A Swarm Intelligence inspired algorithm for contour detection in images

Swarm Intelligence uses a set of agents which are able to move and gather local information in a search space and utilize communication, limited memory, and intelligence for problem solving. In this work, we present an agent-based algorithm which is specifically tailored to detect contours in images. Following a novel movement and communication scheme, the agents are able to position themselves distributed over the entire image to cover all important image positions. To generate global contours, the agents examine the local windowed image information, and based on a set of fitness functions and via communicating with each other, they establish connections. Instead of a centralized paradigm, the global solution is discovered by some principal rules each agent is following. The algorithm is independent of object models or training steps. In our evaluation we focus on boundary detection as a major step towards image segmentation. We therefore evaluate our algorithm using the Berkeley Segmentation Dataset (BSDS) and compare its performance to existing methods via the BSDS benchmark and Pratt's Figure of Merit.

Figure optionsDownload as PowerPoint slideHighlights
► Distributed agents and Swarm Intelligence are utilized to detect contours of arbitrary shape in images.
► Following a novel positioning rule, the agents build a dynamic mesh that reflects the image contours.
► Agents build contour models based on the similarity of image information between themselves and local neighbors.
► Agents negotiate with their local neighborhood to cooperatively establish the overall best contour estimation.
► The algorithm is evaluated on the Berkeley Segmentation Database (BSDS) using Pratt's Figure of Merit and the BSDS benchmark.