Desarrollo de un prototipo funcional de software para estimar la producción de cacao, haciendo uso de herramientas de aprendizaje profundo y visión por computador

dc.contributor.advisorTalero Sarmiento, Leonardo Hernán
dc.contributor.advisorParra Sánchez, Diana Teresa
dc.contributor.advisorMoreno Corzo, Feisar Enrique
dc.contributor.advisorNieves Peña, Néstor Edsgardo
dc.contributor.authorCala Pinzón, Karol Daniela
dc.contributor.authorHernández Flórez, Lisseth Andrea
dc.contributor.authorParra Muñoz, Cristian David
dc.contributor.cvlacTalero Sarmiento, Leonardo Hernán [0000031387]spa
dc.contributor.cvlacParra Sánchez, Diana Teresa [0001476224]spa
dc.contributor.cvlacMoreno Corzo, Feisar Enrique [0001499008]spa
dc.contributor.cvlacNieves Peña, Néstor Edsgardo [0001597250]spa
dc.contributor.googlescholarParra Sánchez, Diana Teresa [es&oi=ao]spa
dc.contributor.googlescholarMoreno Corzo, Feisar Enrique [es&oi=ao]spa
dc.contributor.orcidTalero Sarmiento, Leonardo Hernán [0000-0002-4129-9163]spa
dc.contributor.orcidParra Sánchez, Diana Teresa [0000-0002-7649-0849]spa
dc.contributor.orcidMoreno Corzo, Feisar Enrique [0000-0002-5007-3422]spa
dc.contributor.researchgateTalero Sarmiento, Leonardo Hernán [Leonardo-Talero]spa
dc.contributor.researchgateParra Sánchez, Diana Teresa [Diana-Parra-Sanchez-2]spa
dc.contributor.scopusParra Sánchez, Diana Teresa [57195677014]spa
dc.coverage.campusUNAB Campus Bucaramangaspa
dc.coverage.spatialColombiaspa
dc.date.accessioned2022-03-25T20:48:37Z
dc.date.available2022-03-25T20:48:37Z
dc.date.issued2021
dc.degree.nameIngeniero de Sistemasspa
dc.description.abstractEste proyecto, presenta el diseño y desarrollo de una aplicación móvil funcional capaz de estimar la producción de cacao, que propone la implementación de técnicas de visión por computador y aprendizaje profundo. Esto se debe a que la detección de objetos en la agricultura es importante para estimar la producción de un cultivo, porque incrementa la certeza en la toma de decisiones por parte de un agricultor, por consiguiente, el diseño propuesto realiza un conteo de las mazorcas de cacao que se encuentran en tres estados de sanidad, ya sea con presencia de monilia, fitóftora o completamente sanas. La aplicación planteada hace uso de una cámara de un dispositivo móvil y el sistema operativo Android. Los elementos presentes en el sistema, son un modelo de aprendizaje de máquina entrenado, un conjunto de datos, y tecnologías que apoyan el proceso de desarrollo de software. En primera instancia, se realiza una revisión de la literatura para profundizar sobre las técnicas, tecnologías, y métricas asociadas con visión artificial y que puedan ser aplicadas en el proyecto. Luego, se propone la selección de un conjunto de imágenes con Theobroma cacao. Asimismo, se plantea la adaptación de un modelo de aprendizaje profundo con una definición de parámetros e hiper parámetros, para posteriormente proponer un diseño y desarrollo de un prototipo móvil que detecta, clasifica y localiza las mazorcas de cacao con sus respectivos estados de sanidad, y a su vez estima la producción en términos de kilogramos de granos de cacao seco, teniendo en cuenta la variedad indicada por el usuario. Los resultados obtenidos dejan la evaluación de 8 modelos, en donde el mejor obtiene una mAP de 80.09% y se determina la incidencia de variables asociadas al balanceo sobre la precisión.spa
dc.description.abstractenglishThis project presents the design and development of a functional mobile application capable to estimate cocoa production based on the implementation of computer vision and deep learning techniques. Object detection in agriculture is important to estimate production in a crop because it increases the confidence in decision making by a farmer, therefore, the proposed design performs a count of cocoa pods that are in three sanitary states, either with the presence of monilia, phytophthora or completely healthy. The following application implements an Android mobile device camera. The elements existing in the system contain an object detection model, a dataset, and technologies that support the software development process. A literature review is done to explore techniques, technologies, and metrics associated with computer vision. Subsequently, a selection of an image dataset is done to train a deep learning model, setting up parameters and hyperparameters. Consequently, a design and development of a mobile prototype are proposed to detect, classify, and localize cocoa pods with their respective health status, and it returns the estimated value of production given in kilograms of dry cocoa beans, taking into account the variety indicated by the user. The results show the evaluation of 8 models, where the best one obtains a mAP of 80.09% and the incidence of variables associated with the balancing on the accuracy is determined.spa
dc.description.degreelevelPregradospa
dc.description.learningmodalityModalidad Presencialspa
dc.description.tableofcontents1 INTRODUCCIÓN 13 2 PLANTEAMIENTO DEL PROBLEMA 14 3 OBJETIVOS 17 3.1 OBJETIVO GENERAL ............................................................................. 17 3.2 OBJETIVOS ESPECÍFICOS .................................................................... 17 4 MARCO REFERENCIAL 18 4.1 MARCO CONCEPTUAL .......................................................................... 18 4.1.1 Visión por Computador (Computer Vision) 18 4.1.2 Theobroma Cacao 18 4.1.3 Producción de cacao 18 4.1.4 Red Neuronal (Neural Network) 18 4.2 MARCO TEÓRICO ................................................................................... 18 4.2.1 Periodo De Producción (Cacao) 18 4.2.2 Variedades De Cacao 19 4.2.3 Rendimiento De Cacao. 21 4.2.4 Espacios De Color 21 4.2.5 Métodos de preprocesamiento de imágenes 23 4.2.6 Representación De Imágenes Digitales 25 4.2.7 Operaciones Matriciales Y Vectoriales 26 4.2.8 Borde 26 4.2.9 Inteligencia Artificial 26 4.2.10 Data Agumentation 27 4.2.11 Aprendizaje Automático 30 4.2.12 Redes Neuronales 30 4.2.13 Aprendizaje Profundo 32 4.2.14 Redes Neuronales Convolucionales 32 4.2.15 YOLO 33 4.2.16 Colab 34 4.2.17 Android Studio 34 4.2.18 LabelImg 35 5 METODOLOGÍA 36 6 ANÁLISIS DEL ESTADO DEL ARTE 38 6.1 ANÁLISIS DETALLADO DEL ESTADO DEL ARTE ............................... 49 7 ADAPTACIÓN DEL MODELO DE APRENDIZAJE 53 7.1 ADQUISICIÓN DE DATOS ...................................................................... 53 7.2 ANÁLISIS Y SELECCIÓN DEL CONJUNTO DE DATOS PARA EL ENTRENAMIENTO .......................................................................................... 55 7.3 LIMPIEZA Y ETIQUETADO ..................................................................... 57 7.4 ELECCIÓN DEL MODELO DE APRENDIZAJE MÁQUINA .................... 58 7.5 DESCRIPCIÓN DE YOLOv4 .................................................................... 60 7.6 ENTRENAMIENTO................................................................................... 62 7.7 DEPENDENCIAS DEL ENTRENAMIENTO ............................................. 64 7.8 CONFIGURACIÓN DEL ENTORNO DE EJECUCIÓN ............................ 65 7.9 CARGA Y PREPARACIÓN DEL CONJUNTO DE IMÁGENES ............... 66 7.10 CONFIGURACIÓN DE LA RED NEURONAL .......................................... 67 7.11 PESOS PREENTRENADOS .................................................................... 68 7.12 EJECUCIÓN DEL ENTRENAMIENTO ..................................................... 68 7.13 EVALUACIÓN DEL MODELO ................................................................. 69 7.14 CONVERSIÓN .......................................................................................... 71 7.15 ADAPTACIÓN DEL MODELO ................................................................. 72 8 DISEÑO Y DESARROLLO DEL PROTOTIPO 73 8.1 RECOLECCIÓN DE REQUISITOS .......................................................... 73 8.1.1 Requerimientos funcionales 73 8.1.2 Requerimientos no funcionales 74 8.2 DIAGRAMA DE COMPONENTES ........................................................... 74 8.3 DIAGRAMA DE CASOS DE USO ............................................................ 75 8.4 DIAGRAMA DE SECUENCIA .................................................................. 76 8.5 DISEÑO .................................................................................................... 77 8.6 DESARROLLO DEL PROTOTIPO........................................................... 78 8.7 EVALUACIÓN DEL PROTOTIPO ............................................................ 78 9 DISCUSIÓN 79 10 CONCLUSIONES 81 11 REFERENCIAS 83 ANEXOS 90spa
dc.format.mimetypeapplication/pdfspa
dc.identifier.instnameinstname:Universidad Autónoma de Bucaramanga - UNABspa
dc.identifier.reponamereponame:Repositorio Institucional UNABspa
dc.identifier.repourlrepourl:https://repository.unab.edu.cospa
dc.identifier.urihttp://hdl.handle.net/20.500.12749/16073
dc.language.isospaspa
dc.publisher.facultyFacultad Ingenieríaspa
dc.publisher.grantorUniversidad Autónoma de Bucaramanga UNABspa
dc.publisher.programPregrado Ingeniería de Sistemasspa
dc.relation.referencesAlexeyAB/darknet: YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet). (2020). Retrieved May 5, 2021, from https://github.com/AlexeyAB/darknetspa
dc.relation.referencesAli Süzen, A., Gürfidan, R., Kayaalp, K., & Ali Şimşek, M. (2020). Information Technology and Computer Science. Information Technology and Computer Science, 2, 18–23. https://doi.org/10.5815/ijitcs.2020.02.02spa
dc.relation.referencesAndriod Developers. (2020). Android Studio. https://developer.android.com/studio/spa
dc.relation.referencesAndroid Studio Developer. (2020). Introducción a Android Studio. https://developer.android.com/studio/intro#top_of_pagespa
dc.relation.referencesArgout, X., Salse, J., Aury, J.-M., Guiltinan, M. J., Droc, G., Gouzy, J., Allegre, M., Chaparro, C., Legavre, T., Maximova, S. N., Abrouk, M., Murat, F., Fouet, O., Poulain, J., Ruiz, M., Roguet, Y., Rodier-Goud, M., Barbosa-Neto, J. F., Sabot, F., … Lanaud, C. (2011). The genome of Theobroma cacao. Nature Genetics, 43(2), 101–108. https://doi.org/10.1038/ng.736spa
dc.relation.referencesBargoti, S., & Underwood, J. P. (2017). Image Segmentation for Fruit Detection and Yield Estimation in Apple Orchards. Journal of Field Robotics, 34(6), 1039– 1060. https://doi.org/https://doi.org/10.1002/rob.21699spa
dc.relation.referencesBeitzel, S. M., Jensen, E. C., & Frieder, O. (2009). MAP. Encyclopedia of Database Systems. (2009). In Encyclopedia of Database Systems. Springer US. https://doi.org/10.1007/978-0-387-39940spa
dc.relation.referencesBhardwaj, K. K., Banyal, S., & Sharma, D. K. (2019). Chapter 7 - Artificial Intelligence Based Diagnostics, Therapeutics and Applications in Biomedical Engineering and Bioinformatics (V. E. Balas, L. H. Son, S. Jha, M. Khari, & R. B. T.-I. of T. in B. E. Kumar (eds.); pp. 161–187). Academic Press. https://doi.org/https://doi.org/10.1016/B978-0-12-817356-5.00009-7spa
dc.relation.referencesBochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (n.d.). YOLOv4: Optimal Speed and Accuracy of Object Detection. Retrieved May 1, 2021, from https://arxiv.org/abs/2004.10934spa
dc.relation.referencesBresilla, K., Perulli, G. D., Boini, A., Morandi, B., Grappadelli, L. C., & Manfrini, L. (2020). Comparing deep-learning networks for apple fruit detection to classical hard-coded algorithms. Acta Horticulturae, 1279, 209–216. https://doi.org/10.17660/ActaHortic.2020.1279.31spa
dc.relation.referencesBurger, W., & Burge, M. J. (2016). Digital image processing: an algorithmic introduction using Java. Springer.spa
dc.relation.referencesBuzzy, M., Thesma, V., Davoodi, M., & Mohammadpour Velni, J. (2020). Real-Time Plant Leaf Counting Using Deep Object Detection Networks. In Sensors (Vol. 20, Issue 23). https://doi.org/10.3390/s20236896spa
dc.relation.referencesCai, Y., Li, H., Yuan, G., Niu, W., Li, Y., Tang, X., & Wang, Y. (2021). YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design. www.aaai.orgspa
dc.relation.referencesCecotti, H., Rivera, A., Farhadloo, M., & Pedroza, M. A. (2020). Grape detection with convolutional neural networks. Expert Systems with Applications, 159, 113588. https://doi.org/10.1016/j.eswa.2020.113588spa
dc.relation.referencesCMake. (2021). Retrieved May 5, 2021, from https://cmake.org/spa
dc.relation.referencesColorizer. (2020). http://colorizer.org/spa
dc.relation.referencesCUDA Zone | NVIDIA Developer. (2021). Retrieved May 5, 2021, from https://developer.nvidia.com/cuda-zonespa
dc.relation.referencesDe La Cruz Medina, J., Vargas Ortiz, M., Del Angel Coronel, O. (2011). CACAO: Operaciones Poscosecha. http://www.fao.org/3/a-au995sspa
dc.relation.referencesDostert, N., Asunción Cano, José Roque., La Torre, María I., W. M. (2011, October). Hoja botánica: Cacao. http://www.botconsult.com/downloads/Hoja_Botanica_Cacao_2012.pdfspa
dc.relation.referencesEveringham, M., Luc, ·, Gool, V., Christopher, ·, Williams, K. I., Winn, J., Zisserman, A., Everingham, M., Van Gool, L., Leuven, K. U., Williams, B. C. K. I., Winn, J., & Zisserman, A. (2010). The PASCAL Visual Object Classes (VOC) Challenge. Retrieved May 5, 2021, from http://www.flickr.com/spa
dc.relation.referencesFactors influencing smallholder cocoa production: a management analysis of behavioural decision-making processes of technology adoption and application. (1996). Retrieved September 4, 2020, from https://library.wur.nl/WebQuery/wurpubs/35987spa
dc.relation.referencesFAOSTAT. (n.d.). Retrieved April 13, 2021, from http://www.fao.org/faostat/en/#data/QC/metadatspa
dc.relation.referencesFEDECACAO y los Cacaocultores, le apuestan a la certificación en Buenas Prácticas Agrícolas. (Abril de 2019). Colombia Cacaotera, p.6. Recuperado de www.fedecacao.com.cospa
dc.relation.referencesFedecacao. (2005). CARACTERIZACIÓN FISÍCOQUÍMICA Y BENEFICIO DEL GRANO DE CACAO (Theobroma cacao L.) EN COLOMBIA. https://www.fedecacao.com.co/portal/images/recourses/pub_doctecnicos/fe decacao-pub-doc_09B.pdfspa
dc.relation.referencesFountain, A., & Hütz-Adams, F. (2015). 2015 Cocoa Barometer (USA edition). Retrieved from Barometer Consortium website: http://evols.library.manoa.hawaii.edu/handle/10524/48573spa
dc.relation.referencesFountain, A., & Hütz-Adams, F. (2018). Cocoa Barometer 2018. Retrieved from VOICE Network website: https://www.voicenetwork.eu/wpcontent/uploads/2019/07/2018-Cocoa-Barometer.pdfspa
dc.relation.referencesFountain, A., & Hütz-Adams, F. (2020). Cocoa Barometer 2020. Retrieved from VOICE Network website: https://www.voicenetwork.eu/wpcontent/uploads/2021/03/2020-Cocoa-Barometer-EN.pdfspa
dc.relation.referencesFranceschetti, D. R. (Ed.). (2018). Principles of Robotics & Artificial Intelligencespa
dc.relation.referencesFu, L., Gao, F., Wu, J., Li, R., Karkee, M., & Zhang, Q. (2020, October 1). Application of consumer RGB-D cameras for fruit detection and localization in field: A critical review. Computers and Electronics in Agriculture, Vol. 177, p. 105687. https://doi.org/10.1016/j.compag.2020.105687spa
dc.relation.referencesGayi, S. K., & Tsowou, K. (2017). Cocoa Industry. https://doi.org/10.18356/cfb75b0e-enspa
dc.relation.referencesGené-Mola, J., Gregorio, E., Auat Cheein, F., Guevara, J., Llorens, J., SanzCortiella, R., Escolà, A., & Rosell-Polo, J. R. (2020). Fruit detection, yield prediction and canopy geometric characterization using LiDAR with forced air flow. Computers and Electronics in Agriculture, 168. https://doi.org/10.1016/j.compag.2019.105121spa
dc.relation.referencesGonzalez, R. C., & Woods, R. E. (2018). Digital Image Processing (Fourth).spa
dc.relation.referencesGoogle Colaboratory. (2020). Google Colaboratory. https://colab.research.google.com/notebooks/intro.ipynb#recent=truespa
dc.relation.referencesHabibi Aghdam, H., & Jahani Heravi, E. (2017). Guide to Convolutional Neural Networks. Springer International Publishing. https://doi.org/10.1007/978-3319-57550-6spa
dc.relation.referencesHeredia Gómez, J. F., & Talero Sarmiento, L. H. (2020). Cocoa Ripeness Dataset TCS 01. https://www.kaggle.com/juanfelipeheredia/cocoa-ripeness-datasettcs-01spa
dc.relation.referencesHùng, V. (2020). Tensorflow-yolov4-tflite. https://github.com/hunglc007/tensorflowyolov4-tflitespa
dc.relation.referencesILRF (2014). The fairness gap: Farmer incomes and solutions to child labor in cocoa. Washington, DC, International Labor Rights Forumspa
dc.relation.referencesJhuria, M., Kumar, A., & Borse, R. (2013). Image processing for smart farming: Detection of disease and fruit grading. 2013 IEEE Second International Conference on Image Information Processing (ICIIP-2013), 521–526. https://doi.org/10.1109/ICIIP.2013.6707647spa
dc.relation.referencesJiang, Z., Zhao, L., Li, S., Jia, Y., & Liquan, Z. (n.d.). Real-time object detection method for embedded devices.spa
dc.relation.referencesKang, H., & Chen, C. (2020). Fast implementation of real-time fruit detection in apple orchards using deep learning. Computers and Electronics in Agriculture, 168, 105108. https://doi.org/10.1016/j.compag.2019.105spa
dc.relation.referencesKim, P. (2017). Deep Learning BT - MATLAB Deep Learning: With Machine Learning, Neural Networks and Artificial Intelligence. Apress. https://doi.org/10.1007/978-1-4842-2845-6_5spa
dc.relation.referencesKirk, R., Cielniak, G., & Mangan, M. (2020). L*a*b*Fruits: A Rapid and Robust Outdoor Fruit Detection System Combining Bio-Inspired Features with OneStage Deep Learning Networks. In Sensors (Vol. 20, Issue 1). https://doi.org/10.3390/s20010275spa
dc.relation.referencesKoirala, A., Walsh, K. B., Wang, Z., & McCarthy, C. (2019). Deep learning – Method overview and review of use for fruit detection and yield estimation. In Computers and Electronics in Agriculture (Vol. 162, pp. 219–234). Elsevier B.V. https://doi.org/10.1016/j.compag.2019.04.017spa
dc.relation.referencesKonica Minolta. (2020). Entendiendo El Espacio de Color CIE L*A*B*. https://sensing.konicaminolta.us/mx/blog/entendiendo-el-espacio-de-colorcie-lab/spa
dc.relation.referencesKrig, S. (2014). Computer Vision Metrics: Survey, Taxonomy, and Analysis (Vol. 9781430259305). https://doi.org/10.1007/978-1-4302-5930-5spa
dc.relation.referencesLiu, X., Chen, S. W., Liu, C., Shivakumar, S. S., Das, J., Taylor, C. J., … Kumar, V. (2019). Monocular Camera Based Fruit Counting and Mapping with Semantic Data Association. IEEE Robotics and Automation Letters, 4(3), 2296–2303. https://doi.org/10.1109/LRA.2019.2901987spa
dc.relation.referencesMaldonado, W., & Barbosa, J. C. (2016). Automatic green fruit counting in orange trees using digital images. Computers and Electronics in Agriculture, 127, 572–581. https://doi.org/10.1016/j.compag.2016.07.spa
dc.relation.referencesMartínez Guerrero, N. (2016). Aportes de la investigación de FEDECACAO –Fondo Nacional del Cacao al incremento de la productividad y reconocimiento de la calidad del cacao de Colombiaspa
dc.relation.referencesMitchell, T. M. (1997). Machine Learning. McGraw-Hill Science/Engineering/Mathspa
dc.relation.referencesMite-Baidal, K., Solís-Avilés, E., Martínez-Carriel, T., Marcillo-Plaza, A., Cruz-Ibarra, E., & Baque-Bustamante, W. (2019). Analysis of Computer Vision Algorithms to Determine the Quality of Fermented Cocoa (Theobroma Cacao): Systematic Literature Review. Advances in Intelligent Systems and Computing, 901, 79–87. https://doi.org/10.1007/978-3-030-10728-4_9spa
dc.relation.referencesMordvintsev, A., & Abid K. (2013). Fourier Transform. https://opencv-pythontutroals.readthedocs.io/en/latest/py_tutorials/py_imgproc/py_transforms/py_f ourier_transform/py_fourier_transform.htmlspa
dc.relation.referencesMotamayor, J. C., Lachenaud, P., da Silva e Mota, J. W., Loor, R., Kuhn, D. N., Brown, J. S., & Schnell, R. J. (2008). Geographic and Genetic Population Differentiation of the Amazonian Chocolate Tree (Theobroma cacao L). PLoS ONE, 3(10), e3311. https://doi.org/10.1371/journal.pone.0003311spa
dc.relation.referencesNVIDIA cuDNN | NVIDIA Developer. (2021). Retrieved May 5, 2021, from https://developer.nvidia.com/cudnnspa
dc.relation.referencesOpenCV - OpenCV. (2021). Retrieved May 5, 2021, from https://opencv.orgspa
dc.relation.referencesOpenCV. (2015). Introduction to SURF (Speeded-Up Robust Features). https://docs.opencv.org/master/df/dd2/tutorial_py_surf_intro.htmlspa
dc.relation.referencesPacto por Colombia, pacto por la equidad. (2018). Plan Nacional de Desarrollo. Recuperado de https://colaboracion.dnp.gov.co/CDT/Prensa/ResumenPND2018-2022-final.pdfspa
dc.relation.referencesPatel, H., Jiménez, A., Ceres, R., Annamalai, P., & Lee, W. (2013). A Survey of Computer Vision Methods for Counting Fruits and Yield Predictionspa
dc.relation.referencesPDD-Santander. (2020). Santander siempre contigo y para el mundo Plan de Desarrollo Departamental 2020-2023. Planeación Departamental, 53(9), 1689.spa
dc.relation.referencesPython Software Foundation. (2016). Python Package Index. LabelImg. https://pypi.org/project/labelImg/spa
dc.relation.referencesRahnemoonfar, M., & Sheppard, C. (2017). Deep Count: Fruit Counting Based on Deep Simulated Learning. Sensors, 17(4), 905. https://doi.org/10.3390/s17040905spa
dc.relation.referencesRedacción Economía. (20 de Agosto de 2020). El Espectador: Gobierno presentó proyecto de ley para incluir a Colombia en Organización Internacional del Cacao. Recuperado de https://www.elespectador.com/spa
dc.relation.referencesRedmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2018). You Only Look Once: Unified, Real-Time Object Detection. Retrieved from http://pjreddie.com/yolo/spa
dc.relation.referencesRussell, S. J., Norvig, P., Canny, J. F., Malik, J. M., Edwards, D. D., Jonathan, S. J. S., & Norvig, P. (1995). Arificial Intelligence: A Modern Approach. Alan Aptspa
dc.relation.referencesSánchez, V., Z ambrano, J., & Iglesias, C. (2019). La cadena de valor del cacao en América Latina y el Caribe. Retrieved from: http://repositorio.iniap.gob.ec/handle/41000/5382spa
dc.relation.referencesSchuld, M., & Petruccione, F. (2018). Machine Learning. In Supervised Learning with Quantum Computers (pp. 21–73). Springer International Publishing. https://doi.org/10.1007/978-3-319-96424-9_2spa
dc.relation.referencesSerrano, S., & Heredia Gómez, J. F. (2020). Cocoa Diseases (YOLOv4). https://www.kaggle.com/serranosebas/enfermedades-cacao-yolov4spa
dc.relation.referencesShorten, C., & Khoshgoftaar, T. M. (2019). A survey on Image Data Augmentation for Deep Learning. Journal of Big Data, 6(1), 60. https://doi.org/10.1186/s40537-019-0197-0spa
dc.relation.referencesSolomon, C., & Breckon, T. (2011). Fundamentals of Digital Image Processing. https://doi.org/doi:10.1002/9780470689776.spa
dc.relation.referencesTan, D. S., Leong, R. N., Laguna, A. F., Ngo, C. A., Lao, A., Amalin, D., & Alvindia, D. (2016). A framework for measuring infection level on cacao pods. 2016 IEEE Region 10 Symposium (TENSYMP), 384–389. https://doi.org/10.1109/TENCONSpring.2016.7519437spa
dc.relation.referencesVasconez, J. P., Delpiano, J., Vougioukas, S., & Auat Cheein, F. (2020). Comparison of convolutional neural networks in fruit detection and counting: A comprehensive evaluation. Computers and Electronics in Agriculture, 173, 105348. https://doi.org/10.1016/j.compag.2020.105348spa
dc.relation.referencesVoora, V., Bermúdez, S., & Larrea, C. (2019). Global Market Report: Cocoa. International Institute for Sustainable Development.spa
dc.relation.referencesWan, S., & Goudos, S. (2020). Faster R-CNN for multi-class fruit detection using a robotic vision system. Computer Networks, 168, 107036. https://doi.org/10.1016/j.comnet.2019.107036spa
dc.relation.referencesWang, C.-Y., Liao, H.-Y. M., Yeh, I.-H., Wu, Y.-H., Chen, P.-Y., & Hsieh, J.-W. (2019). CSPNET: A NEW BACKBONE THAT CAN ENHANCE LEARNING CAPABILITY OF CNN A PREPRINT. https://github.com/WongKinYiu/CrossStagePartialNetworks.spa
dc.relation.referencesWang, Q., Nuske, S., Bergerman, M., & Singh, S. (2013). Automated Crop Yield Estimation for Apple Orchards. In J. P. Desai, G. Dudek, O. Khatib, & V. Kumar (Eds.), Experimental Robotics: The 13th International Symposium on Experimental Robotics (pp. 745–758). Springer International Publishing. https://doi.org/10.1007/978-3-319-00065-7_50spa
dc.relation.referencesWhite, S., & Kennedy, J. (2018). CMY and CMYK Color Spaces. https://docs.microsoft.com/en-us/windows/win32/wcs/cmy-and-cmyk-colorspacesspa
dc.relation.referencesZhang, B., Gao, Y., Zhao, S., & Liu, J. (2010). Local Derivative Pattern Versus Local Binary Pattern: Face Recognition With High-Order Local Pattern Descriptor. IEEE Transactions on Image Processing, 19(2), 533–544. https://doi.org/10.1109/TIP.2009.2035882spa
dc.relation.referencesZhou, Z., Song, Z., Fu, L., Gao, F., Li, R., & Cui, Y. (2020). Real-time kiwifruit detection in orchard using deep learning on AndroidTM smartphones for yield estimation. Computers and Electronics in Agriculture, 179, 105856. https://doi.org/10.1016/j.compag.2020.105856spa
dc.relation.referencesZou, H., Lu, H., Li, Y., Liu, L., & Cao, Z. (2020). Maize tassels detection: a benchmark of the state of the art. Plant Methods, 16(1), 1–15. https://doi.org/10.1186/s13007-020-00651-zspa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.creativecommonsAtribución-NoComercial-SinDerivadas 2.5 Colombia*
dc.rights.localAbierto (Texto Completo)spa
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/2.5/co/*
dc.subject.keywordsSystems engineerspa
dc.subject.keywordsTechnological innovationsspa
dc.subject.keywordsMobile appspa
dc.subject.keywordsDecision makingspa
dc.subject.keywordsComputer visionspa
dc.subject.keywordsPrototype developmentspa
dc.subject.keywordsArtificial intelligencespa
dc.subject.keywordsComputer simulationspa
dc.subject.lembIngeniería de sistemasspa
dc.subject.lembInnovaciones tecnológicasspa
dc.subject.lembDesarrollo de prototiposspa
dc.subject.lembSoftwarespa
dc.subject.lembInteligencia artificialspa
dc.subject.lembSimulación por computadoresspa
dc.subject.proposalAplicación móvilspa
dc.subject.proposalToma de decisionesspa
dc.subject.proposalVisión por computadorspa
dc.titleDesarrollo de un prototipo funcional de software para estimar la producción de cacao, haciendo uso de herramientas de aprendizaje profundo y visión por computadorspa
dc.title.translatedDevelopment of a functional software prototype to estimate cocoa production, using deep learning tools and computer visionspa
dc.type.coarhttp://purl.org/coar/resource_type/c_7a1f
dc.type.driverinfo:eu-repo/semantics/bachelorThesis
dc.type.hasversioninfo:eu-repo/semantics/acceptedVersion
dc.type.localTrabajo de Gradospa
dc.type.redcolhttp://purl.org/redcol/resource_type/TP

Archivos

Bloque original

Mostrando 1 - 2 de 2
Cargando...
Miniatura
Nombre:
2021_Tesis_Karol_Daniela_Cala.pdf
Tamaño:
2.93 MB
Formato:
Adobe Portable Document Format
Descripción:
Tesis
Cargando...
Miniatura
Nombre:
2021_Licencia_Karol_Daniela_Cala.pdf
Tamaño:
780.7 KB
Formato:
Adobe Portable Document Format
Descripción:
Licencia

Bloque de licencias

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
license.txt
Tamaño:
829 B
Formato:
Item-specific license agreed upon to submission
Descripción: