Bienvenido al Repositorio Institucional del Concytec

El Repositorio Institucional del Concytec tiene como objetivo permitir el libre acceso a la producción científica institucional, optimizando su visibilidad; así mismo garantizar la preservación y conservación de la información relacionada a la ciencia, tecnología e innovación.



Display.item.jsp


Por favor, utiliza este identificador para citar o enlazar este ítem:
http://hdl.handle.net/20.500.12390/2803


Título: Deep Convolutional Neural Networks for Plant Species Characterization Based on Leaf Midrib
Autor(es): Scabini, Leonardo F. S. 
Condori, Rayner M. 
Munhoz, Isabella C. L. 
Bruno, Odemir M. 
Resumen: The automatic characterization and classification of plant species is an important task for plant taxonomists. On this work, we propose the use of well-known pre-trained Deep Convolutional Neural Networks (DCNN) for the characterization of plants based on their leaf midrib. The samples studied are microscope images of leaf midrib cross-sections taken from different specimens under varying conditions. Results with traditional handcrafted image descriptors demonstrate the difficulty to effectively characterize these samples. Our proposal is to use DCNN as a feature extractor through Global Average Pooling (GAP) over the raw output of its last convolutional layers without the application of summarizing functions such as ReLU and local poolings. Results indicate considerably performance improvements over previous approaches under different scenarios, varying the image color-space (gray-level or RGB) and the classifier (KNN or LDA). The highest result is achieved by the deeper network analyzed, ResNet (101 layers deep), using the LDA classifier, with 99.20% of accuracy rate. However, shallower networks such as AlexNet also provide good classification results (97.36%), which is still a significant improvement over the best previous result (83.67% of combined fractal descriptors).
Tema: Deep Convolutional Neural Networks;Global average pooling;Plant classification;Leaf midrib
Editorial: Springer International Publishing
Fecha de publicación: 2019
Publicado en: COMPUTER ANALYSIS OF IMAGES AND PATTERNS, CAIP 2019, PT II 
Financiamiento: 009-2018-FONDECYT 
Tipo de publicación: info:eu-repo/semantics/article
Identificador Handle: http://hdl.handle.net/20.500.12390/2803
DOI: 10.1007/978-3-030-29891-3_34
Nivel de acceso: info:eu-repo/semantics/closedAccess
Colección:4.1 Organización de eventos

Registro Dublin Core completo



Páginas vistas

4
marcado en 20-oct-2021

Google ScholarTM

Check

Altmetric

  • Compartir este item
  • QR Code

Los ítems de DSpace están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.