A Flower Image Classification Algorithm Based on Saliency Map and PCANet

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.