Search technique for images recognises visual patterns

March 16, 2005

Dutch researcher Mirela Tanase has developed a new technique for finding images using search engines. Her technique is based on how the human eye recognises objects. It can increase the success rate of certain search operations for objects from 10 to 70 percent.

Tanase developed two methods for decomposing objects into parts, which are then used to search for similar objects. The first method decomposes the interior of the shape. Humans find this task easy, but a computer often has problems working out how it should decompose an object. The second method works on a range of skeletons and decomposes the contour instead of the interior. Branching points in the skeleton provide an indication as to which pieces of the contour belong to perceptually different parts.

Subsequently Tanase developed a 'part-based' search engine. This finds images by using parts of objects. For example, for the image of a deer the engine can look for the legs of the deer. As well as images of a deer, the results found include other images containing similar contours, for example, elks, horses or elephants.

This search method provides a useful addition to the method chosen by MPEG7 to search contours. In certain cases where the MPEG7 method is relatively unsuccessful, the number of objects correctly found can increase from 10 to 70 percent.

Digitalisation

In recent years there has been an explosion in the number of digitalized photo collections made available to everyone via the Internet. Museums and art galleries are not the only parties involved. Hospitals also have databases with photos and many companies provide a detailed overview of their entire product range on the web.

Internet search engines such as Google work well for text files but are far less effective in searching for images. Due to the growing number of images in collections, there is an increasing need for good search methods. Searching using keywords is time-consuming and not always effective. Looking for visual information such as colour, texture and shapes found in the images, significantly increases the number of correctly identified objects in a search.

Source: Netherlands Organization for Scientific Research

Explore further: Zwicky Transient Facility sees 'first light'

Related Stories

Zwicky Transient Facility sees 'first light'

November 14, 2017

A new robotic camera with the ability to capture hundreds of thousands of stars and galaxies in a single shot has taken its first image of the sky—an event astronomers refer to as "first light." The camera is the centerpiece ...

Small asteroid or comet 'visits' from beyond the solar system

October 26, 2017

A small, recently discovered asteroid - or perhaps a comet - appears to have originated from outside the solar system, coming from somewhere else in our galaxy. If so, it would be the first "interstellar object" to be observed ...

Recommended for you

Physicists design $100 handheld muon detector

November 20, 2017

At any given moment, the Earth's atmosphere is showered with high-energy cosmic rays that have been blasted from supernovae and other astrophysical phenomena far beyond the Solar System. When cosmic rays collide with the ...

The strange case of the scuba-diving fly

November 20, 2017

More than a century ago, American writer Mark Twain observed a curious phenomenon at Mono Lake, just to the east of Yosemite National Park: enormous numbers of small flies would crawl underwater to forage and lay eggs, but ...

Recurring martian streaks: flowing sand, not water?

November 20, 2017

Dark features on Mars previously considered evidence for subsurface flowing of water are interpreted by new research as granular flows, where grains of sand and dust slip downhill to make dark streaks, rather than the ground ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.