Advertisement

UCLA open sources image detector that can see what we can't

The powerful algorithm is now up on GitHub and Matlab Central

Bahram Jalali

UCLA has released the source code to powerful image detection software that can see an object's every detail at high speed -- key for applications like fingerprint and iris scanning, or self-driving cars. It starts by identifying an object's edges and then looking for and extracting its other, fainter features. For instance, if there are items with textured surfaces in the image, the algorithm can recognize and enhance them, as you can see in the example below the fold. It can even see through bright lights to detect their sources' structures, such as lamps, LED lights and even the moon.

The Phase Stretch Transform algorithm was developed by UCLA professor Bahram Jalali, senior researcher Mohammad Asghari and their team. Their project is a spin-off of the university's research on photonic time stretch that can be used to detect cancer cells. It's also the secret behind what UCLA once called the "world's fastest camera" that can capture events that happen very, very fast. The algorithm is now up and available to the public on GitHub and Matlab Central.