Survey on Image Dimensionality Reduction Using Deep Learning Techniques

  • Authors

    • K M. Monica
    • G Bindu
    • S Sridevi
    2018-08-15
    https://doi.org/10.14419/ijet.v7i3.27.17755
  • Image, dimensional reduction, deep learning, real time application.

  • Abstract

    Images provide rich information. With reference to the data set which may be related or unrelated in nature, locates step by step, a wide range of application and its attributes through capturing mechanism by sensing the suitable technologies. On the other hand, it also creates a huge quantity of data which may be relevant, irrelevant or redundant in nature and it is used for detailed task of the image.  Also, Many brings a lot of problems such as increase in computational time of image, density of image and range of mapping of data, semantics of the data set and also it also there is a scope of huge amount of labeled data for the process of training to the new environment setup.  Mostly, this is not easy and costly for users to obtain sufficient training models in several application modules.  This research paper deals with these problems by exploring the more classical dimension reduction algorithms with deep knowledge for supporting communities.

      

  • References

    1. [1] Zhong G, Wang LN, Ling X & Dong J, “An overview on data representation learning: From traditional feature learning to recent deep learningâ€, The Journal of Finance and Data Science, Vol.2, No.4,(2016), pp.265-278.

      [2] Xie H, Li J & Xue H, “A survey of dimensionality reduction techniques based on random projectionâ€, arXiv preprint arXiv:1706.04371, (2017).

      [3] Saikia S, Fidalgo E, Alegre E & Fernández-Robles L, “Object detection for crime scene evidence analysis using deep learningâ€, International Conference on Image Analysis and Processing, (2017), pp.14-24.

      [4] Surendar, A. (n.d.). Short communication: Role of Microbiology in the Pharmaceutical &Medical Device. 433| International Journal of Pharmaceutical Research, 10(3).

      [5] Lee JG, Jun S, Cho YW, Lee H, Kim GB, Seo JB & Kim N, “Deep learning in medical imaging: general overviewâ€, Korean journal of radiology, Vol.18, No.4,(2017), pp.570-584.

      [6] Murinto & Dyah NR, “Dimensionality Reduction using Hybrid Support Vector Machine and Discriminant Independent Component Analysis for Hyperspectral Imageâ€, International Journal of Advanced Computer Science and Applications, Vol.8, No.11,(2017), pp.601-605.

      [7] Su J, Yi D, Liu C, Guo L & Chen WH, “Dimension reduction aided hyperspectral image classification with a small-sized training dataset: experimental comparisonsâ€, Sensors, Vol.17, No.12, (2017).

      [8] B Kassimbekova, G Tulekova, V Korvyakov (2018). Problems of development of aesthetic culture at teenagers by means of the Kazakh decorative and applied arts. Opción, Año 33. 170-186

  • Downloads

  • How to Cite

    M. Monica, K., Bindu, G., & Sridevi, S. (2018). Survey on Image Dimensionality Reduction Using Deep Learning Techniques. International Journal of Engineering & Technology, 7(3.27), 179-181. https://doi.org/10.14419/ijet.v7i3.27.17755

    Received date: 2018-08-17

    Accepted date: 2018-08-17

    Published date: 2018-08-15