Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{197139,
        author = {G. Krupa Havilah and B. Sai Sri Vardhan and K. Surya Sesha Sai and G. Chandu and M. Satish and Dr. Y. Venkat},
        title = {Classification of Blood Cells from Microscopic Images Using Shallow CNN},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {5654-5659},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197139},
        abstract = {— In recent years, various diseases such as anaemia, malaria, leukaemia, and other infections have significantly affected human health. Identifying these conditions requires blood testing, which serves as an initial step in detecting abnormalities in the human body. Traditionally, blood cell identification is performed manually, making the process time-consuming and prone to human error. To overcome these limitations, modern technological approaches offer automated solutions that improve accuracy and efficiency. These advancements help reduce processing time and minimize errors, making blood cell identification more reliable for diagnostic applications.
In this work, we propose a solution for blood cell identification using deep learning techniques to classify different types of blood cells through Convolutional Neural Networks (CNN). This system is capable of identifying and classifying various blood cells such as Red Blood Cells (RBC), White Blood Cells (WBC), and platelets with the help of microscopic images. The model includes several preprocessing techniques, such as normalization, data augmentation, and noise removal, to enhance the quality of the input data.
In this system, we use a CNN model that can automatically extract features from the input data, such as shape, colour, and texture. This helps reduce the manual effort required for feature extraction. The CNN model is trained on a labelled dataset and evaluated using performance metrics such as accuracy, precision, recall, and F1-score. This approach helps automate the process of blood cell identification, reducing errors and minimizing the time required.},
        keywords = {Deep Learning; Convolutional Neural Networks (CNN); Blood Cell Classification; Medical Imaging; Artificial Intelligence},
        month = {April},
        }