Method for evaluation of coarse cork oak root system by means of digital imaging
- 186 Downloads
Digital imaging is becoming a powerful tool for data storage and information retrieval. Image comparison and similarity evaluation has become part of the information market and it is today a common part of, for example, web search engines. The cork oak tree (Quercus suber L.), the dominant species of the ‘montado’ woodland system is, due to its cultural and socio-economic value, protected by law that prevents extensive destructive studies on an essential part of the tree—the root. Especially in the Mediterranean zone, where the water is the limiting growth factor, the root development studies are of significant interest. In this work we present a method of using digital images for cork oak coarse root systems-evaluation by means of digital imaging. Acquired images of structural roots are processed automatically to prevent subjective decisions by the human observer. The performance of the method, its potential for semantic retrieval and similarity assessment is demonstrated, having as example eight young cork oak root systems, and critical issues for evaluation and conclusion-making, are discussed.
KeywordsCoarse root system Cork oak Digital image Image similarity
This work was done with the support of the following projects: Agroreg – natural and artificial regeneration of montados (www.agroreg.uevora.pt) and Transsub – root systems of cork oak and transplant of adult trees (www.transsub.uevora.pt). The first author would like to acknowledge FCT (Fundaçao de Ciencia e Tecnologia) for funding the research, through grant SFRH/BPD/29953/2006.
- Ferreira A, Gonçalves AG (2001) Plano específico de ordenamento florestal para o alentejo. Universidade Evora, Evora, p 200Google Scholar
- Genis A, Blumberg DG, Ben-Asher J (2006) Optimizing application of image analysis tools to determine physical characteristics of fine roots. Environ Control Biol 44(1):11–20Google Scholar
- Goldberger J, Gordon S, Greenspan H (2003) An efficient image similarity measure based on approximations of KL-divergence between two gaussian mixtures. In: Proceeding of Ninth IEEE International Conference on Computer Vision, vol 1.pp 487–493Google Scholar
- Gonzalez RC, Woods RE (1992) Digital image processing. Addison-Wesley Publishing Company, Massachusetts, p 716Google Scholar
- Ribeiro NA, Gonçalves AC, Dias SS, Afonso T, Ferreira AG (2003) Multilevel monitoring systems for cork oak (Quercus suber L.) stands in Portugal. In: Corona P, Köhl M, Marchetti M (eds) Advances in forest inventory for sustainable forest management and biodiversity monitoring. Kluwer Academic Publishers, The Netherlands, pp 395–404Google Scholar
- Surovy P (2006) Modeling the horizontal structure of forest by means of geostatistic and digital image analysis. Dissertation thesis, Technical University of Zvolen, p 65Google Scholar
- Surovy P, Brasil F, Ribeiro NA, Oliveira MRG (2007) Avaliação da morfologia dos sistemas radicais de plantas de regeneração do sobreiro através de imagem digital. Revista Ciências Agrárias, pp 290–295Google Scholar
- van Noordwijk M, Brouwer G, Meijboom F, Oliveira MRG, Bengough AG (2000) Trench profile techniques and core break methods. In: Smit AL et al (eds) Root methods A: handbook. Springer-Verlag Heidelberg, New York, pp 211–233Google Scholar
- Wang Y-H (2003) Image indexing and similarity retrieval based on spatial relationship model. Information sciences—informatics and computer science. Int J Arch 154(1-2):39–58Google Scholar
- Zhang D-Q, Chang S-F (2004) Detecting image near-duplicate by stochastic attributed relational graph matching with learning. In: Proceedings of the 12th annual ACM international conference on Multimedia. pp 877–884Google Scholar