Pre-trained Deep Neural Network Model of VGG 16 for Flower Image Classification

  • Unique Paper ID: 160729
  • Volume: 10
  • Issue: 1
  • PageNo: 1018-1025
  • Abstract:
  • Flowers are everywhere around us. They can feed insects, birds, animals and humans. They are also used as medicines for humans and some animals. A good understanding of flowers is essential to help in identifying new or rare species when came across. This will help the medicinal industry to improve. As the classification of flower species is an important task, it is already in research and many different approaches have been developed. Currently, flower image classification methods can be divided into two categories such as methods based on manual feature extraction and methods based on deep learning to automatically extract features. Manual feature extraction methods mostly extract colour features, texture features, and shape features of images, and combine them with machine learning algorithms for classification. Aiming at the problem that the classification accuracy of the traditional flower classification method is low and the deep neural network requires a large amount of original data. In this work, we proposed a model based on fine-tuning of a pre-trained deep learning model, called VGG16. The experimental results on the international public flower recognition dataset, Oxford flower-102 dataset, show that by enhancing the original data, the accuracy of the network's recognition and classification of flowers is improved. At the same time, the model proposed in this work is superior to other traditional network models, with higher recognition accuracy and robustness.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 10
  • Issue: 1
  • PageNo: 1018-1025

Pre-trained Deep Neural Network Model of VGG 16 for Flower Image Classification

Related Articles