Experimental reaction-diffusion pre-processor for shape recognition. (English) Zbl 1068.68694
Summary: We have produced an experimental implementation of a massively-parallel reaction-diffusion processor which performs one of the most essential parts of shape recognition – construction of a skeleton. A skeleton is a unique, stable and invariant representation of a shape, therefore computation of the skeleton is an essential tool of computer vision. Skeleton computation is a typical ‘natural’ spatial problem that can be solved with the use of biological, chemical or physical phenomena. One possible approach – a reaction-diffusion based computation – is explored in this Letter. A contour is represented by a concentration profile of one reagent, a planar substrate is mixed with another reagent. The reagent, representing the original contour diffuses to form a coloured phase in a reaction with the substrate-reagent. However, at sites where two diffusion wave fronts meet no coloured phase is formed and the substrate retains its uncoloured state. These loci of the computation space represent a skeleton of the given contour. In the Letter we only describe a laboratory prototype of a reaction-diffusion processor that computes a skeleton, no further tasks of image processing are undertaken, one could say we have designed an unconventional chemical pre-processor for shape recognition.
MSC:
| 68T45 | Machine vision and scene understanding |
| 68U10 | Computing methodologies for image processing |
References:
| [1] | Adamatzky, A., Computing in Nonlinear Media and Automata Collectives (2001), IoP Publishing · Zbl 0983.68129 |
| [2] | (Beck, J.; Hope, B.; Rosenfeld, A., Human and Machine Vision (1983), Academic Press) · Zbl 0825.68672 |
| [3] | Heijmans, H. J.; Roerdink, J. B., Mathematical Morphology and Its Applications to Image and Signal Processing (1998), Kluwer Academic Publishers · Zbl 0894.00056 |
| [4] | Kuhnert, L.; Agladze, K. L.; Krinsky, V. I., Nature, 337, 244 (1989) |
| [5] | Rambidi, N. G.; Maximichev, A. V., Adv. Mater. Opt. Electron., 7, 171 (1997) |
| [6] | Adamatzky, A.; Tolmachiev, D., Adv. Mater. Opt. Electron., 7, 135 (1997) |
| [7] | Tolmachev, D.; Adamatzky, A., Adv. Mater. Opt. Electron., 6, 191 (1996) |
| [8] | Agladze, K.; Magome, N.; Aliev, R.; Yamaguchi, T.; Yoshikawa, K., Physica D, 106, 247 (1997) |
| [9] | Rambidi, N. G.; Yakovenchuck, D., Adv. Mater. Opt. Electron., 5, 67 (1999) |
| [10] | Calabi, L.; Hartnett, W. E., Am. Math. Monthly, 75, 335 (1968) · Zbl 0161.41602 |
| [11] | Brady, M., (Beck, J.; Hope, B.; Rosenfeld, A., Human and Machine Vision (1983), Academic Press), 39-84 |
| [12] | Ogniewicz, R. L.; Kübler, O., Pattern Recognition, 28, 343 (1995) |
| [13] | Pavlidis, T., IEEE Trans. Pattern Anal. Mach. Intell., 2, 301 (1980) |
| [14] | Maragos, P. A., Opt. Engrg., 26, 623 (1987) |
| [15] | Haralick, R.; Shapiro, L., Computer and Robots (1992), Addison-Wesley |
| [16] | (Dori, D.; Bruckstein, A., Shape, Structure and Pattern Recognition (1994), World Scientific Publishers) |
| [17] | (Forsyth, D.; Mundy, J.; Cipolla, R.; Goos, G., Shape, Contour and Grouping in Computer Vision (2000), Springer) |
| [18] | Loncaric, S., Pattern Recognition, 31, 983 (1998) · Zbl 0954.68131 |
| [19] | Marr, D., Vision (1982), Freeman |
| [20] | P. Moreau, J.-P. Braquelaire, Two-dimensional thick-skeleton morphing, 1996, http://citeseer.nj.nec.com/87262.html; P. Moreau, J.-P. Braquelaire, Two-dimensional thick-skeleton morphing, 1996, http://citeseer.nj.nec.com/87262.html |
| [21] | Blum, H., (Wathen-Dunn, W., Models for the Perception of Speech and Visual Form (1967), MIT Press) |
| [22] | Blum, H., J. Theor. Biol., 38, 205 (1973) |
| [23] | A.R. Pearce, T. Caelli, S. Sestito, S. Goss, M. Selvestrel, G. Murray, Skeletonizing topographical regions for navigational path planning, Technical Report CVPRL and ARL, Australia, 1993; A.R. Pearce, T. Caelli, S. Sestito, S. Goss, M. Selvestrel, G. Murray, Skeletonizing topographical regions for navigational path planning, Technical Report CVPRL and ARL, Australia, 1993 |
| [24] | Rosenfeld, A.; Pfaltz, J. L., Pattern Recognition, 1, 33 (1968) |
| [25] | Adamatzky, A., Neural Networks World, 3, 241 (1994) |
| [26] | Rambidi, N. G.; Maximychev, A. V.; Usatov, A. V., Adv. Mater. Opt. Electron., 4, 191 (1994) |
| [27] | G. Abdel-Hamid, Y.-H. Yang, Multiscale skeletonization: an electrostaticfield-based approach, VR-94-6, 14, 1994, http://citeseer.nj.nec.com/201707.html; G. Abdel-Hamid, Y.-H. Yang, Multiscale skeletonization: an electrostaticfield-based approach, VR-94-6, 14, 1994, http://citeseer.nj.nec.com/201707.html |
| [28] | Adamatzky, A., Math. Comput. Modelling, 23, 51 (1996) · Zbl 0848.68066 |
| [29] | Ogniewicz, R.; Ilg, M., (Proceedings of IEEE Conference Computer Vision and Pattern Recognition, CVPR (1992), IEEE Press), 63-69 |
| [30] | Mayya, N.; Rajan, V. T., Pattern Recognition Lett., 16, 147 (1995) |
| [31] | T. Grigorishin, G. Abdel-Hamid, Y.-H. Yang, Skeletonization: an electrostatic field-based approach, VR-96-1, 1, 1996; T. Grigorishin, G. Abdel-Hamid, Y.-H. Yang, Skeletonization: an electrostatic field-based approach, VR-96-1, 1, 1996 |
| [32] | Laplante, J. P.; Pemberton, M.; Hjelmfelt, A.; Ross, J., J. Phys. Chem., 99, 10063 (1995) |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
