The Disease Detection for Maize-Plant using K-Means Clustering


  • Muhamad Amirul Mohd Yusof Faculty of Electrical and Electronic Engineering,UTHM
  • Ain Nazari


Maize-Plant Disease, SVM Classifier, K-Means Clustering


Identifying and recognition are the one of main importance processes that has been used in many industries nowadays. To make this process more efficient, the technology such image processing need to be used. One of industry which is in a lot of demand nowadays is maize-plant. The quality care for maize plant should be emphasized by the farmers to ensure the maize that produced is healthy and non-diseased. People usually use guide books or website to recognize the maize plant disease and this consuming a lot of time and hard to bring the accurate result. An automated detection system can help to identify the types of maize plant disease with more efficient. The purpose of this research is to design a system that can analyze plant image using image processing method. The proposed method consists of five stage which is pre-processing, image segmentation, feature extraction and classification. The histogram equalization and median filtering algorithm is used in pre-processing process. Then for the segmentation, there are two part which are leaf area and disease area. The thresholding, masking and k-means algorithm is used to perform this segmentation. In feature extraction process, there are 13 features need to extract from the image to perform classification in Support Vector Machine (SVM) classifier. Hence, from the findings of the study, it indicates that the system is able to identify the type of maize plant disease correctly with the average accuracy, sensitivity and specificity for healthy leaf is 97.53%, 90.08% and 85.4%. While for the overall disease leaf is 97.27%, 90.82% and 84.93%. In conclusion, this system has developed an automated system to identify the types of diseases for maize plant.




How to Cite

Mohd Yusof, M. A., & Nazari, A. (2021). The Disease Detection for Maize-Plant using K-Means Clustering. Evolution in Electrical and Electronic Engineering, 2(2), 834–841. Retrieved from