Feature Extraction Languages and Visual Pattern Recognition

Aus de_evolutionary_art_org
Version vom 14. Januar 2015, 11:15 Uhr von Gbachelier (Diskussion | Beiträge)

(Unterschied) ← Nächstältere Version | Aktuelle Version (Unterschied) | Nächstjüngere Version → (Unterschied)
Wechseln zu: Navigation, Suche


M. Maghoumi and Brian J. Ross: Feature Extraction Languages and Visual Pattern Recognition. Brock COSC TR CS-14-03, January 2014.



Visual pattern recognition and classification is a challenging com- puter vision problem. Genetic programming has been applied to- wards automatic visual pattern recognition. An important factor in evolving effective classifiers is the suitability of the GP lan- guage for defining expressions for feature extraction and classifi- cation. This research presents a comparative study of a variety of GP languages suitable for classification. Four different languages are examined, which use different selections of image processing operators. One of the languages does block classification, which means that an entire region of pixels is classified simultaneously. The other languages are pixel classifiers, which determine classifi- cation for a single pixel. Pixel classifiers are more common in the GP-vision literature. We tested the languages on different instances of Brodatz textures, as well as aerial and camera images. Our re- sults show that the most effective languages are pixel-based ones with spatial operators. However, as is to be expected, the nature of the image will naturally determine the effectiveness of the language used.

Extended Abstract


Used References

[1] P. Brodatz. Textures: a photographic album for artists and designers, volume 66. Dover New York, 1966.

[2] M. Ebner. A real-time evolutionary object recognition system. In Proceedings of the 12th European Conference on Genetic Programming, EuroGP ’09, pages 268–279, Berlin, Heidelberg, 2009. Springer-Verlag.

[3] M. Ebner. Towards automated learning of object detectors. In Proceedings of the 2010 international conference on Applications of Evolutionary Computation - Volume Part I, EvoApplicatons’10, pages 231–240, Berlin, Heidelberg, 2010. Springer-Verlag.

[4] P. Espejo, S. Ventura, and F. Herrera. A survey on the application of genetic programming to classification. Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on, 40(2):121–144, 2010.

[5] N. Harvey, S. Perkins, S. Brumby, J. Theiler, R. Porter, A. Cody Young, A. Varghese, J. Szymanski, and J. Bloch. Finding golf courses: The ultra high tech approach. In S. Cagnoni, editor, Real-World Applications of Evolutionary Computing, volume 1803 of Lecture Notes in Computer Science, pages 54–64. Springer Berlin Heidelberg, 2000.

[6] D. Howard, S. C. Roberts, and R. Brankin. Target detection in sar imagery by genetic programming. Adv. Eng. Softw., 30(5):303–311, May 1999.

[7] T. Loveard and V. Ciesielski. Representing classification problems in genetic programming. In Evolutionary Computation, 2001. Proceedings of the 2001 Congress on, volume 2, pages 1070–1077 vol. 2, 2001.

[8] D. Montana. Strongly Typed Genetic Programming. Evolutionary Computation, 3(2):199–230, 1995.

[9] J. Nickolls, I. Buck, M. Garland, and K. Skadron. Scalable parallel programming with cuda. Queue, 6(2):40–53, Mar. 2008.

[10] R. Poli. Genetic programming for feature detection and image segmentation. In T. Fogarty, editor, Evolutionary Computing, volume 1143 of Lecture Notes in Computer Science, pages 110–125. Springer Berlin Heidelberg, 1996.

[11] R. Poli. Genetic programming for image analysis. In Proceedings of the First Annual Conference on Genetic Programming, pages 363–368. MIT Press, 1996.

[12] B. Ross, A. Gualtieri, F. Fueten, and P. Budkewitsch. Hyperspectral Image Analysis Using Genetic Programming. Applied Soft Computing, 5(2):147–156, 2005.

[13] A. Song. Texture Classification: a Genetic Programming Approach. PhD thesis, RMIT University, April 2003.

[14] A. Song and V. Ciesielski. Fast texture segmentation using genetic programming. In Evolutionary Computation, 2003. CEC ’03. The 2003 Congress on, volume 3, pages 2126–2133 Vol.3, 2003.

[15] A. Song and V. Ciesielski. Texture analysis by genetic programming. In Evolutionary Computation, 2004. CEC2004. Congress on, volume 2, pages 2092–2099 Vol.2, 2004.

[16] A. Song, T. Loveard, and V. Ciesielski. Towards genetic programming for texture classification. In M. Stumptner, D. Corbett, and M. Brooks, editors, AI 2001: Advances in Artificial Intelligence, volume 2256 of Lecture Notes in Computer Science, pages 461–472. Springer Berlin Heidelberg, 2001.

[17] W. A. Tackett. Genetic programming for feature discovery and image discrimination. In Proceedings of the 5th International Conference on Genetic Algorithms, pages 303–311, San Francisco, CA, USA, 1993. Morgan Kaufmann Publishers Inc.

[18] J. F. Winkeler and B. Manjunath. Genetic programming for object detection. In Genetic Programming 1997: Proceedings of the Second Annual Conference, pages 330–335. Morgan Kaufmann, 1997.


Full Text


intern file

Sonstige Links