Experimental Results

Here we present results for our CACE model and compare its performance against the CPM, the geodesic contour, and the GVF geodesic contour models. The software for all the methods we compare against was developed in-house.

CACE copes much better than CPM when faced with weak edges. Fig. 2 shows a synthetic image of a circle with a blurred edge region indicated by a black window. In such regions the image-based forces are significantly influenced by the stronger edges nearby. As the image-based forces always dominate the direction of movement, particles which have arrived at the weak edges will continue moving to the stronger edges with the weak edges left unmarked. This leads CPM to fail to close the border around the synthetic circle. On the other hand, as shown in Fig. 3 CACE stabilizes around the boundaries, successfully detecting the whole object, due to the bi-directional nature of its force field and the characteristics of the contour itself. The vectors pointing towards the edges, although weak, prevent leakage from both sides.

(Click on the vector image for larger view.)

Figure 2: Columnwise from left: disk object image with highlighted weak edge area, the normalized Coulomb force in CPM (equivalently the boundary attraction force in CACE) field in box area, initialized CPM, instance of particle movements, and the final CPM result.

Figure 3: Propagation of CACE on disc object with weak edges.