection, flower feature learning. In first part, we combine saliency map with gray-scale map to select flower region. In second part, we use the flower region as input to train the PCANet which is a simple deep learning network for learning flower feature automatically, then a 102-way softmax layer that follow the PCANet achieve classification. Our approach achieves 84.12% accuracy on Oxford 17 Flowers dataset. The results show that a combination of Saliency Map and simple deep learning network PCANet can applies to flower image classification problem.

KEYWORDS

Saliency map, PCANet, deep learning, flower image classification.

Cite this paper

References

About | Terms & Conditions | Issue | Privacy | Contact us
Copyright © 2001 - David Publishing Company All rights reserved, www.davidpublisher.com
3 Germay Dr., Unit 4 #4651, Wilmington DE 19804; Tel: 1-323-984-7526; Email: [email protected]