Image Processing Reference
In-Depth Information
Although for Rosin's method the CA converged after that iteration, this was not the
case for the other methods, whose results steadily degraded when further iterations
were applied. Popovici and Popovici's [26] method converged after three iterations,
and Rosin's [34] method also converged after a similar number of iterations when
trained on the BSDS300 dataset. This suggests that none of the above approaches
are using the full power of CA to capture more global image structure by propagat-
ing information across the image via a larger number of iterations. The version of
Rosin's method [34] trained on the noisy version of the USF training data required
more (typically fifteen) iterations, and this is consistent with the denoising rules
in [32]. The latter were found to be competitive with alternative denoising methods,
and also required several tens of iterations of the rules (depending on the level of
noise).
Nevertheless, cellular automata based edge detection holds promise since it is
computationally efficient, and can moreover be tuned to specific domains (i.e. ap-
plications and/or image types) by appropriate selection/learning of rules. Not only
that, but pre-processing and post-processing stages such as noise filtering, thinning
and edge linking can also be easily included in the cellular automata framework.
References
1. Avidan, S., Shamir, A.: Seam carving for content-aware image resizing. ACM Trans.
Graph. 26(3), 10 (2007)
2. Bastürk, A., Günay, E.: Efficient edge detection in digital images using a cellular neural
network optimized by differential evolution algorithm. Expert Syst. Appl. 36(2), 2645-
2650 (2009)
3. Batouche, M., Meshoul, S., Abbassene, A.: On solving edge detection by emergence.
In: Ali, M., Dapoigny, R. (eds.) IEA/AIE 2006. LNCS (LNAI), vol. 4031, pp. 800-808.
Springer, Heidelberg (2006)
4. Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Analysis
and Machine Intelligence 8, 679-698 (1986)
5. Chang, C., Zhang, Y., Gdong, Y.: Cellular automata for edge detection of images. Int.
Conf. on Machine Learning and Cybernetics 6, 3830-3834 (2004)
6. Chen, Y., Yan, Z.: A cellular automatic method for the edge detection of images. In:
Huang, D.-S., Wunsch II, D.C., Levine, D.S., Jo, K.-H. (eds.) ICIC 2008. LNCS (LNAI),
vol. 5227, pp. 935-942. Springer, Heidelberg (2008)
7. Diwakar, M., Patel, P., Gupta, K.: Cellular automata based edge-detection for brain tu-
mor. In: Advances in Computing, Communications and Informatics, pp. 53-59 (2013)
8. Ens, J., Lawrence, P.: An investigation of methods for determining depth from focus.
IEEE Trans. Pattern Analysis and Machine Intelligence 15(2), 97-108 (1993)
9. Georgilas, I., Gale, E., Adamatzky, A., Melhuish, C.: UAV horizon tracking using mem-
ristors and cellular automata visual processing (2013)
10. Gharehchopogh, F., Ebrahimi, S.: A novel approach for edge detection in images based
on cellular learning automata. Int. J. Computer Vision and Image Processing 2(4), 51-61
(2012)
11. Gorsevski, P., Onasch, C., Farver, J., Ye, X.: Detecting grain boundaries in deformed
rocks using a cellular automata approach. Computers & Geosciences 42, 136-142 (2012)
Search WWH ::
Custom Search