Imagine computers being able to understand paintings or paint abstract images much like humans. Bo Li at Ume? University in Sweden demonstrates a breakthrough concept in the field of computer vision using curves and lines to represent image shapes and furthermore to recognize objects.

Accurate modelling of image features is very important in a wide range of computer vision applications, for example: image registration, 3D reconstruction, and object detection. In future technologies such as Google Car, virtual reality, or AI brain, image features will remain fundamental components. In spite of the fact that hundreds of solutions for the detection of image features already exist, up until now there had been a solid concept missing.

In his doctoral dissertation at the Department of Applied Physics and Electronics at Ume? University, Bo Li has developed a breakthrough concept in computer vision: interest curves. According to Bo Li, the most important element in feature extraction is the robustness. His results show that his 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," explains Bo Li.

His doctorate work shows many advantages of using curve features in computer vision applications.

Story Source:
The whole story is posted on ScienceDaily.