Abstract:
We propose a contour detection method
based on the mechanisms from biological visual
perception. The temporal analysis of image is the
basis of the model. The temporal notion means that
the static image is transformed into a data flow.
Each element of the flow is treated independently
from the others. Our aim is image segmentation
through contour detection. The model is composed
of a succession of five stages: noise reduction,
asynchronous processing, isotropic filtering and
adaptive smoothing, dynamic thresholding, and
temporal integration. To evaluate the proposed
approach, objective and subjective analyses are
performed on synthetic and actual images.