ABSTRACT
Nowadays, object recognition is widely studied under the paradigm of matching local features. This work describes a genetic programming methodology that synthesizes mathematical expressions that are used to improve a well known local descriptor algorithm. It follows the idea that object recognition in the cerebral cortex of primates makes use of features of intermediate complexity that are largely invariant to change in scale, location, and illumination. These local features have been previously designed by human experts using traditional representations that have a clear, preferably mathematically, well-founded definition. However, it is not clear that these same representations are implemented by the natural system with the same structure. Hence, the possibility to design novel operators through genetic programming represents an open research avenue where the combinatorial search of evolutionary algorithms can largely exceed the ability of human experts. This paper provides evidence that genetic programming is able to design new features that enhance the overall performance of the best available local descriptor. Experimental results confirm the validity of the proposed approach using a widely accept testbed and an object recognition application.
- ]]S. Agarwal and D. Roth. Learning a sparse representation for object detection. In Proceedings of the Seventh European Conference on Computer Vision. LNCS: 2353, pages 97--101, 2002. Google ScholarDigital Library
- ]]H. Bay, T. Tuytelaars, and L. V. Gool. Surf: Speeded up robust features. ECCV, 3951:404--417, 2006. Google ScholarDigital Library
- ]]N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In CVPR - Volume 1, pages 886--893, Washington, DC, USA, 2005. Google ScholarDigital Library
- ]]M. Ebner. An adaptive on-line evolutionary visual system. IEEE Workshop on Pervasive Adaptation, pages 84--89, 2008. Google ScholarDigital Library
- ]]B. Gokberk, M. Irfanolglu, L. Akarun, and E. Alpaydin. Learning the best subset of local features for face recognition. Pattern Recognition, 40:1520--1532, 2006. Google ScholarDigital Library
- ]]D. Howard, S. C. Roberts, and R. Brankin. Target detection in sar imagery by genetic programming. Advances in Engineering Software, 30(5):303--311, 1999. Google ScholarDigital Library
- ]]D. Howard, S. C. Roberts, and C. Ryan. The boru data crawler for object detection tasks in machine vision. EvoWorkshops. LNCS: 2279, pages 222--232, 2002. Google ScholarDigital Library
- ]]Y. Ke and R. Sukthankar. Pca-sift: A more distinctive representation for local image descriptors. In CVPR, 27 June - 2 July,Washington,DC, volume 2, pages 506--513. IEEE Computer Society, 2004. Google ScholarDigital Library
- ]]J. J. Koenderinkand A. J. V. Doorn. Representationof local geometry in the visual system. Biological Cybernetics, 55(3):367--375, 1987. Google ScholarDigital Library
- ]]K. Krawiec and B. Bhanu. Visual learning by coevolutionary feature synthesis. IEEE Trans. on Systems, Man, and Cybernetics-Part B: Cybernetics, 35(3):409--425, 2005. Google ScholarDigital Library
- ]]Y. Lin and B. Bhanu. Evolutionary feature synthesis for object recognition. IEEE Trans. on Systems, Man, and Cybernetics-Part C: Apps and Revs, 35(2):156--171, 2005. Google ScholarDigital Library
- ]]Y. Lin and B. Bhanu. Object detection via feature synthesis using mdl-based genetic programming. IEEE Trans. on Systems, Man, and Cybernetics-Part B: Cybernetics, 35(3):538--547, 2005. Google ScholarDigital Library
- ]]D. Lowe. Object recognition from local scale-invariant features. ICCV, pages 1150--1157, 1999. Google ScholarDigital Library
- ]]K. Mikolajczyk and C. Schmid. A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(10):1615--1630, 2005. Google ScholarDigital Library
- ]]C. B. Perez and G. Olague. Learning invariant region descriptor operators with genetic programming and the f-measure. International Conference on Pattern Recognition, December 8-11 2008.Google ScholarCross Ref
- ]]R. Poli, W. Langdon, and N. Freitag. A field guide to genetic programming. Published via http://lulu.com and freely available at http://www.gp-field-guide.org.uk, 2008. Google ScholarDigital Library
- ]]J. R. Koza. Genetic Programming. The MIT Press., 1993. Google ScholarDigital Library
- ]]C. Schmid and R. Mohr. Local grayvalue invariants for image retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(5):530--534, 1997. Google ScholarDigital Library
- ]]E. Tola, V. Lepetit, and P. Fua. A fast local descriptor for dense matching. In CVPR, 23-28 June, Anchorage, AK. IEEE Computer Society, 2008.Google Scholar
- ]]L. Trujillo and G. Olague. Synthesis of interest point detectors through genetic programming. Genetic and Evolutionary Computation Conference, pages 887--894, 2006. Google ScholarDigital Library
- ]]C. Van-Rijsbergen. Information retrieval.Ed. Butterworth-Heinemann. Second Edition, 1979. Google ScholarDigital Library
- ]]S. Winder and M. Brown. Learning local image descriptors. IEEE Conf. on CVPR, pages 1--8, 2007.Google ScholarCross Ref
- ]]M. Zhang. Genetic programming for object detection: A two-phase approach with an improved fitness function. Electronic Letters on Computer Vision and Image Analysis, 6(1):27--43, 2007.Google ScholarCross Ref
- ]]M. Zhang, V. B. Ciesielski, and P. Andreae. A domain-independent window approach to multiclass object detection using genetic programming. EURASIP Journal on Applied Signal Processing, 2003(8):841--859, 2003. Google ScholarDigital Library
Index Terms
- Evolutionary learning of local descriptor operators for object recognition
Recommendations
Random interest regions for object recognition based on texture descriptors and bag of features
In this work we propose a novel method for object recognition based on a random selection of interest regions, texture features (local binary/ternary patterns and local phase quantization) for describing each region, a bag-of-features approach for ...
An improved local feature descriptor based on SIFT
ICIMCS '10: Proceedings of the Second International Conference on Internet Multimedia Computing and ServiceConstructing proper descriptors for interest points is a critical aspect for local features related tasks in some computer vision and pattern recognition. This paper proposed to improve the SIFT descriptor by means of combining the second derivative and ...
Evolving Local Descriptor Operators through Genetic Programming
EvoWorkshops '09: Proceedings of the EvoWorkshops 2009 on Applications of Evolutionary Computing: EvoCOMNET, EvoENVIRONMENT, EvoFIN, EvoGAMES, EvoHOT, EvoIASP, EvoINTERACTION, EvoMUSART, EvoNUM, EvoSTOC, EvoTRANSLOGThis paper presents a new methodology based on Genetic Programming that aims to create novel mathematical expressions that could improve local descriptors algorithms. We introduce the RDGP-ILLUM descriptor operator that was learned with two image pairs ...
Comments