Object Recognition Using Keras with Backend Tensor Flow
-
2018-07-04 https://doi.org/10.14419/ijet.v7i3.6.14977
-
Machine Learning, Deep neural networks, Tensor flow, Keras Library -
Abstract
Now a day’s Machine Learning Plays an important role in computer vision, object recognition and image classification. Recognizing objects in images is an interesting thing, this recognization can be done easily by human beings but the computer cannot. The Problem with traditional neural networks is object recognition. So, to avoid difficulties in recognition of objects in images the deep neural networks especially Tensor flow under Keras Library is used and it will improve the Accuracy while recognizing objects. In this paper we present object recognition using Keras Library with backend Tensor flow.
Â
-
References
[1] https://elitedatascience.com/learn-machine-learning#what
[2] https://www.datanami.com/2017/01/30/deep-learning-now/
[3] https://elitedatascience.com/python-deep-learning-libraries#keras
[5] https://www.tensorflow.org/install/install_java
[6] https://machinelearningmastery.com/introduction-python-deep-learning-library-keras/
[7] https://elitedatascience.com/keras-tutorial-deep-learning-in-python.
[8] Tensor Flow, Available online: https://www.tensorflow.org.
[9] B. Frederic, P. Lamblin, R. Pascanu et al., “Theano: new features and speed improvements,†in Deep Learning and Unsupervised Feature Learning NIPS 2012 Workshop, 2012, http://deeplearning.net/software/theano/.
[10] Athanasius Voulodimos, Nikolaos Doulamis, Anastasias Doulamis, and Eftychios Protopapadakis, “Deep Learning for Computer Vision: A Brief Review,†Computational Intelligence and Neuroscience, vol. 2018, Article ID 7068349, 13 pages, 2018. doi:10.1155/2018/7068349.
-
Downloads
-
How to Cite
Bandi, R., & Amudhavel, J. (2018). Object Recognition Using Keras with Backend Tensor Flow. International Journal of Engineering & Technology, 7(3.6), 229-233. https://doi.org/10.14419/ijet.v7i3.6.14977Received date: 2018-07-02
Accepted date: 2018-07-02
Published date: 2018-07-04