Clara Hung L&S Math & Physical Sciences
Scalable Dataset Acquisition for Data-driven Lensless Imaging
Lensless imagers are low-cost, compact cameras with applications in medical imaging, photography, and more. Many designs for lensless imagers have been proposed, but the optimal design is not known as it is object-dependent. A method to capture images from different systems under similar conditions is needed to fairly compare system performance. Furthermore, as lensless imaging is moving towards data-intensive research, large-scale lensless measurement datasets are necessary for neural network evaluation. Yet, of the few existing datasets in the field, none fully address these demands.
We propose a portable data acquisition pipeline capable of capturing from multiple lensless imaging systems simultaneously, paired with a ground truth lensed image. This contribution would enable a fair comparison of multiple different lensless systems, a quantitative understanding of optimal lensless imager design, and facilitate emerging work in machine learning and information theory.
Message To Sponsor
Thank you for your generous funding of my summer research project! This experience not only allowed me to grow significantly as a researcher, it has also taught me how to be more independent in my research. It has made me more confident in my abilities as a researcher and pushes me to continue my work in graduate school and beyond. I will be applying to PhD programs this fall, and SURF has helped me form a more cohesive research identity.