Next Article in Journal
Compound Context-Aware Bayesian Inference Scheme for Smart IoT Environment
Previous Article in Journal
What Can 5G Do for Public Safety? Structural Health Monitoring and Earthquake Early Warning Scenarios
 
 
Article

Weed Classification from Natural Corn Field-Multi-Plant Images Based on Shallow and Deep Learning

1
Centro de Investigaciones en Óptica A.C., Loma del Bosque 115, Leon 37150, Guanajuato, Mexico
2
Instituto Nacional de Investigaciones Forestales, Agrícolas y Pecuarias—Campo Experimental Pabellón, Pabellon de Arteaga 20671, Aguascalientes, Mexico
3
Centro de Investigación en Matemáticas A.C., Lasec y Andador Galileo Galilei, Quantum Ciudad del Conocimiento, Zacatecas 98160, Zacatecas, Mexico
4
Consejo Nacional de Ciencia y Tecnología, Ciudad de Mexico 03940, Mexico
*
Author to whom correspondence should be addressed.
Academic Editor: Vittorio M.N. Passaro
Sensors 2022, 22(8), 3021; https://doi.org/10.3390/s22083021
Received: 30 March 2022 / Revised: 9 April 2022 / Accepted: 11 April 2022 / Published: 14 April 2022
(This article belongs to the Section Smart Agriculture)
Crop and weed discrimination in natural field environments is still challenging for implementing automatic agricultural practices, such as weed control. Some weed control methods have been proposed. However, these methods are still restricted as they are implemented under controlled conditions. The development of a sound weed control system begins by recognizing the crop and the different weed plants presented in the field. In this work, a classification approach of Zea mays L. (Crop), narrow-leaf weeds (NLW), and broadleaf weeds (BLW) from multi-plant images are presented. Moreover, a large image dataset was generated. Images were captured in natural field conditions, in different locations, and growing stages of the plants. The extraction of regions of interest (ROI) is carried out employing connected component analysis (CCA), whereas the classification of ROIs is based on Convolutional Neural Networks (CNN) and compared with a shallow learning approach. To measure the classification performance of both methods, accuracy, precision, recall, and F1-score metrics were used. The best alternative for the weed classification task at early stages of growth and in natural corn field environments was the CNN-based approach, as indicated by the 97% accuracy value obtained. View Full-Text
Keywords: corn and weed classification; natural environment; multi-plant species; multi-plant image; classic ML; deep learning corn and weed classification; natural environment; multi-plant species; multi-plant image; classic ML; deep learning
Show Figures

Figure 1

MDPI and ACS Style

Garibaldi-Márquez, F.; Flores, G.; Mercado-Ravell, D.A.; Ramírez-Pedraza, A.; Valentín-Coronado, L.M. Weed Classification from Natural Corn Field-Multi-Plant Images Based on Shallow and Deep Learning. Sensors 2022, 22, 3021. https://doi.org/10.3390/s22083021

AMA Style

Garibaldi-Márquez F, Flores G, Mercado-Ravell DA, Ramírez-Pedraza A, Valentín-Coronado LM. Weed Classification from Natural Corn Field-Multi-Plant Images Based on Shallow and Deep Learning. Sensors. 2022; 22(8):3021. https://doi.org/10.3390/s22083021

Chicago/Turabian Style

Garibaldi-Márquez, Francisco, Gerardo Flores, Diego A. Mercado-Ravell, Alfonso Ramírez-Pedraza, and Luis M. Valentín-Coronado. 2022. "Weed Classification from Natural Corn Field-Multi-Plant Images Based on Shallow and Deep Learning" Sensors 22, no. 8: 3021. https://doi.org/10.3390/s22083021

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop