Computers Perceive Image Curves like Artists with New Technology
Computers may actually be able to perceive image curves, rather like artists. Scientists have demonstrated a breakthrough concept in the field of computer vision using curves and lines to represent image shapes and recognize objects.
Human perception can recognize objects through image features, such as shapes and curves. For example, we can identify faces, animals, cars and other daily objects in simple sketch images. For computers, though, recognizing objects or image features are challenging.
Now, researchers have developed a breakthrough concept in computer vision, called interest curves. With this method, the computer can actually redraw an image using curve strokes, and recognize objects through these curves.
The new concept may bring about new dimensions of understanding image features, including points, regions, lines and curves. It also enables these features to be represented within the same theoretical framework. It advances the standard for future research regarding image features, at the same time as it provides practical guidance to the field.
The most important element in the feature, though, is its robustness. The method enables curves and lines to be detected robustly under various image transformations and disturbances.
"Curves and lines are naturally more useful than points, because humans use these shapes to describe the world," said Bo Li, one of the researchers, in a news release.
The new method could be useful for recognition software and many other applications in the future.
For more great science stories and general news, please visit our sister site, Headlines and Global News (HNGN).