SavedAdd your journal

Journals / Karaelmas Fen ve Mühendislik Dergisi / 2018 / Cilt: 8 - Sayı: 2

Usage of artificial neural networks method for image enhancement of reconstructed image in digital holography

Sayısal Holografide Geri Elde Edilen Görüntünün İyileştirilmesi İçin Yapay Sinir Ağları Metodunun Kullanılması

GÜLHAN USTABAŞ KAYA
ZEHRA SARAÇ
Pages
561–569
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

In addition, these relative error figures are supported with error histogram obtained from MATLAB neural network fitting toolbox.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The aim of paper is to use an artificial neural network approach for enhancement of three dimensional image reconstructed in digital holography.
📊
Key Findings & Data:An artificial neural network method based on Gerchberg-Saxton algorithm is implemented to reduce the noise and increase the brightness of this image.
💡
Conclusion & Impact:In addition, these relative error figures are supported with error histogram obtained from MATLAB neural network fitting toolbox.
🔬Design:Research Article
📍Scope:Comprehensive Sample
⚙️Variables:Yapay sinir ağları · Sayısal holografi · Gerchberg-Saxton algoritması

Abstract

The aim of paper is to use an artificial neural network approach for enhancement of three dimensional image reconstructed in digital holography. An artificial neural network method based on Gerchberg-Saxton algorithm is implemented to reduce the noise and increase the brightness of this image. The results of proposed method have been presented by a relative error. In addition, these relative error figures are supported with error histogram obtained from MATLAB neural network fitting toolbox.

Özet

Bu makalenin amacı, yapay sinir ağları yaklaşımını sayısal holografide hologramdan geri elde edilen üç boyutlu görüntünün iyileştirilmesi için kullanmaktır. Gerchberg-Saxton algoritmasına dayalı yapay sinir ağları metodu, gürültünün azaltılması ve bu görüntünün parlaklığının arttırılması için uygulanmıştır. Önerilen metodun sonuçları, bağıl hata ile sunulmuştur. Ayrıca, bu bağıl hata şekilleri, MATLAB yapay sinir ağları araç kutusu ile elde edilen hata histogramları ile desteklenmiştir

🔖

Cite This Article

KAYA, G. U., SARAÇ, Z. (2018). Usage of artificial neural networks method for image enhancement of reconstructed image in digital holography. Karaelmas Fen ve Mühendislik Dergisi, Cilt: 8 - Sayı: 2, 561–569. https://ajindex.com/articles/196244

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (12)

  1. Avidor, G., Gur, E. 2010. An adaptive algorithm for phase retrieval from high intensity images. International Conference on Image Processing Theory Tools and Applications. pp. 225-228,
  2. Paris. Duda, RO., Hart, PE., Stork, DG. 2000. Pattern Classification. 2 nd Ed, John Wiley, New York, USA, 680 pp. Dyomin, VV., Kamenev, DV., Olshukov, AS. 2014. Methods for image enhancement and accuracy increase in the digital holography of particles. Oceans 2014. pp. 1-5,
  3. Taiwan. Farnood Ahmadi, F., Valadan Zoej, MJ., Ebadi, H., Mokhtarzade, M. 2008. The application of neural networks, image processing and cad-based environments facilities in automatic road extraction and vectorization from high resolution satellite images. Int. Arch. Photogramm. Rem. S. Spat. Inf. Sci., 37(1): 585-592.
  4. Gerchberg, RW., Saxton, WO. 1972. A practical algorithm for the determination of phase from image and diffraction plane pictures. Optik, 35(2):237-246.
  5. Avidor, G., Gur, E. 2010. An adaptive algorithm for phase retrieval from high intensity images. International Conference on Image Processing Theory Tools and Applications. pp. 225-228,
  6. Paris. Duda, RO., Hart, PE., Stork, DG. 2000. Pattern Classification. 2 nd Ed, John Wiley, New York, USA, 680 pp. Dyomin, VV., Kamenev, DV., Olshukov, AS. 2014. Methods for image enhancement and accuracy increase in the digital holography of particles. Oceans 2014. pp. 1-5,
  7. Taiwan. Farnood Ahmadi, F., Valadan Zoej, MJ., Ebadi, H., Mokhtarzade, M. 2008. The application of neural networks, image processing and cad-based environments facilities in automatic road extraction and vectorization from high resolution satellite images. Int. Arch. Photogramm. Rem. S. Spat. Inf. Sci., 37(1): 585-592.
  8. Gerchberg, RW., Saxton, WO. 1972. A practical algorithm for the determination of phase from image and diffraction plane pictures. Optik, 35(2):237-246.
  9. Hect-Nielsen, R. 1989. Theory of the back propagation neural network. International 1989 Joint Conference on Neural Networks. pp. 593-605.
  10. Washington, DC, USA. Hornik, K., Stinchcombe, M., White, H. 1989. Multilayer feed forward networks are universal approximators. Neural Networks. 2(1):359-366.
  11. Isa, IS., Saad, Z., Omar, S., Osman, MK., Ahmad, KA., Mat Sakim, HA. 2010. Suitable MLP network activation functions for breast cancer and thyroid disease detection. Second International Conference on Computational Intelligence, Modelling and Simulation. pp. 39-44.
  12. Tuban, Indonesia. Latifoglu, F. 2013. A novel approach to speckle nois