Image across Domains, Experiments, Algorithms and Learning
U. S. Department of Energy Advanced Scientific Computing Research Early Career Research Project
2016 - 2020
Imagine inspecting 1 TB of images in 1 sec? Forget binge watching, this means 200 movies in a blink of the eye. This amount of images overwhelms scientists who depend on experimental data recorded in image files. But how to visually examine that many pictures? What we need is to construct computer programs that recognize relevant patterns from digital images. That is what I have done for the past 20 years: I use computer vision and machine learning techniques to enable people to use pictures in decision-making. I construct algorithms applied to material science, aiming to control the quality of compounds and, for example, improve durability of aircrafts. Another project is to design computational tools for biological structure description and interactions, for example, to enable neurologists to detect cells and functions in cellular communities.
I’m Dani Ushizima and my mission is to turn data into decisions. As a Staff Scientist at the Computational Research Division, Berkeley Lab, and a member of the CAMERA Center and the Data Analytics and Visualization Group, LBNL, my job is to design analytics-driven strategies to cope with data. I also investigate Data Science methods as a Data Scientist Staff at the Berkeley Institute for Data Science (BIDS), UC Berkeley in collaboration with UCSF and BioCAMERA. As part of scientific teams, my R&D focuses on computer vision applied to images across domains. Other initiatives I co-lead are ImageXD and CRIC.