Pest Detection on Plants Using Image Processing

Plant pest and disease detection is crucial for ensuring agricultural productivity and food security. This paper presents a machine learning-based approach utilizing image processing techniques to identify pests and diseases in plants. The system employs Histogram of Oriented Gradients (HOG) for feature extraction and a Support Vector Machine (SVM) classifier for classification. The dataset is built from labelled images of pests and diseases in plants, and the trained model is used to predict new instances. Additionally, color-based segmentation in the HSV color space enhances detection by isolating affected regions. The method efficiently processes images, detects contours, and classifies the affected areas as either pest-infected or diseased. Experimental results demonstrate the model’s effectiveness in distinguishing between pests and diseases with high accuracy. The proposed system provides an automated and scalable solution for early detection, aiding in timely intervention and precision agriculture practices.