Image Classification Using TensorFlow
Deep learning (DL) is a process that consists of a set of methods which classifies the raw data into meaningful information fed into the machine. DL performs classification tasks directly from sound, text, and images. One of the famous algorithms for classification of images in DL is convolutional neural networks (CNN). In this research, we tested DL model for image recognition using TensorFlow from Dockers software. We received 99% accurate to identify the test image. The system configuration used for this research includes Ubuntu 16.04, Python 2.7, TensorFlow 1.9, and Google image set (Fatkun Batch Download Image: Google, Google, chrome.google.com/webstore/detail/fatkun-batch-download-ima/nnjjahlikiabnchcpehcpkdeckfgnohf).
This work was supported by the AFRL Minority Leaders Research Collaboration Program, contract FA8650-13-C-5800. The authors greatly acknowledge AFRL/RY for their assistance in this work.
- 1.Fatkun Batch Download Image: Google, Google, chrome.google.com/webstore/detail/fatkun-batch-download-ima/nnjjahlikiabnchcpehcpkdeckfgnohf
- 2.Neural Networks: Artificial Intelligence: A Modern Approach, by Stuart Jonathan. Russell and Peter Norvig, pp. 736–748. Prentice Hall Pearson Education International (2003)Google Scholar
- 3.TensorFlow: TensorFlow, www.tensorflow.org/
- 4.Wasserman, P.D.: Neural Computing: Theory and Practice. Van Nostrand Reinhold, New York (1989)Google Scholar
- 5.MarkDaoust: Tensorflow-flow-poets-2, (2018). https://github.com/googlecodelabs/tensorflow-for-poets-2
- 6.Kang, N.: Multi-Layer Neural Networks with Sigmoid Function – Deep Learning for Rookies. https://towardsdatascience.com/multi-layer-neural-networks-with-sigmoid-function-deep-learning-for-rookies-2-bf464f09eb7f
- 9.Goel, B.: Developments in the field of natural language processing. Int. J. Adv. Res. Comput. Sci. 8, (2017)Google Scholar
- 12.Vaezipour, A., Mosavi, A., Seigerroth, U.: Machine learning integrated optimization for decision making. 26th Europian Conference on Operational Research, Rome (2013)Google Scholar
- 13.Bannister, A.: Biometrics and AI: how face sentinel evolves 13 times faster thanks to deep learning, Editor, IFSEC Global (September 13, 2016)Google Scholar
- 15.Mo, D.: A survey on deep learning: one small step toward AI, https://daisypodcast.files.wordpress.com/2014/01/mo.pdf (2012), pp. 1–16
- 16.Glorot, X., Bordes, A. et. al.: Domain adaptation for large-scale sentiment classification: a deep learning approach, Proceedings of the 28th International conference on international conference on machine learning (ICML), (July 2, 2011), pp. 513–520Google Scholar