Rice, one of the most important crops globally, serves as a vital nutritional source for over 50% of the world's population. However, it is highly susceptible to various diseases that can severely impact both the quality and quantity of the harvest, sometimes causing a reduction of 20%–40% in crop yield. Timely detection and accurate identification of rice plant diseases are critical for ensuring a healthy harvest. Farmers must be able to recognize these diseases visually, but daily field surveys are labor-intensive, time-consuming and costly, ultimately driving up the price of rice for consumers. Rice leaves are prone to several bacterial, viral and fungal diseases, which significantly affect rice production. To meet the growing global demand for rice, effective disease detection is essential. However, challenges in disease recognition arise due to background noise and varying capture conditions in images. Convolutional Neural Network (CNN)-based models have significantly advanced the detection and identification of rice plant diseases. This paper aims to achieve efficient and timely detection and identification of rice plant diseases by exploring the CNN models, both with and without segmentation techniques, for diseases such as Brown Spot, Leaf Blast and Neck Blast.