Wheat Yellow Rust Disease Infection Type Classification Using Texture Features
Wheat is a staple crop of Pakistan that covers almost 40% of the cultivated land and contributes almost 3% in the overall Gross Domestic Product (GDP) of Pakistan. However, due to increasing seasonal variation, it was observed that wheat is majorly affected by rust disease, particularly in rain-fed...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/1/146 |
| _version_ | 1797497616902127616 |
|---|---|
| author | Uferah Shafi Rafia Mumtaz Ihsan Ul Haq Maryam Hafeez Naveed Iqbal Arslan Shaukat Syed Mohammad Hassan Zaidi Zahid Mahmood |
| author_facet | Uferah Shafi Rafia Mumtaz Ihsan Ul Haq Maryam Hafeez Naveed Iqbal Arslan Shaukat Syed Mohammad Hassan Zaidi Zahid Mahmood |
| author_sort | Uferah Shafi |
| collection | DOAJ |
| description | Wheat is a staple crop of Pakistan that covers almost 40% of the cultivated land and contributes almost 3% in the overall Gross Domestic Product (GDP) of Pakistan. However, due to increasing seasonal variation, it was observed that wheat is majorly affected by rust disease, particularly in rain-fed areas. Rust is considered the most harmful fungal disease for wheat, which can cause reductions of 20–30% in wheat yield. Its capability to spread rapidly over time has made its management most challenging, becoming a major threat to food security. In order to counter this threat, precise detection of wheat rust and its infection types is important for minimizing yield losses. For this purpose, we have proposed a framework for classifying wheat yellow rust infection types using machine learning techniques. First, an image dataset of different yellow rust infections was collected using mobile cameras. Six Gray Level Co-occurrence Matrix (GLCM) texture features and four Local Binary Patterns (LBP) texture features were extracted from grayscale images of the collected dataset. In order to classify wheat yellow rust disease into its three classes (healthy, resistant, and susceptible), Decision Tree, Random Forest, Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), and CatBoost were used with (i) GLCM, (ii) LBP, and (iii) combined GLCM-LBP texture features. The results indicate that CatBoost outperformed on GLCM texture features with an accuracy of 92.30%. This accuracy can be further improved by scaling up the dataset and applying deep learning models. The development of the proposed study could be useful for the agricultural community for the early detection of wheat yellow rust infection and assist in taking remedial measures to contain crop yield. |
| first_indexed | 2024-03-10T03:21:48Z |
| format | Article |
| id | doaj.art-1c14b932cbcf405c906caf28668db44f |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T03:21:48Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-1c14b932cbcf405c906caf28668db44f2023-11-23T12:17:37ZengMDPI AGSensors1424-82202021-12-0122114610.3390/s22010146Wheat Yellow Rust Disease Infection Type Classification Using Texture FeaturesUferah Shafi0Rafia Mumtaz1Ihsan Ul Haq2Maryam Hafeez3Naveed Iqbal4Arslan Shaukat5Syed Mohammad Hassan Zaidi6Zahid Mahmood7School of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST), Islamabad 44000, PakistanSchool of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST), Islamabad 44000, PakistanSchool of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST), Islamabad 44000, PakistanDepartment of Engineering and Technology, School of Computing and Engineering, University of Huddersfield, Queensgate, Huddersfield HD1 3DH, UKSchool of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST), Islamabad 44000, PakistanCollege of Electrical and Mechanical Engineering (CEME), National University of Sciences and Technology(NUST), Islamabad 44000, PakistanSchool of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST), Islamabad 44000, PakistanWheat Programme, Crop Sciences Institute, National Agricultural Research Centre (NARC), Islamabad 44000, PakistanWheat is a staple crop of Pakistan that covers almost 40% of the cultivated land and contributes almost 3% in the overall Gross Domestic Product (GDP) of Pakistan. However, due to increasing seasonal variation, it was observed that wheat is majorly affected by rust disease, particularly in rain-fed areas. Rust is considered the most harmful fungal disease for wheat, which can cause reductions of 20–30% in wheat yield. Its capability to spread rapidly over time has made its management most challenging, becoming a major threat to food security. In order to counter this threat, precise detection of wheat rust and its infection types is important for minimizing yield losses. For this purpose, we have proposed a framework for classifying wheat yellow rust infection types using machine learning techniques. First, an image dataset of different yellow rust infections was collected using mobile cameras. Six Gray Level Co-occurrence Matrix (GLCM) texture features and four Local Binary Patterns (LBP) texture features were extracted from grayscale images of the collected dataset. In order to classify wheat yellow rust disease into its three classes (healthy, resistant, and susceptible), Decision Tree, Random Forest, Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), and CatBoost were used with (i) GLCM, (ii) LBP, and (iii) combined GLCM-LBP texture features. The results indicate that CatBoost outperformed on GLCM texture features with an accuracy of 92.30%. This accuracy can be further improved by scaling up the dataset and applying deep learning models. The development of the proposed study could be useful for the agricultural community for the early detection of wheat yellow rust infection and assist in taking remedial measures to contain crop yield.https://www.mdpi.com/1424-8220/22/1/146texture analysiswheat yellow rust diseaseGLCM featuresfeature extractionmachine learninglocal binary pattern (LBP) |
| spellingShingle | Uferah Shafi Rafia Mumtaz Ihsan Ul Haq Maryam Hafeez Naveed Iqbal Arslan Shaukat Syed Mohammad Hassan Zaidi Zahid Mahmood Wheat Yellow Rust Disease Infection Type Classification Using Texture Features Sensors texture analysis wheat yellow rust disease GLCM features feature extraction machine learning local binary pattern (LBP) |
| title | Wheat Yellow Rust Disease Infection Type Classification Using Texture Features |
| title_full | Wheat Yellow Rust Disease Infection Type Classification Using Texture Features |
| title_fullStr | Wheat Yellow Rust Disease Infection Type Classification Using Texture Features |
| title_full_unstemmed | Wheat Yellow Rust Disease Infection Type Classification Using Texture Features |
| title_short | Wheat Yellow Rust Disease Infection Type Classification Using Texture Features |
| title_sort | wheat yellow rust disease infection type classification using texture features |
| topic | texture analysis wheat yellow rust disease GLCM features feature extraction machine learning local binary pattern (LBP) |
| url | https://www.mdpi.com/1424-8220/22/1/146 |
| work_keys_str_mv | AT uferahshafi wheatyellowrustdiseaseinfectiontypeclassificationusingtexturefeatures AT rafiamumtaz wheatyellowrustdiseaseinfectiontypeclassificationusingtexturefeatures AT ihsanulhaq wheatyellowrustdiseaseinfectiontypeclassificationusingtexturefeatures AT maryamhafeez wheatyellowrustdiseaseinfectiontypeclassificationusingtexturefeatures AT naveediqbal wheatyellowrustdiseaseinfectiontypeclassificationusingtexturefeatures AT arslanshaukat wheatyellowrustdiseaseinfectiontypeclassificationusingtexturefeatures AT syedmohammadhassanzaidi wheatyellowrustdiseaseinfectiontypeclassificationusingtexturefeatures AT zahidmahmood wheatyellowrustdiseaseinfectiontypeclassificationusingtexturefeatures |