Publicado

2018-01-01

Un nuevo enfoque para la clasificación de imágenes multiespectrales basado en complejos cartesianos

A new approach to multispectral image classification based on abstract complex cells

DOI:

https://doi.org/10.15446/dyna.v85n204.66161

Palabras clave:

clasificación, complejo cartesiano, superpixel, topología, máquina de soporte vectorial (es)
classification, Cartesian complex, superpixel, topology, support vector machine (en)

Descargas

Autores/as

El presente artículo propone un nuevo enfoque de clasificación de imágenes que utiliza como representación del espacio complejos cartesianos libre de ambigüedad en las relaciones topológicas. El enfoque propuesto comprende seis fases: (i) conversión de la imagen convencional al espacio de complejos cartesianos; (ii) transformación a niveles de grises; (iii) producción de super-píxeles basada en la transformada de cuenca; (iv) producción del espacio de textura aprovechando elementos inter-pixel 1-dimensionales; (v) clasificación mediante máquinas de soporte vectorial; y (vi) evaluación de los resultados. Aunque la exactitud temática de la clasificación a partir del nuevo enfoque mejora la exactitud obtenida con una representación convencional del espacio, la prueba de confianza indica que esa mejoría no es estadísticamente significativa. Sin embargo, el nuevo enfoque puede ser fortalecido en el futuro mediante la incorporación de técnicas para mejorar la definición de límites entre cuencas utilizando valores de probabilidad y espacios de textura multiescala.
This article proposes a new approach to image classification using a space representation as a Cartesian complex free of ambiguity in the topological relationships of adjacency, connectivity, and boundary. The proposed model comprises six phases: (i) image conversion from the conventional space into the Cartesian complex space; (ii) greyscale transformation, (iii) super-pixel space production based on watershed transform, (iv) texture space production taking advantage of 1-dimensional interpixel elements, (v) classification using support vector machines and (vi) results quality assessment. Although global accuracy of the proposed classification improves accuracy of results obtained with a conventional representation of space, the confidence test shows that this improvement is not statistically significant. However, the new approach can be further strengthened by incorporating techniques to improve boundaries definition between watersheds based on probability values as well as using spaces of multiscale texture.

Descargas

Los datos de descargas todavía no están disponibles.

Citas

Rosenfeld, A., Connectivity in digital pictures. Journal of ACM, [online], 17(1), pp. 146-160, 1970. Available at: http://dl.acm.org/citation.cfm?id=321570

Kiselman, C.O., Digital jordan curve theorems, Proceedings of 9th International Conference of Discrete Geometry for Computer Imagery (DGCI), 2000. pp. 46-56

Kovalevsky, V.A., Axiomatic digital topology. Journal of Mathematical Imaging and Vision, [online], 26(1), pp. 41-58, 2006. Available at: https://link.springer.com/article/10.1007/s10851-006-7453-6

Kopperman, R. and Pfaltz, J.L., Jordan surfaces in discrete antimatroid topologies, Proceedings of 10th International Workshop in Combinatorial Image Analysis (IWCIA 2004), Auckland, New Zealand, 2004, Springer Berlin Heidelberg, 2005. pp. 334-350. DOI: 10.1007/978-3-540-30503-3_25

Kovalevsky, V., Geometry of locally finite spaces: Computer

agreeable topology and algorithms for computer imagery Baerbel Kovalevsky, 2008.

Kovalevsky, V.A., Finite topology as applied to image analysis. Journal Computer Vision, Graphics, and Image Processing, [online], 46(2), pp. 141-161, 1989. Available at: http://dl.acm.org/citation.cfm?id=65318

Munkres, J.R., Elements of algebraic topology. Advanced book classics. The advanced book program. Avalon Publishing, 1984.

Khalimsky, E., Kopperman, R. and Meyer, P.R., Computer graphics and connected topologies on finite ordered sets, Topology and its Applications, 36(1), pp. 1-17, 1990.

Szeliski, R., Computer vision. London: Springer London, [online]. 2011. Available at: http://link.springer.com/10.1007/978-1-84882-935-0

Arbelaéz, P., Maire, M., Fowlkes, C. and Malik, J., Contour detection and hierarchical image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, [online]. 33(5), pp. 898-916, 2011. Available at: http://resolver.caltech.edu/CaltechAUTHORS:20110415 -113118411

Valero, J., Research´s Report: Development of an Alternative method for multispectral image segmentation based on cartesian complexes and its associated oriented matroids. Universidad Distrital Francisco José de Caldas. Bogotá, 2015, 42 P.

Tso, B. and Mather, P.M., Classification methods for remotely sensed data. CRC Press, 2009.

Valero, J., Lizarazo, I., and Arbelaez, P., Multispectral image segmentation based on cartesian complexes and their associated oriented matroids, Proceedings of GEOBIA 2016: Solutions and Synergies., September 14 - 16 of 2016, University of Twente Faculty of Geo-Information and Earth Observation (ITC), [online]. 2016. Available at: http://proceedings.utwente.nl/442/

Naqash, T. and Shafi, I., Edge sharpening in grayscale images using modified Sobel technique, Proceedings of Multitopic Conference (INMIC), IEEE 14th International, 2011. pp. 132-136 DOI: 10.1109/INMIC.2011.6151458

Dou, Y., Hao, K. and Ding, Y., A short step affine transformation Sobel algorithm based image edge detection in low illumination, proceedings of Chinese Automation Congress (CAC), 2015. pp. 594-597. DOI: 10.1109/CAC.2015.7382569

Deng, C., Ma, W. and Yin, Y., An edge detection approach of image fusion based on improved Sobel operator, Proceedings of 4th International Congress on Image and Signal Processing (CISP), 2011. 3. pp. 1189-1193. DOI: 10.1109/CISP.2011.6100499

International Society for Photogrammetry and Remote Sensing. 2D Semantic labeling contest, [online]. 2016. Available at http://www2.isprs.org/commissions/comm3/wg4/semantic-labeling.html

Kovalevsky, V., Algorithms in digital geometry based on cellular topology. Springer-Verlag Berlin Heidelberg, 2004. pp. 366-393.

Nikodem, J., Plateau problem in the watershed transform. Computing and Informatics, 28(2), pp.195-207, 2012.

Leung, T. and Malik, J., Detecting, localizing and grouping repeated scene elements from an image. In Buxton, B. and Cipolla, R., Eds., Computer Vision — ECCV ’96, Springer Berlin Heidelberg. [online]. 1996, pp. 546-555. Available at https://link.springer.com/ chapter/10.1007/BFb0015565

Gimenez, Y., Clasificación no supervisada: El método de K-Medias. Tesis de licenciatura. Facultad de Ciencias Exactas y Naturales Departamento de Matemática. Universidad de Buenos Aires, Argentina. [online]. 2010. Available at: http://cms.dm.uba.ar/ academico/carreras/licenciatura/tesis/2010/Gimenez_Yanina.pdf

Gonzales, R. and Woods, R.E., Digital Image Processing (4th Edition). Pearson International, 2017.

Tan, P.N., Steinbach, M. and Kumar, V., Introduction to data mining. Addison-Wesley, 2013.

Lizarazo, I., Accuracy assessment of object-based image classification: Another Step. International Journal of Remote Sensing, 35(16), pp. 6135-6156, 2014. DOI: 10.1080/01431161.2014.943328