Fourier Ptychographic Imaging via Neural Network Modeling

Speaker: Dr. Guoan Zheng
Affiliation: University of Connecticut

Abstract:  Fourier ptychography is a recently developed phase retrieval approach for large field-of-view and high-resolution imaging. This technique stitches together many variably illuminated, low-resolution measurements in the Fourier space to expand the frequency passband and recover the high-resolution complex object image. Without involving any mechanical scanning, it facilitates large field of view imaging in a simple and robust manner. In this talk, I will first discuss the principle of phase retrieval. I will then introduce the Fourier ptychography approach and discuss its applications in microscopy and long-range imaging. I will also discuss how to model the Fourier ptychographic imaging process using a neural network and recover the complex object information using a popular machine learning library, TensorFlow.  In the proposed neural network, the object is treated as 2D learnable weights of a convolutional or a multiplication layer.  The output of the network is modeled as the loss function one aims to minimize. The batch size of the network corresponds to the number of captured low-resolution images in one forward / backward pass. Since convolution and multiplication are the two most-common operations in imaging modeling, the model may provide a new perspective to examine many coherent and incoherent systems.

Biography:   Dr. Guoan Zheng received the M.S. and Ph.D. degrees in electrical engineering from Caltech in 2008 and 2013, respectively. He is currently an assistant professor at the University of Connecticut, with a joint appointment in Biomedical Engineering and Electrical Engineering departments. He is the recipient of UConn research excellence award, Caltech Demetriades Thesis Prize, and Lemelson-MIT Caltech Student Prize. The Fourier ptychography approach he developed is now a subchapter in Goodman’s famous textbook, “Introduction to Fourier Optics.” His current research interest focuses on the development of novel imaging and sensing techniques for biomedical applications. 

For more information, contact Prof. Aydogan Ozcan ()

Date(s) - Apr 11, 2018
1:00 pm - 2:30 pm

E-IV Maxwell Room #57-124
420 Westwood Plaza - 5th Flr. , Los Angeles CA 90095