Dog Breed Identification with Fine Tuning of Pre-Trained Models
B. Vijaya Kumar1, K. Bhavya2
1Dr. B. Vijaya Kumar, Professor & Head, Department of Computer Science & Engineering, Vidya Jyothi Institute of Technology VJIT, Hyderabad (Telangana), India.
2K. Bhavya, PG Scholar, Department of CSE, Vidya Jyothi Institute of Technology VJIT, Hyderabad (Telangana), India.
Manuscript received on 19 October 2019 | Revised Manuscript received on 25 October 2019 | Manuscript Published on 02 November 2019 | PP: 3677-3680 | Volume-8 Issue-2S11 September 2019 | Retrieval Number: B14640982S1119/2019©BEIESP | DOI: 10.35940/ijrte.B1464.0982S1119
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Dog Breed identification is a specific application of Convolutional Neural Networks. Though the classification of Images by Convolutional Neural Network serves to be efficient method, still it has few drawbacks. Convolutional Neural Networks requires a large amount of images as training data and basic time for training the data and to achieve higher accuracy on the classification. To overcome this substantial time we use Transfer Learning. In computer vision, transfer learning refers to the use of a pre-trained models to train the CNN. By Transfer learning, a pre-trained model is trained to provide solution to classification problem which is similar to the classification problem we have. In this project we are using various pre-trained models like VGG16, Xception, InceptionV3 to train over 1400 images covering 120 breeds out of which 16 breeds of dogs were used as classes for training and obtain bottleneck features from these pre-trained models. Finally, Logistic Regression a multiclass classifier is used to identify the breed of the dog from the images and obtained 91%, 94%,95% validation accuracy for these different pre-trained models VGG16, Xception, InceptionV3.
Keywords: Image Classification, Transfer Learning, Convolutional Neural Network, Vgg16, Xception, Inception-V3.
Scope of the Article: Artificial Intelligent Methods, Models, Techniques