<![CDATA[This study aims to implement the GLCM (Gray Level Co-Occurrence Matrix) and KNN (K-Nearest Neighbor) methods in the classification of fiber root species based on leaf images. Fibrous roots are the most common root type in certain plants, and classifying plant species based on leaf image can provide useful information in contacting plants. The GLCM method is used to extract texture features from leaf images. The GLCM matrix describes the relative occurrence of pixel pairs with different gray intensities in the image. These features can provide information about leaf texture that can be used in classification. Furthermore, the KNN algorithm is used to classify plant types based on the extracted features. The dataset used in this study consists of a number of leaf images representing several different types of fiber root plants. Image processing includes pre-processing to obtain a clean image and ensure consistency of image size. After feature extraction using the GLCM method, these features are used as input for the KNN algorithm. KNN is used to classify unknown leaf images into one of the plant classes that have been previously trained. The experimental results show that the GLCM and KNN methods can provide good results in the classification of fiber root plant species based on leaf images. High classification accuracy indicates the effectiveness of this method in identifying plant species based on textural features of leaf images. Thus, this method can be a useful tool in the field of plant recognition and other applications that involve identifying plant species based on leaf images]]>
Copyrights © 2024
