Loading...

Utilization of Different Optical Wavelengths in Diffractive Deep Neural Networks for Object Classification in Multi-Channel Images

Ebrahimi, Sevda | 2019

363 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 53311 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Vosughi Vahdat, Bijan; Kavehvash, Zahra
  7. Abstract:
  8. Diffractive deep neural network is an optical machine-learning framework that uses diffractive surfaces, optical devices, electro-optic devices and engineered matterials to optically perform computational tasks. These diffractive networks, after their desing and train phase by computers and machine learning algorithms, are physically fabricated using 3D printing or lithography, to actualize the model of trained network. Machine learning processes and alghorithms are performed through light-matter interaction and diffraction of light. This procedure is done at the speed of light and without the need of any power, except for the light illumination for the input object. In comparison with standard ANNs, which are computer-based, their capacity of processing information at the speed of light and low energy consumptions, is especially significant for recognizing target objects more quickly and it might provide major advantages for autonomous vehicle systems and various defense related applications. In this thesis, we have proposed a diffractive deep neural network for classifying objects in images consist of two channels. We have assigned two different wavelength for each channel of the image, and extracted the alghorithms for training procedure of diffractive network. Finally the diffractive deep neural network is adjusted to employ two frequencies mutually to perform classification task
  9. Keywords:
  10. Optical Computing ; Object Classification ; Deep Neural Networks ; Diffraction ; Diffractive Deep Neural Networks

 Digital Object List

 Bookmark

No TOC