Flower classification via convolutional neural network

In this paper, we address the problem of natural flower classification. It is a challenging task due to the non-rigid deformation, illumination changes, and inter-class similarity. We build a large dataset of flower images in the wide with 79 categories and propose a novel framework based on convolutional neural network (CNN) to solve this problem. Unlike other methods using hand-crafted visual features, our method utilizes convolutional neural network to automatically learn good features for flower classification. The neural network consists of five convolutional layers where small receptive fields are adopted, some of which are followed by max-pooling layers, and three fully-connected layers with a final 79-way softmax. Our approach achieves 76.54% classification accuracy on our challenging flower dataset. Moreover, test our algorithm on the Oxford 102 Flowers dataset. It outperforms the previous known methods and achieves 84.02% classification accuracy. Experimental results on a well-known dataset and our own dataset demonstrate that our method is quite effective in flower classification.