Skip navigation
Engineers develop technology for image and video-based web searches

Narrator:       This is Science Today. When we go online to conduct a search, we type in a term and the search engine gives us back returns from pages that have that same text in them. But engineers at the University of California, Santa Cruz are hoping to take web searches a big step forward. Peyman Milanfar, a professor of electrical engineering, has developed a search technique for images and videos.

Milanfar:        What you'd like to be able to do is search for images that you might  be interested in with another image. So, this is the notion of basically being able to find similarity between images without having a huge number of examples of that category of interest.

Narrator:       Milanfar's approach uses a single image. This type of visual approach would not only change how we surf the web, but it has broad applications in areas such as video surveillance and security systems.

Milanfar:        What we have is the fundamental core technology, which once it's married to technology having to do with databases and with large processing power, is going to have hopefully a global impact.

Narrator:       For Science Today, I'm Larissa Branin.