Artículos

 

Quadrilateral Detection Using Genetic Algorithms

 

Detección de cuadriláteros usando algoritmos genéticos

 

Victor Ayala Ramirez, Sergio A. Mota Gutierrez, and Raul E. Sánchez Yanez

 

Universidad de Guanajuato, División de Ingenierías Campus Irapuato–Salamanca, Carr. Salamanca–Valle de Santiago Km. 3.5+1.8, Comunidad Palo Blanco, 36700, Salamanca, Mexico. E–mail: ayalav@ugto.mx, sanchezy@ugto.mx, samota@laviria.org

 

Article received on 12/03/2010.
Accepted 05/03/2011.

 

Abstract

An approach based on the use of genetic algorithms to detect quadrilateral shapes in images is presented in this paper. The proposed approach finds the best sets of four edge points that are the vertices of quadrilateral shapes in the image. The proposed method uses the evidence provided by the image resulting of the application of an edge detection operator to the input image. Individuals having the best fitness scores are those that are supported by the edge evidence as being the vertices of a quadrilateral present in the input image. We use a sharing operator to avoid detecting similar quadrilaterals. This procedure is used to detect multiple quadrilaterals in a single run of our algorithm. Our method can handle perspective distortion and Gaussian noise corruption on the quadrilaterals to be detected. We have fulfilled tests to validate our approach on synthetic, noise–corrupted and real world images. Tests are both quantitative and qualitative. The proposed approach has shown also to be fast for real–time quadrilateral detection.

Keywords: Genetic algorithms, quadrilateral detection, shape recognition.

 

Resumen

En este artículo se presenta un enfoque para la detección de formas cuadriláteras en imágenes usando algoritmos genéticos. El enfoque propuesto encuentra los mejores conjuntos de cuatro puntos de borde que son vértices de cuadriláteros presentes en la imagen. El método propuesto usa la evidencia proporcionada por la imagen resultante de la aplicación de un operador de detección de bordes a la imagen de entrada. Los individuos con mejor valor de adecuación son aquéllos que representan a los vértices de cuadriláteros presentes en la imagen. A fin de evitar la detección de cuadriláteros similares entre sí, se usa una función de sharing. Esto permite detectar múltiples cuadriláteros en una sola ejecución del algoritmo. Nuestro método puede manejar la presencia de distorsión perspectiva y de ruido Gaussiano aditivo en los cuadriláteros por ser detectados. Se presentan pruebas para validar nuestro enfoque sobre imágenes sintéticas, imágenes corrompidas por ruido e imágenes reales. Las pruebas son tanto cuantitativas como cualitativas e incluyen también la detección de cuadriláteros en imágenes dibujadas a mano. El enfoque propuesto muestra también ser rápido para la detección de cuadriláteros.

Palabras clave: Algoritmos genéticos, detección de cuadriláteros, reconocimiento de formas.

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

Acknowledgements

This work has been partially funded by the Fondos Mixtos Conacyt–Concyteg project "Herramientas mecatrónicas para la implementación de entornos virtuales" Project No. GTO– 2005–C04–18605. The work of Mota–Gutierrez is supported by Mexico's Conacyt scholarship grant No. 253676/213766.

 

References

1. Ayala–Ramirez, V., Garcia–Capulin, C.H., Perez–Garcia, A. & Sanchez–Yanez, R.E. (2006). Circle detection on images using genetic algorithms. Pattern Recognition Letters 27(6), 652–657.         [ Links ]

2. Ayala, V., Hayet, J.B., Lerasle, F. & Devy, M. (2000). Visual localization of a mobile robot in indoor environments using planar landmarks. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000), Takamatsu, Japan, 1, 275–280.         [ Links ]

3. Bradski, G. & Kaehler, A. (2008). Learning OpenCV: Computer Vision with the Open CV Library, CA., USA: O'Reilly.         [ Links ]

4. Canann, S. A., Tristano, J.R. & Staten, M.L. (1998). An approach to combined laplacian and optimization–based smoothing for triangular, quadrilateral, and quaddominant meshes. 7th International Meshing Roundtable, Michigan, U.S.A, 479–494.         [ Links ]

5. Cerri, A., Biasotti, S. & Gorgi, D. (2007). K–dimensional size functions for shape descriptions and comparison. 14th International Conference on Image Analysis and processing (ICIAP2007), Modena, Italy, 795–800.         [ Links ]

6. Fraundorfer, F., Ober, S. & Bischof, H. (2004). Natural, salient image patches for robot localization. 17^th International Conference on Pattern Recognition (ICPR'04), Cambridge UK, 4, 881 –884.         [ Links ]

7. Holland, J.H. (1975). Adaptation in Natural and Artificial Systems. Ann Arbor, MI: University of Michigan Press.         [ Links ]

8. Keller, C.G., Sprunk, C., Bahlmann, C., Giebel, J. & Baratoff, G. (2008) Real–time recognition of U.S. speed signs. 2008 IEEE Intelligent Vehicles Symposium, Eindhoven, The Netherlands, 518–523.         [ Links ]

9. Ko, B.C. & Nam, J.Y. (2006). Automatic object–of–interest segmentation from natural images. 18^th International Conference on Pattern Recognition (ICPR'06), Hong Kong, China, 4, 45–48.         [ Links ]

10. Lazebnik, S., Schmid, C. & Ponce, C. (2006). Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06), New York, USA, 2, 2169–2178.         [ Links ]

11. Lee, C.K. & Lo, S.H. (1994). A new scheme for the generation of a graded quadrilateral mesh. Computers and Structures, 52(5), 847–857.         [ Links ]

12. Murillo, A.C., Kosecka, J., Guerrero, J.J. & Sagues, C. (2008). Visual door detection integrating appearance and shape cues. Robotics and Autonomous Systems, 56(6), 512–521.         [ Links ]

13. Nishida, H. (1996). Shape recognition by integrating structural descriptions and geometrical/statistical transforms. Computer Vision and Image Understanding, 64(2), 248–262.         [ Links ]

14. Orrite, C. & Herrero, J.E. (2004). Shape matching of partially occluded curves invariant under projective transformation. Computer Vision and Image Understanding, 93(1), 34–64.         [ Links ]

15. Ozcan, E. & Mohan, C.K. (1997). Partial shape matching using genetic algorithms. Pattern Recognition Letters, 18(10), 987–992.         [ Links ]

16. Paragios, N., Rousson, M. & Ramesh, V. (2003). Non–rigid registration using distance functions, Computer Vision and Image Understanding, 89(2–3), 142–165.         [ Links ]

17. Prasad, B.G., Biswas, K.K. & Gupta, S.K. (2004). Region–based image retrieval using integrated color, shape and location index. Computer Vision and Image Understanding 94(1–3), 193–233.         [ Links ]

18. Sanchez, A.J. & Martinez, J.M. (2000). Robot–arm pick and place behavior programming system using visual perception. 15th International Conference on Pattern Recognition, Barcelona, Spain, 4, 507–510.         [ Links ]

19. Ser, P.K., Choy, C.S.T. & Siu, W.C. (1999). Genetic algorithm for the extraction of nonanalytic objects from multiple dimensional parameter space. Computer Vision and Image Understanding, 73(1), 1 –13.         [ Links ]

20. Shokoufandeh, A., Bretzner, L., Macrini, D., Demirci, M.F., Jonsson, C. & Dickinson, S. (2006). The representation and matching of categorical shape. Computer Vision and Image Understanding, 103(2), 139–154.         [ Links ]

21. Shotton, J., Blake, A. & Cipolla, R. (2008). Multiscale categorical object recognition using contour fragments. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(7), 1270–1281.         [ Links ]

22. Silapachote, P., Weinman, J., Hanson, A., Weiss, R. & Mattar, M.A. (2005). Automatic sign detection and recognition in natural scenes. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, California, USA, 3, 27.         [ Links ]

23. Sun, Y.N. & Huang, S.C. (2000). Genetic algorithms for error–bounded polygonal approximation. International Journal of Pattern Recognition and Artificial Intelligence, 14(3), 297–314.         [ Links ]

24. Super, B.J. (2002). Fast retrieval of isolated visual shapes. Computer Vision and Image Understanding, 85(1), 1 –21.         [ Links ]

25. Torralba, A., Murphy, K.P., Freeman, W.T. & Rubin, M.A. (2003). Context–based vision system for place and object recognition. Ninth IEEE International Conference on Computer Vision (ICCV03), Nice, France, 273–280.         [ Links ]

26. Tu, Z., Zheng, S. & Yuille, A. (2008). Shape matching and registration by data–driven EM. Computer Vision and Image Understanding, 109(3), 290–304.         [ Links ]

27. Yin, P.Y. (2000). A tabu search approach to polygonal approximation of digital curves. International Journal of Pattern Recognition and Artificial Intelligence, 14(2), 243–255.         [ Links ]