Weed detection in a Rice Crop through Image Processing and Classification Using Convolutional Neural Networks

Artificial Intelligence (AI) today occupies a central ranking, especially in a context where technological progress is omnipresent. Among the most influential tools, deep learning has established itself in both professional and academic domains. This article focuses on the effectiveness of convolutional neural networks for detecting weeds competing with rice. To achieve this, an extension of the pre-trained Inception_V3 model was used for image classification, while MobileNet was employed for image processing. This innovative approach, tested on a rice field where distinguishing between rice and weeds is challenging, represents a significant advancement in the AI field. However, the training of both models revealed limitations: Inception_V3 exhibited overfitting after the 10th iteration, while MobileNet showed high volatility and overfitting from the first iteration. Despite these challenges, Inception_V3 stood out for its superior accuracy.