Brian A. Barsky, Professor

Closed (1) Aberration Compensated Displays for Personalized Vision Correction

Applications for fall 2021 are now closed for this project.

This project is investigating algorithmic vision correction for the user of a display based on his or her spectacles prescription in simple cases or based on measurements of the optical aberrations of his or her vision in more complex cases. Our approach is to compute an altered display that when viewed by the particular individual user would appear in sharp focus for this particular individual. Since some visual impairments involve irregular astigmatism and high order optical aberrations which are impossible to correct with spectacle lenses, the proposed research could provide the opportunity to use display devices for the first time to those for whom this has been heretofore impossible due to their suffering from these ocular conditions.

Website of interest: http://www.cs.berkeley.edu/~barsky
See the video at: http://www.cs.berkeley.edu/~barsky/inverse.blurring.multilayer.displays.mp4

Day-to-day supervisor for this project: Anmol Parande, Graduate Student

Qualifications: C/C++ programming or Matlab Programming(Image processing toolkit), or CS184, or Fourier Analysis or Linear Algebra, all desirable but not essential

Weekly Hours: to be negotiated

Related website: https://people.eecs.berkeley.edu/~barsky/siggraph.2014.html
Related website: https://barskygroup.wixsite.com/home

Closed (2) Assistive Technology for Cursor Control (Navigation, Selection, Pointing, and Clicking) by Capturing Hand Movements

Applications for fall 2021 are now closed for this project.

This project is concerned with assistive technology that enables users with fine motor control difficulties to navigate, select, point, and click without physically manipulating a mouse. The idea is to use a camera to capture the user’s hand movements.

There are many individuals who do not have the ability to control the pointer easily by moving a physical mouse. Unfortunately, there no viable alternatives due to the fact that the mouse has become an essential input device for all modern computers. Inability to control the mouse could be caused by impaired sensation from a wide variety of conditions and illnesses. This project aims to help those with impaired sensation by developing a computer-vision based input system with a camera as its input device.

The current project is developing a system that comprises three modules of detection, tracking, and response: (1) The detection stage extracts the hand and recognizes its gesture which can then be used to alter the users' control; for example, a specific movement could correspond to a click of the mouse. (2) The hand is traced by a tracker and its movement is filtered with an anti-shake filter to perform a more stable movement. (3) In the response stage, the granularity (e.g., dots per inch) of the cursor is adjusted according to the user’s speed of hand movement.


Day-to-day supervisor for this project: Rohan Hajela, Graduate Student

Weekly Hours: to be negotiated

Related website: http://www.cs.berkeley.edu/~barsky
Related website: https://barskygroup.wixsite.com/home