A Smart Waste Collection system can be enhanced by optimizing waste collection routes through real-time waste classification, thereby reducing operational costs. Accurate waste classification promotes efficient recycling by directing organic waste towards composting and converting non-organic waste into recyclable materials. This proper classification prevents the contamination of soil, water, and air, mitigating the environmental impacts of improper waste management. Segregating organic waste for composting returns valuable nutrients to the soil, supports sustainable agriculture, and conserves resources. Traditional waste classification methods, which often rely on manual sorting or basic rule-based systems, are labor-intensive, time-consuming, and prone to errors. Human involvement can lead to inconsistencies and variations in waste categorization, while rule-based systems struggle with complex and diverse waste compositions, resulting in suboptimal accuracy, particularly with mixed waste. These methods may also lack scalability and adaptability for large-scale urban waste classification. In contrast, a machine learning (ML)-driven waste classification system harnesses AI algorithms to automate and enhance the classification process. By employing image analysis techniques to extract visual features such as color, texture, and shape from waste images, the system achieves higher accuracy and efficiency in waste classification.