This study addresses the challenge of classifying white blood cells (WBCs) using microscopic images, aiming to improve accuracy and efficiency. The research introduces a novel approach that combines extensive pre-processing techniques, including data augmentation, with an optimized convolutional neural network (CNN) model. The study compares the proposed method with conventional deep learning and transfer learning models, such as ResNet, VGG16, MobileNet, and InceptionV3. The results show that the proposed CNN model achieves a significantly higher accuracy of 0.9986, outperforming other models and demonstrating superior computational efficiency. The study also highlights the importance of pre-processing in enhancing the performance of machine learning and deep learning models. Additionally, the proposed method is validated using a different dataset for malaria parasite screening, achieving an accuracy score of 0.9996. The research concludes that the proposed approach is effective and reliable for WBC classification, offering a practical alternative to existing methods.This study addresses the challenge of classifying white blood cells (WBCs) using microscopic images, aiming to improve accuracy and efficiency. The research introduces a novel approach that combines extensive pre-processing techniques, including data augmentation, with an optimized convolutional neural network (CNN) model. The study compares the proposed method with conventional deep learning and transfer learning models, such as ResNet, VGG16, MobileNet, and InceptionV3. The results show that the proposed CNN model achieves a significantly higher accuracy of 0.9986, outperforming other models and demonstrating superior computational efficiency. The study also highlights the importance of pre-processing in enhancing the performance of machine learning and deep learning models. Additionally, the proposed method is validated using a different dataset for malaria parasite screening, achieving an accuracy score of 0.9996. The research concludes that the proposed approach is effective and reliable for WBC classification, offering a practical alternative to existing methods.