Non-destructive Machine Vision System based Rice Classification using Ensemble Machine Learning Algorithms
MM Shivamurthaiah… - Recent Advances in …, 2024 - ingentaconnect.com
MM Shivamurthaiah, HK Kushtagi Shetra
Recent Advances in Electrical & Electronic Engineering (Formerly …, 2024•ingentaconnect.comAims and Background: Agriculture plays a major role in the global economy, providing food,
raw materials, and jobs to billions of people and driving economic growth and poverty
reduction. Rice is the most widely consumed crop domestically, making it a particularly
important crop for rural populations. The exact number of rice varieties worldwide is difficult
to determine as new varieties are constantly being developed and marketed. Objective: The
most common method of rice variety identification is a comparison of its physical and …
raw materials, and jobs to billions of people and driving economic growth and poverty
reduction. Rice is the most widely consumed crop domestically, making it a particularly
important crop for rural populations. The exact number of rice varieties worldwide is difficult
to determine as new varieties are constantly being developed and marketed. Objective: The
most common method of rice variety identification is a comparison of its physical and …
Aims and Background
Agriculture plays a major role in the global economy, providing food, raw materials, and jobs to billions of people and driving economic growth and poverty reduction. Rice is the most widely consumed crop domestically, making it a particularly important crop for rural populations. The exact number of rice varieties worldwide is difficult to determine as new varieties are constantly being developed and marketed.
Objective
The most common method of rice variety identification is a comparison of its physical and chemical properties to a reference collection of known types.
Methodology
This is a relatively quick and cost-effective approach that can be used to accurately differentiate between distinct varieties. In some cases, genetic testing may be used to confirm the identity of a variety, although this technique is more expensive and time-consuming. However, we can also utilize efficient, precise, and cost-effective digital image processing and machine vision techniques.
Results
This study describes different types of ensemble methods, such as bagging (Decision Tree, Random Forest, Extra Tree), boosting (AdaBoost, Gradient Boost, and XGBoost), and voting classifiers to classify five different varieties of rice. Extreme Gradient Boosting (XGBoost) has achieved the highest average classification accuracy of 99.60% among all the algorithms.
Conclusion
The findings of the performance measurement indicated that the proposed model was successful in classifying the various varieties of rice.
ingentaconnect.com
以上显示的是最相近的搜索结果。 查看全部搜索结果