Image processing for naval ultrasonic imaging system
Brief Description of Project:
Visualization in turbid water for Navy divers and underwater unmanned vehicles remains a challenging problem. Our lab is currently developing ultrasound imaging systems for underwater visualization. Software and systems are needed to automatically and efficiently enhance and analyze images obtained by the imaging system.
This summer project focuses on exploring the use of state-of-the-art deep learning methods to perform critical image processing tasks, including classification and enhancement of image contents. The project will involve collection of data, with the use of a water tank test-bed, needed to design and test the deep learning networks, as well as contributing to the development of image processing procedures.
Experience with python is required. Matlab experience and image processing experience are desirable.
Nature of Supervision:
PI and collaborating faculty and graduate students
A Brief Research Plan (period is for 10 weeks):
Weeks 1-2: Project overview, plan development
Weeks 3-9: Data curation, deep network training/testing
Week 10: Project write-up
Number of Open Slots: 1
Name: Jack Noble
Department: Electrical Engineering & Computer Science