Rice is one of the major crops that plays a vital role in ensuring food security in Bangladesh. However, several rice leaf diseases such as brown spot, leaf blast, and hispa significantly reduce crop yield and quality every year. Early and accurate detection of these diseases is important for minimizing agricultural losses and improving productivity. Traditional disease detection methods mainly depend on visual observation and expert knowledge, which are often time-consuming and less effective for large-scale agricultural applications. In recent years, deep learning techniques have shown promising performance in automated plant disease classification. In this study, a Convolutional Neural Network (CNN)-based deep learning framework with transfer learning is proposed for rice leaf disease classification. The proposed method extracts deep feature representations using two pre-trained transfer learning models. These extracted features are then combined through feature fusion to improve the representation of disease patterns from rice leaf images. Furthermore, machine learning classifiers such as K-Nearest Neighbor (K-NN) and Support Vector Machine (SVM) are integrated with the deep features to enhance classification performance. Experimental results demonstrate that the proposed hybrid framework can effectively classify rice leaf diseases with improved accuracy and reduced processing time. The findings suggest that the proposed approach may support intelligent agricultural monitoring systems for early disease detection in rice cultivation.