The proposed research aims to revolutionize the categorization of RBC (Red Blood Cell) images by implementing a criteria-based classification system. It strives to enhance classification precision by harnessing the potential of Deep Convolutional Neural Networks (DCNs) compared to traditional CNNs. Utilizing a dataset comprising 790 images as the benchmark, a specifically tailored Deep Convolutional Neural Network is employed for analysis. The research presents a novel deep learning approach geared towards refining the accuracy of RBC image classification by contrasting the performance of Convolutional Neural Networks against Deep Convolutional Neural Networks. Through the utilization of G power, a sample size of 27 per group was determined for experimentation. The outcomes illustrate that the Deep Convolutional Neural Network exhibits superior performance, achieving a classification accuracy of 93.8%, with the lowest mean error, in contrast to the Convolutional Neural Network's accuracy of 85.8%. Notably, a significant difference of p=0.005 is observed between these two classifiers. In summary, this study conclusively demonstrates that for the classification of blood cell images, the Deep Convolutional Neural Network surpasses the Conventional Neural Network, showcasing its remarkable efficacy and potential for advancement in this domain