A Custom Imaging Pipeline for Automated Microscopy

In the human visual system, light that reaches the eye is processed by the brain and understood in shapes, colours, and intensities. In the instance of digital cameras, light that reaches a camera sensor must undergo processing to be presented in a human-readable format. The process that achieves this task is known as the in-camera processing pipeline, and is present among all digital cameras readily available to end consumers. While many of the problems of imaging are solved in an open-world format due to the prevalence of mobile phone cameras, the current techniques degrade under specific settings. One such setting is imaging cells through a microscope, where the subject of the image, intensity of light, and stringent requirements of a medical context provide novel constraints not encountered in common imaging scenarios of mobile phones. This project develops proprietary algorithms and calibration techniques for imaging cells with cameras found in mobile phones for medical diagnosis.

Faculty Supervisor:

Michael S. Brown

Student:

Partner:

Vital Biosciences Inc. Mississauga

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

York University

Program: