A novel hybrid feature method for weeds identification in the agriculture sector
Weed identification and controlling systems are gaining great attention and are very effective for large productivity in the agriculture sector. Currently, farmers are facing a weed control and management problem, and to tackle this challenge precision agriculture in the form of selective spraying i...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Czech Academy of Agricultural Sciences
2023-09-01
|
| Series: | Research in Agricultural Engineering |
| Subjects: | |
| Online Access: | https://rae.agriculturejournals.cz/artkey/rae-202303-0004_a-novel-hybrid-feature-method-for-weeds-identification-in-the-agriculture-sector.php |
| _version_ | 1797692504664965120 |
|---|---|
| author | Sheeraz Arif Arif Rashid Hussain Nadia Mustaqim Ansari Waseem Rauf |
| author_facet | Sheeraz Arif Arif Rashid Hussain Nadia Mustaqim Ansari Waseem Rauf |
| author_sort | Sheeraz Arif Arif |
| collection | DOAJ |
| description | Weed identification and controlling systems are gaining great attention and are very effective for large productivity in the agriculture sector. Currently, farmers are facing a weed control and management problem, and to tackle this challenge precision agriculture in the form of selective spraying is much-needed practice. In this article, we introduce a novel framework for a weed identification system that leverages (hybrid) the robust and relevant features of deep learning models, such as convolutional neural network (CNN) and handcrafted features. First, we apply the image pre-processing and augmentation techniques for image quality and dataset size enhancement. Then, we apply handcrafted feature extraction techniques, such as local binary pattern (LBP) and histogram of oriented gradients (HOG) to extract texture and shape features from the input. We also apply the deep learning model, such as CNN, to capture the relevant semantic features. Lastly, we concatenate the features extracted from a different domain and explore the performance using different classifiers. We achieved better performance and classification accuracy in the presence of the extreme gradient boosting (XGBoost) classifier. The achieved results witnessed the effectiveness and applicability of the given method and the importance of concatenated features. |
| first_indexed | 2024-03-12T02:29:33Z |
| format | Article |
| id | doaj.art-073cd978adcd4c01957cd56546ebbc0a |
| institution | Directory Open Access Journal |
| issn | 1212-9151 1805-9376 |
| language | English |
| last_indexed | 2024-03-12T02:29:33Z |
| publishDate | 2023-09-01 |
| publisher | Czech Academy of Agricultural Sciences |
| record_format | Article |
| series | Research in Agricultural Engineering |
| spelling | doaj.art-073cd978adcd4c01957cd56546ebbc0a2023-09-05T08:25:50ZengCzech Academy of Agricultural SciencesResearch in Agricultural Engineering1212-91511805-93762023-09-0169313214210.17221/77/2022-RAErae-202303-0004A novel hybrid feature method for weeds identification in the agriculture sectorSheeraz Arif Arif0Rashid Hussain1Nadia Mustaqim Ansari2Waseem Rauf3Department of Computer Science, Faculty of Information Technology, Salim Habib University, Karachi, PakistanDepartment of Information and Communication Engineering, Beijing Institute of Technology, Beijing, ChinaDepartment of Electronic Engineering, Faculty of Engineering Science and Technology, Hamdard University, Karachi, PakistanDepartment of Electronic Engineering, Dawood University of Engineering and Technology, Karachi, PakistanWeed identification and controlling systems are gaining great attention and are very effective for large productivity in the agriculture sector. Currently, farmers are facing a weed control and management problem, and to tackle this challenge precision agriculture in the form of selective spraying is much-needed practice. In this article, we introduce a novel framework for a weed identification system that leverages (hybrid) the robust and relevant features of deep learning models, such as convolutional neural network (CNN) and handcrafted features. First, we apply the image pre-processing and augmentation techniques for image quality and dataset size enhancement. Then, we apply handcrafted feature extraction techniques, such as local binary pattern (LBP) and histogram of oriented gradients (HOG) to extract texture and shape features from the input. We also apply the deep learning model, such as CNN, to capture the relevant semantic features. Lastly, we concatenate the features extracted from a different domain and explore the performance using different classifiers. We achieved better performance and classification accuracy in the presence of the extreme gradient boosting (XGBoost) classifier. The achieved results witnessed the effectiveness and applicability of the given method and the importance of concatenated features.https://rae.agriculturejournals.cz/artkey/rae-202303-0004_a-novel-hybrid-feature-method-for-weeds-identification-in-the-agriculture-sector.phpconvolutional neural networkdeep learninghandcrafted featuresweed detectionxgboost classifier |
| spellingShingle | Sheeraz Arif Arif Rashid Hussain Nadia Mustaqim Ansari Waseem Rauf A novel hybrid feature method for weeds identification in the agriculture sector Research in Agricultural Engineering convolutional neural network deep learning handcrafted features weed detection xgboost classifier |
| title | A novel hybrid feature method for weeds identification in the agriculture sector |
| title_full | A novel hybrid feature method for weeds identification in the agriculture sector |
| title_fullStr | A novel hybrid feature method for weeds identification in the agriculture sector |
| title_full_unstemmed | A novel hybrid feature method for weeds identification in the agriculture sector |
| title_short | A novel hybrid feature method for weeds identification in the agriculture sector |
| title_sort | novel hybrid feature method for weeds identification in the agriculture sector |
| topic | convolutional neural network deep learning handcrafted features weed detection xgboost classifier |
| url | https://rae.agriculturejournals.cz/artkey/rae-202303-0004_a-novel-hybrid-feature-method-for-weeds-identification-in-the-agriculture-sector.php |
| work_keys_str_mv | AT sheerazarifarif anovelhybridfeaturemethodforweedsidentificationintheagriculturesector AT rashidhussain anovelhybridfeaturemethodforweedsidentificationintheagriculturesector AT nadiamustaqimansari anovelhybridfeaturemethodforweedsidentificationintheagriculturesector AT waseemrauf anovelhybridfeaturemethodforweedsidentificationintheagriculturesector AT sheerazarifarif novelhybridfeaturemethodforweedsidentificationintheagriculturesector AT rashidhussain novelhybridfeaturemethodforweedsidentificationintheagriculturesector AT nadiamustaqimansari novelhybridfeaturemethodforweedsidentificationintheagriculturesector AT waseemrauf novelhybridfeaturemethodforweedsidentificationintheagriculturesector |