Insect classification and detection in field crops using modern machine learning techniques
The agriculture sector has an immense potential to improve the requirement of food and supplies healthy and nutritious food. Crop insect detection is a challenging task for farmers as a significant portion of the crops are damaged, and the quality is degraded due to the pest attack. Traditional inse...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-09-01
|
| Series: | Information Processing in Agriculture |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214317320302067 |
| _version_ | 1797765445652054016 |
|---|---|
| author | Thenmozhi Kasinathan Dakshayani Singaraju Srinivasulu Reddy Uyyala |
| author_facet | Thenmozhi Kasinathan Dakshayani Singaraju Srinivasulu Reddy Uyyala |
| author_sort | Thenmozhi Kasinathan |
| collection | DOAJ |
| description | The agriculture sector has an immense potential to improve the requirement of food and supplies healthy and nutritious food. Crop insect detection is a challenging task for farmers as a significant portion of the crops are damaged, and the quality is degraded due to the pest attack. Traditional insect identification has the drawback of requiring well-trained taxonomists to identify insects based on morphological features accurately. Experiments were conducted for classification on nine and 24 insect classes of Wang and Xie dataset using the shape features and applying machine learning techniques such as artificial neural networks (ANN), support vector machine (SVM), k-nearest neighbors (KNN), naive bayes (NB) and convolutional neural network (CNN) model. This paper presents the insect pest detection algorithm that consists of foreground extraction and contour identification to detect the insects for Wang, Xie, Deng, and IP102 datasets in a highly complex background. The 9-fold cross-validation was applied to improve the performance of the classification models. The highest classification rate of 91.5% and 90% was achieved for nine and 24 class insects using the CNN model. The detection performance was accomplished with less computation time for Wang, Xie, Deng, and IP102 datasets using insect pest detection algorithm. The comparison results with the state-of-the-art classification algorithms exhibited considerable improvement in classification accuracy, computation time performance while apply more efficiently in field crops to recognize the insects. The results of classification accuracy are used to recognize the crop insects in the early stages and reduce the time to enhance the crop yield and crop quality in agriculture. |
| first_indexed | 2024-03-12T20:11:16Z |
| format | Article |
| id | doaj.art-053a38177ac54996bc5c2b5ce8c1a4ce |
| institution | Directory Open Access Journal |
| issn | 2214-3173 |
| language | English |
| last_indexed | 2024-03-12T20:11:16Z |
| publishDate | 2021-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Information Processing in Agriculture |
| spelling | doaj.art-053a38177ac54996bc5c2b5ce8c1a4ce2023-08-02T01:41:52ZengElsevierInformation Processing in Agriculture2214-31732021-09-0183446457Insect classification and detection in field crops using modern machine learning techniquesThenmozhi Kasinathan0Dakshayani Singaraju1Srinivasulu Reddy Uyyala2Machine Learning and Data Analytics Lab, Centre of Excellence in Artificial Intelligence, Department of Computer Applications, National Institute of Technology, Tiruchirappalli, Tiruchirappalli 620015, Tamil Nadu, IndiaMachine Learning and Data Analytics Lab, Centre of Excellence in Artificial Intelligence, Department of Computer Applications, National Institute of Technology, Tiruchirappalli, Tiruchirappalli 620015, Tamil Nadu, IndiaCorresponding author.; Machine Learning and Data Analytics Lab, Centre of Excellence in Artificial Intelligence, Department of Computer Applications, National Institute of Technology, Tiruchirappalli, Tiruchirappalli 620015, Tamil Nadu, IndiaThe agriculture sector has an immense potential to improve the requirement of food and supplies healthy and nutritious food. Crop insect detection is a challenging task for farmers as a significant portion of the crops are damaged, and the quality is degraded due to the pest attack. Traditional insect identification has the drawback of requiring well-trained taxonomists to identify insects based on morphological features accurately. Experiments were conducted for classification on nine and 24 insect classes of Wang and Xie dataset using the shape features and applying machine learning techniques such as artificial neural networks (ANN), support vector machine (SVM), k-nearest neighbors (KNN), naive bayes (NB) and convolutional neural network (CNN) model. This paper presents the insect pest detection algorithm that consists of foreground extraction and contour identification to detect the insects for Wang, Xie, Deng, and IP102 datasets in a highly complex background. The 9-fold cross-validation was applied to improve the performance of the classification models. The highest classification rate of 91.5% and 90% was achieved for nine and 24 class insects using the CNN model. The detection performance was accomplished with less computation time for Wang, Xie, Deng, and IP102 datasets using insect pest detection algorithm. The comparison results with the state-of-the-art classification algorithms exhibited considerable improvement in classification accuracy, computation time performance while apply more efficiently in field crops to recognize the insects. The results of classification accuracy are used to recognize the crop insects in the early stages and reduce the time to enhance the crop yield and crop quality in agriculture.http://www.sciencedirect.com/science/article/pii/S2214317320302067Crop pest classificationCrop insect detectionImage processingMachine learningImage segmentation |
| spellingShingle | Thenmozhi Kasinathan Dakshayani Singaraju Srinivasulu Reddy Uyyala Insect classification and detection in field crops using modern machine learning techniques Information Processing in Agriculture Crop pest classification Crop insect detection Image processing Machine learning Image segmentation |
| title | Insect classification and detection in field crops using modern machine learning techniques |
| title_full | Insect classification and detection in field crops using modern machine learning techniques |
| title_fullStr | Insect classification and detection in field crops using modern machine learning techniques |
| title_full_unstemmed | Insect classification and detection in field crops using modern machine learning techniques |
| title_short | Insect classification and detection in field crops using modern machine learning techniques |
| title_sort | insect classification and detection in field crops using modern machine learning techniques |
| topic | Crop pest classification Crop insect detection Image processing Machine learning Image segmentation |
| url | http://www.sciencedirect.com/science/article/pii/S2214317320302067 |
| work_keys_str_mv | AT thenmozhikasinathan insectclassificationanddetectioninfieldcropsusingmodernmachinelearningtechniques AT dakshayanisingaraju insectclassificationanddetectioninfieldcropsusingmodernmachinelearningtechniques AT srinivasulureddyuyyala insectclassificationanddetectioninfieldcropsusingmodernmachinelearningtechniques |