<![CDATA[The dominance of deep learning in image-based waste classification has led to high accuracy but often requires large datasets and significant computational resources, limiting its applicability in resource-constrained environments. Conversely, lightweight feature-based methods offer efficiency but typically suffer from lower robustness. This study addresses this gap by proposing a balanced approach that combines computational efficiency with competitive classification performance. An automatic image-based classification system is developed to categorize household waste into three material classes: paper, plastic, and metal. The proposed method utilizes complementary color features from RGB and HSV color spaces along with shape features, which are processed using a lightweight Artificial Neural Network (ANN). The model is evaluated using a dataset of 300 images with a 90:10 train-test split. Experimental results show that the proposed feature combination achieves a training accuracy of 94.444% and a testing accuracy of 90.000%. In addition, the model demonstrates balanced performance with precision, recall, and F1-score values of up to 0.976, 0.956, and 0.948 on training data, and consistent values of 0.900 on testing data. These results indicate that the proposed approach achieves competitive performance while maintaining low computational cost, with an average testing time of 0.007 seconds. This study contributes to the field of computer vision by demonstrating that a carefully designed feature-based ANN model can serve as an efficient alternative to deep learning for waste classification tasks. The proposed method offers a practical trade-off between accuracy and computational efficiency, making it suitable for real-world deployment in resource-limited environments.]]>
