We have focused on rapid and efficient estimator to find object distance from hologram in order to reconstruct original image. Our approach to find it makes the estimator pre-trained through deep learning. Especially in off-axis holography configuration, our method eliminates the unnecessary factors and reduces information loss occurred by resizing image to plug into Convolution Neural Network (CNN). Training is performed on the generated images at several specific distances under various optical conditions and the accuracy of estimation is validated.
|Title of host publication||Digital Holography and Three-Dimensional Imaging, DH 2018|
|Publisher||OSA - The Optical Society|
|Publication status||Published - 2018|
|Event||Digital Holography and Three-Dimensional Imaging, DH 2018 - Orlando, United States|
Duration: 2018 Jun 25 → 2018 Jun 28
|Name||Optics InfoBase Conference Papers|
|Volume||Part F100-DH 2018|
|Other||Digital Holography and Three-Dimensional Imaging, DH 2018|
|Period||18/6/25 → 18/6/28|
Bibliographical notePublisher Copyright:
© 2018 The Author(s).
All Science Journal Classification (ASJC) codes
- Electronic, Optical and Magnetic Materials
- Mechanics of Materials