RNN- and CNN-based weed detection for crop improvement: An overview
Introduction. Deep learning is a modern technique for image processing and data analysis with promising results and great potential. Successfully applied in various fields, it has recently entered the field of agriculture to address such agricultural problems as disease identification, fruit/plant c...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Kemerovo State University
2021-11-01
|
| Series: | Foods and Raw Materials |
| Subjects: | |
| Online Access: | http://jfrm.ru/en/issues/1879/1961/ |
| _version_ | 1818835821638189056 |
|---|---|
| author | Brahim Jabir Loubna Rabhi Noureddine Falih |
| author_facet | Brahim Jabir Loubna Rabhi Noureddine Falih |
| author_sort | Brahim Jabir |
| collection | DOAJ |
| description | Introduction. Deep learning is a modern technique for image processing and data analysis with promising results and great potential. Successfully applied in various fields, it has recently entered the field of agriculture to address such agricultural problems as disease identification, fruit/plant classification, fruit counting, pest identification, and weed detection. The latter was the subject of our work. Weeds are harmful plants that grow in crops, competing for things like sunlight and water and causing crop yield losses. Traditional data processing techniques have several limitations and consume a lot of time. Therefore, we aimed to take inventory of deep learning networks used in agriculture and conduct experiments to reveal the most efficient ones for weed control. Study objects and methods. We used new advanced algorithms based on deep learning to process data in real time with high precision and efficiency. These algorithms were trained on a dataset containing real images of weeds taken from Moroccan fields. Results and discussion. The analysis of deep learning methods and algorithms trained to detect weeds showed that the Convolutional Neural Network is the most widely used in agriculture and the most efficient in weed detection compared to others, such as the Recurrent Neural Network. Conclusion. Since the Convolutional Neural Network demonstrated excellent accuracy in weed detection, we adopted it in building a smart system for detecting weeds and spraying them in place. |
| first_indexed | 2024-12-19T02:56:48Z |
| format | Article |
| id | doaj.art-76c47661b439482785715b42fe919e86 |
| institution | Directory Open Access Journal |
| issn | 2308-4057 2310-9599 |
| language | English |
| last_indexed | 2024-12-19T02:56:48Z |
| publishDate | 2021-11-01 |
| publisher | Kemerovo State University |
| record_format | Article |
| series | Foods and Raw Materials |
| spelling | doaj.art-76c47661b439482785715b42fe919e862022-12-21T20:38:20ZengKemerovo State UniversityFoods and Raw Materials2308-40572310-95992021-11-019238739610.21603/2308-4057-2021-2-387-396RNN- and CNN-based weed detection for crop improvement: An overviewBrahim Jabir0https://orcid.org/0000-0002-8762-9199Loubna Rabhi1https://orcid.org/0000-0002-4617-5223Noureddine Falih2https://orcid.org/0000-0001-7804-5450Sultan Moulay Slimane University, Beni Mellal, MoroccoSultan Moulay Slimane University, Beni Mellal, MoroccoSultan Moulay Slimane University, Beni Mellal, MoroccoIntroduction. Deep learning is a modern technique for image processing and data analysis with promising results and great potential. Successfully applied in various fields, it has recently entered the field of agriculture to address such agricultural problems as disease identification, fruit/plant classification, fruit counting, pest identification, and weed detection. The latter was the subject of our work. Weeds are harmful plants that grow in crops, competing for things like sunlight and water and causing crop yield losses. Traditional data processing techniques have several limitations and consume a lot of time. Therefore, we aimed to take inventory of deep learning networks used in agriculture and conduct experiments to reveal the most efficient ones for weed control. Study objects and methods. We used new advanced algorithms based on deep learning to process data in real time with high precision and efficiency. These algorithms were trained on a dataset containing real images of weeds taken from Moroccan fields. Results and discussion. The analysis of deep learning methods and algorithms trained to detect weeds showed that the Convolutional Neural Network is the most widely used in agriculture and the most efficient in weed detection compared to others, such as the Recurrent Neural Network. Conclusion. Since the Convolutional Neural Network demonstrated excellent accuracy in weed detection, we adopted it in building a smart system for detecting weeds and spraying them in place.http://jfrm.ru/en/issues/1879/1961/digital agricultureweed detectionmachine learningdeep learningconvolutional neural network (cnn)recurrent neural network (rnn) |
| spellingShingle | Brahim Jabir Loubna Rabhi Noureddine Falih RNN- and CNN-based weed detection for crop improvement: An overview Foods and Raw Materials digital agriculture weed detection machine learning deep learning convolutional neural network (cnn) recurrent neural network (rnn) |
| title | RNN- and CNN-based weed detection for crop improvement: An overview |
| title_full | RNN- and CNN-based weed detection for crop improvement: An overview |
| title_fullStr | RNN- and CNN-based weed detection for crop improvement: An overview |
| title_full_unstemmed | RNN- and CNN-based weed detection for crop improvement: An overview |
| title_short | RNN- and CNN-based weed detection for crop improvement: An overview |
| title_sort | rnn and cnn based weed detection for crop improvement an overview |
| topic | digital agriculture weed detection machine learning deep learning convolutional neural network (cnn) recurrent neural network (rnn) |
| url | http://jfrm.ru/en/issues/1879/1961/ |
| work_keys_str_mv | AT brahimjabir rnnandcnnbasedweeddetectionforcropimprovementanoverview AT loubnarabhi rnnandcnnbasedweeddetectionforcropimprovementanoverview AT noureddinefalih rnnandcnnbasedweeddetectionforcropimprovementanoverview |