Desarrollo de un método basado en visión por computador para segmentar imágenes de los anillos de crecimiento en la especie Apeiba membranácea.

dc.contributor.advisorEspinosa-Bedoya, Albeirospa
dc.contributor.authorSánchez Aguiar, Andrés Felipespa
dc.contributor.researchgroupGIDIA: Grupo de Investigación y Desarrollo en Inteligencia Artificialspa
dc.coverage.sucursalUniversidad Nacional de Colombia - Sede Medellínspa
dc.date.accessioned2020-01-31T19:57:28Zspa
dc.date.available2020-01-31T19:57:28Zspa
dc.date.issued2019-12-02spa
dc.description.abstractDendrochronology has been a tool of great importance when it comes to ecological studies and has allowed the study of climate and forests around the world. However, this technique was originally developed in temperate zones, which resulted in the bias that rings only occur in zones with seasons. For this reason, studies of growth rings in the tropics are minimal compared to studies outside of it. Due to the difference in the anatomical characteristics of the species within the tropics, it is necessary to create tools focused on these species that allow a greater development of dendrochronology in the tropics. Thus, the development of a method that allows segmenting the growth rings in the Apeiba membranacea species from computer vision techniques is proposed. The process begins by analyzing how to develop the acquisition of the images, finding that the best option for this is by scanning the images at a resolution of 1200 PPP, then the color spaces of these images were evaluated by experts criteria finding that the channels based on intensity are those that best reflect the anatomical characteristics, especially the RGB space, which presents with different levels the anatomical characteristics in each of its channels. Subsequently, different segmentation techniques were analyzed and it was found that the most appropriate is the use of a Ternausnet architecture in different batches weighing the final result. When validating the results against hand segmented images, a Jaccard index of 0.75, an accuracy of 0.85, a sensitivity of 0.85 and a specificity of 0.88 were obtained, concluding that the most appropriate way to address this problem is through the use of different models, trained based on daca one of the anatomical characteristics of the species.spa
dc.description.abstractLa dendrocronología ha sido una herramienta de gran importancia a la hora de hacer estudios ecológicos y ha permitido el estudio del clima y los bosques alrededor del mundo. Sin embargo, esta técnica se desarrolló originalmente en las zonas templadas, lo que resultó en el sesgo de que los anillos solo se presentan en las zonas con estaciones. Por tal razón, los estudios de anillos de crecimiento en el trópico son mínimos en comparación a los estudios fuera de él. Por la diferencia en las características anatómicas de las especies dentro del trópico se ve necesaria la creación de herramientas enfocadas en estas especies que permitan un mayor desarrollo de la dendrocronología en el trópico. Así, se propone el desarrollo de un método que permita segmentar los anillos de crecimiento en la especie Apeiba membranácea a partir de técnicas de visión por computador. El proceso se inicia analizando cómo desarrollar la adquisición de las imágenes, encontrando que la mejor opción para esto es escaneando las imágenes a una resolución de 1200 PPP, posteriormente se evaluó mediante el criterio de expertos los espacios de color de estas imágenes encontrando que los canales basados en intensidad son los que mejor reflejan las características anatómicas, en especial el espacio RGB, que presenta con diferentes niveles las características anatómicas en cada uno de sus canales. Posteriormente, se analizaron diferentes técnicas de segmentación y se encontró que la más adecuada es el uso de una arquitectura Ternausnet en diferentes lotes ponderando el resultado final. Al validar los resultados contra las imágenes segmentadas a mano, se obtuvo un índice de Jaccard de 0.75, una exactitud de 0.85, una sensibilidad de 0.85 y una especificidad de 0.88, concluyendo que la forma más adecuada de abordar este problema es mediante el uso de diferentes modelos, entrenados con base a daca una de las características anatómicas de la especie.spa
dc.format.mimetypeapplication/pdfspa
dc.identifier.urihttps://repositorio.unal.edu.co/handle/unal/75549
dc.language.isospaspa
dc.publisher.branchUniversidad Nacional de Colombia - Sede Medellínspa
dc.relation.referencesKumar Patel, K., Kar, A., Jha, S. N., & Khan, M. A. (2012). Machine vision system: a tool for quality inspection of food and agricultural products. Journal of Food Science and Technology, 123–14.spa
dc.relation.referencesMontana, G., & Brebisson , A. (2015). Deep Neural Networks for Anatomical Brain Segmentation. The IEEE Conference on Computer Vision and Pattern Recognitionspa
dc.relation.referencesBorianne, P., Pernaudat, R., & Subsol, G. (2011). Automated delineation of tree-rings in X-Ray Computed Tomography images of wood. IEEE.spa
dc.relation.referencesCerda, M., Hitschfeld-Kahler, N., & Mery, D. (2007). Robust Tree-Ring Detection. PacificRim Symposium on Image and Video Technology.spa
dc.relation.referencesConner, W., Schowengerdt, R., Munro, M., & Hughes, M. (1998). Design of a computer vision based tree ring dating system. 1998 IEEE Southwest Symposium on Image Analysis and Interpretation, 256-261.spa
dc.relation.referencesDendroecological investigations on Swietenia. (2003). Trees 17, 244-250spa
dc.relation.referencesDerganc, J., Likar, B., Tomaževič, D., & Pernuš, F. (2003). Real-time automated visual inspection of color tablets in pharmaceutical blisters. Real-Time Imaging, 113-124.spa
dc.relation.referencesDünisch, O., Montóia, V., & Bauch, J. (2003). Dendroecological investigations on Swietenia. Trees 17, 244–250.spa
dc.relation.referencesEntacher, K., & Planitzer, D. (2007). Towards an automated generation of tree ring. Proceedings of the 5th International Symposium on, 174–179.spa
dc.relation.referencesFabijańska, A., Barniak, J., Danek, M., & Piórkowski, A. (2017). A Comparative Study of Image Enhancement Methods in Tree-Ring Analysis. researchgate.spa
dc.relation.referencesFichtler, E., & Worbes, M. (2010). Wood anatomy and tree-ring structure and their importance for tropical dendrochronology. Amazonian Floodplain Forests: Ecophysiology, Biodiversity and Sustainable Management, 329-346.spa
dc.relation.referencesHenke, M., & Sloboda, B. (2014). Semiautomatic tree ring segmentation using Active Contours and an optimised gradient operator. Central European Forestry Journal.spa
dc.relation.referencesKamil, R., Malik, A. S., Thong, C.-M., & Mohd Hani, A. F. (2012). A review of SMD-PCB defects and detection algorithms. Fourth International Conference on Machine Vision (ICMV 2011): Computer Vision and Image Analysis; Pattern Recognition and Basic Technologies.spa
dc.relation.referencesKennel, P., Borianne, P., & Subsol, G. (2015). An automated method for tree-ring delineation based on active contours guided by DT-CWT complex coefficients in photographic images: Application to Abies alba wood slice images.spa
dc.relation.referencesLara, W., Bravo, F., & Sierra, C. (2015). measuRing: An R package to measure tree-ring widths from scanned images. Dendrochronologia, 43-50spa
dc.relation.referencesLocosselli, G., Krottenthaler, S., Pitsch, P., Anhuf, D., & Ceccantini, G. (2017). Age and growth rate of congeneric tree species (Hymenaea spp. - Leguminosae) inhabiting different tropical biomes. erdkunde, 45-57.spa
dc.relation.referencesMainieri, C., & Chimelo, J. (1989). Fichas das características das principais madeiras brasileiras. Sao paolo: Instituto de Pesquisas Tecnológicas (IPT.spa
dc.relation.referencesMaioli Barbosa, A. C., Pereira, G. A., Granato-Souza, D., Santos , R. M., & Leite Fontes, M. A. (2018). Tree rings and growth trajectories of tree species from seasonally dry tropical fores. Australian journal of botany, 414-42.spa
dc.relation.referencesMery, D., & Carrasco, M. (2006). Advances on Automated Multiple View Inspection. Pacific-Rim Symposium on Image and Video Technology, 513-522.spa
dc.relation.referencesNgan, H., Pang, G., & Yung, N. (2011). Review article: Automated fabric defect detectionA review. Image and Vision Computing, 442-458 .spa
dc.relation.referencesPons, T., & Helle, G. (2011). Identification of anatomically non-distinct annual rings in tropical trees using stable isotopes. Springer-Verlag.spa
dc.relation.referencesRonneberger, O., Fischer, P, & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, 234–241spa
dc.relation.referencesSheppard, P., & Graumlich, L. (1994). A reflected-light video imaging system for tree-ring analysis of conifers. Tree rings, environment and humanity. Radiocarbon 1996. Proceedings of the International conference, 17-21.spa
dc.relation.referencesSioma, A., & Socha, J. (2016). Automation of annual tree increment measurement using vision system. Drewno 59, 19–30.spa
dc.relation.referencesSundari, P. M., Brito, S., & Kumar, R. (2014). An Approach for Dendroclimatology Using Image Processing Techniques. 2014 World Congress on Computing and Communication Technologies, 234-236.spa
dc.relation.referencesTherrell, M., Stahle, D., Mukelabai, M., & Shugart, H. (2007). Age, and radial growth dynamics of Pterocarpus angolensis in southern Africa. forest ecology and managment, 24-31.spa
dc.relation.referencesTimm, F., & Barth, E. (2012). Novelty detection for the inspection of light-emitting diodes. Expert Systems with Applications.spa
dc.relation.referencesWorbes, M. (1989). Growth rings, increment and age of trees in inundation forests, savanna and a mountain forest in the neotropics. IAWA, 109–122.spa
dc.relation.referencesXu, k., Wang, X., An, H., Sun, H., Han, w., & Li , Q. (2017). Tree-ring widths are good proxies of annual variation in forest productivity in temperate forests. Scientific Reports.spa
dc.relation.referencesZhou, H., Feng, R., Huang, H., Lin, E., & Yu, J. (2012). Method of tree-ring image analysis for dendrochronology. Optical Engineering.spa
dc.rightsDerechos reservados - Universidad Nacional de Colombiaspa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.licenseAtribución-SinDerivadas 4.0 Internacionalspa
dc.rights.licenseAtribución-SinDerivadas 4.0 Internacionalspa
dc.rights.spaAcceso abiertospa
dc.rights.urihttp://creativecommons.org/licenses/by-nd/4.0/spa
dc.subject.ddcIngeniería y operaciones afinesspa
dc.subject.proposalDendrocronología, Visión por computador, Apeiba membranácea, Aprendizaje profundo, Segmentaciónspa
dc.titleDesarrollo de un método basado en visión por computador para segmentar imágenes de los anillos de crecimiento en la especie Apeiba membranácea.spa
dc.typeDocumento de trabajospa
dc.type.coarhttp://purl.org/coar/resource_type/c_8042spa
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aaspa
dc.type.contentTextspa
dc.type.driverinfo:eu-repo/semantics/workingPaperspa
dc.type.redcolhttp://purl.org/redcol/resource_type/WPspa
dc.type.versioninfo:eu-repo/semantics/acceptedVersionspa
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2spa

Archivos

Bloque original

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
1037629866.2019.pdf
Tamaño:
2.31 MB
Formato:
Adobe Portable Document Format
Descripción:
Tesis de Maestría en Ingeniería - Ingeniería de Sistemas

Bloque de licencias

Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
3.9 KB
Formato:
Item-specific license agreed upon to submission
Descripción: