Early Pest Detection From Crops Using Image Processing and Computational Intelligence

This study presents an early pest detection system for crops through the integration of image processing and computational intelligence. The proposed method employs a multi-step approach for accurate pest identification. Initially, input images undergo pre-processing steps including resizing, contrast adjustment, noise removal, and conversion to the LAB color space. 

The segmentation phase employs k-means clustering to delineate regions of interest. Further, the Gray Level Co-occurrence Matrix (GLCM) is utilized for feature extraction, capturing crucial texture features such as contrast, correlation, energy, homogeneity, mean, standard deviation, entropy, root mean square (RMS), variance, smoothness, kurtosis, and skewness. 

Subsequently, a Support Vector Machine (SVM) classification algorithm is employed to categorize segmented regions as pest or non-pest. The proposed methodology demonstrates promising results in early pest detection, showcasing the efficacy of integrating image processing and computational intelligence techniques. The approach achieves high accuracy in pest classification, thereby offering a reliable tool for proactive pest management in agricultural settings.

Keywords: Pre-Processing, support vector machine, machine learning, Gray Level Co-occurrence Matrix (GLCM), Classification, Accuracy.