Active contours are a popular approach for object segmentation that uses an energy minimizing spline to extract an objects boundary. Non-parametric approaches can be computationally complex while parametric approaches can be impacted by parameter sensitivity. A decoupled active contour (DAC) overcomes these problems by decoupling the external and internal energies and optimizing them separately. However a drawback of this approach is its reliance on the edge gradient as the external energy. This can lead to poor convergence toward the object boundary in the presence of weak object and strong background edges. To overcome these issues with convergence, a novel approach is proposed that takes advantage of a sparse texture model which explicitly considers texture for boundary detection. The approach then defines the external energy as a weighted combination of textural and structural variation maps and feeds it into a multi-functional hidden Markov model for more robust object boundary detection. The enhanced decoupled active contour (EDAC) is qualitatively and visually analyzed on two natural image datasets as well as Brodatz images. The results demonstrate that EDAC selectively combines texture and structural information to extract the object boundary without impact on computation time and a reliance on color.
Illustration of the architecture for the EDAC approach: The multi-functional variation map of the source image is derived using a weighted combination of the textural and structural variation maps, where the textural variation map is determined using the sparse texture model. This map is used to formulate the active contour by optimizing the external and internal energies to result in the segmented image.
From left to right: Source image, sparse texture model, external energy, snake and ground truth are shown for two examples where structural and textural variations enable effective active contour segmentation.
Related research areas