This study investigates the impact of illumination levels on classification performance in microscopic cell images and proposes a novel approach for the deep learning-based diagnosis of white blood cells. The proposed method integrates statistical texture features derived from grayscale images based on GLCM 1 and LBP 2 with the Convolutional Block Attention Module (CBAM) in a hybrid architecture built upon the VGG16 model. In this architecture, both visual (RGB) and structural (texture) information are processed simultaneously, aiming to obtain deeper and more meaningful representations for classification. Within this scope, the effect of varying illumination levels on microscopic images has been evaluated in detail for the first time, and the model’s performance was tested under multiple lighting conditions.
As part of the study, nine different illumination conditions were created by adjusting light levels from –80 to +80, and the model’s classification performance under each condition was comprehensively evaluated. According to the findings, only 11 misclassifications occurred at the +40 light level, identifying this setting as the most optimal illumination condition, under which the model achieved the highest accuracy. When considering average performance metrics, the model achieved remarkable success with 99.46 % accuracy, 99.33 % F1‑score, 99.27 % recall, and 99.87 % specificity. Notably, the model performed almost flawlessly in classifying eosinophil and basophil cells.
It was concluded that hybridizing the CBAM attention mechanism with texture features significantly improved classification performance. Furthermore, the model’s robustness against illumination variability was supported by confusion matrices and error counts, emphasizing the critical role of lighting conditions in microscopic image analysis. In this regard, the study offers an innovative contribution to the literature both in terms of illumination optimization and multi-feature integration.
1. Kutlu, H., Avci, E., Özyurt, F. White blood cells detection and classification based on regional convolutional neural networks // Med Hypotheses, Churchill Livingstone, 2020, Vol. 135, p. 109472.
2. Sengur, A. et al. White Blood Cell Classification Based on Shape and Deep Features // 2019, International Conference on Artificial Intelligence and Data Processing Symposium, IDAP 2019, Institute of Electrical and Electronics Engineers Inc.
3. Navya, K.T., Prasad, K., Singh, B.M.K. Classification of blood cells into white blood cells and red blood cells from blood smear images using machine learning techniques // 2021, 2nd Global Conference for Advancement in Technology, GCAT 2021, Institute of Electrical and Electronics Engineers Inc.
4. Alkafrawi, I.M.I., Dakhell, Z.A. Blood Cells Classification Using Deep Learning Technique // Proceedings of 2022 International Conference on Engineering and MIS, ICEMIS 2022. Institute of Electrical and Electronics Engineers Inc.
5. Al-Dulaimi, K. et al. Segmentation of White Blood Cell, Nucleus and Cytoplasm in Digital Haematology Microscope Images: A Review-Challenges, Current and Future Potential Techniques // IEEE Rev Biomed Eng. IEEE Rev Biomed Eng, 2021. Vol. 14, pp. 290–306.
6. Khouani, A. et al. Automated recognition of white blood cells using deep learning // Biomed Eng Lett. Springer Verlag, 2020. Vol. 10, # 3, pp. 359–367.
7. Jiang, M. et al. White Blood Cells Classification with Deep Convolutional Neural Networks // Intern J. Pattern Recognit Artif Intell. World Scientific Publishing Co. Pte Ltd, 2018, Vol. 32, # 9.
8. Khan, S. et al. Efficient leukocytes detection and classification in microscopic blood images using convolutional neural network coupled with a dual attention network // Comput Biol Med. Elsevier Ltd, 2024, Vol. 174, p. 108146.
9. Fırat, H. Classification of microscopic peripheral blood cell images using multibranch lightweight CNNbased model // Neural Comput Appl. Springer Science and Business Media Deutschland GmbH, 2024. Vol. 36, # 4, pp. 1599–1620.
10. Vogado, L. et al. Leukemia diagnosis in blood slides using transfer learning in CNNs and SVM for classification // Elsevier LHS, Aires Engineering Applications of Artificial Intelligence, 2018, Elsevier.
11. Palta, Olcay, Çıbuk, Musa; Güldemir, H. Image Enhancement in Whıte Blood Cells Usıng Hybrıd (Chale+Gauss) Fılter and Flask-Based Web Servıce Integratıon // 7 Internatıonal Medıterranean Congress. 2025, pp. 897–906.
12. Palta, Olcay; Çıbuk, Musa; Güldemir, H. Deep Learning-Based Classification of White Blood Cells: An Ensemble Model Approach // 7 Internatıonal Medıterranean Congress, 2025, pp. 262–270.
13. Cengiz, M.S. and Cengiz, C. Numerıcal Analysıs of Tunnel LED Lıghtıng Maıntenance Factor // IIUMEJ, Dec. 2018, Vol. 19, # 2, pp. 154–163. https://doi.org/10.31436/iiumej.v19i2.1007
14. Cengiz, Ç. Relationship of Braking Distance and Rear Headlight on Highways // Light & Engineering, 2024, Vol. 32, # 2, pp. 29–36.
15. Cengiz, Ç., Aydoğdu, H., GAMMA renewal functions in censored data // Bitlis Eren Universty Journal Science Technolgy, 2015, 5 (2), pp. 97–101.
16. Efe, S.B., Varhan, D. Interior Lighting of a Historical Building by Using LED Luminaires A Case Study of Fatih Pasha Mosque // Light & Engineering, 2020, Vol. 28, # 4, pp. 77–83.
17. Cengiz, M.S. Effects of Luminaire Angle and Illumination Topology on Illumination Parameters in Road Lighting // Light & Engineering, 2020, Vol. 28, # 4, pp. 47–56.
18. S. Rüstemli, S. and M.S. Cengiz, M.S. Actıve Fılter Solutıonsın Energy Systems // Turk. J. Elec. Eng. & Comp. Sci., 2015, Vol. 23, # 6, pp. 1587–1607, Nov. 2015.
19. Cengiz, M.S. The Relationship between Maintenance Factor and Lighting Level in Tunnel Lighting // Light & Engineering, 2019, Vol. 27, # 3, pp. 75–88.
20. Guler, O., Onaygil, S. The Effect of Luminance Uniformity on Visibility Level in Road Lighting // Lighting Research & Technology, 2003, Vol. 35, # 3, pp. 199–215.
21. Cengiz, M.S. and Rüstemli, S. Passive Filter Solutions and Simulation Performance in Industrial Plants // Bitlis Eren University Journal of Science and Technology, 2016, Vol. 6, # 1, pp. 39–43, doi: 10.17678/beujst.94574.https://doi.org/10.3906/elk-1402-212.
22. Wu, P. et al. Spectral-level assessment of light pollution from urban façade lighting // Sustain Cities Soc. Elsevier, 2023. Vol. 98, p. 104827.
23. Duranay, Z.B. and Guldemir, H. Power Prediction in Photovoltaic Systems with Neural Networks: A Multi-Parameter Approach // Applied Sciences, 2025, Vol. 15, # 7, p. 3615, doi: 10.3390/APP15073615
24. Dişli, F., Gedikpınar, M., Fırat, H., Şengür, A., Güldemir, H., and Koundal, D. Epilepsy Diagnosis from EEG Signals Using Continuous Wavelet Transform-Based Depthwise Convolutional Neural Network Model // Diagnostics 2025, Vol. 15, # 1, p. 84, doi: 10.3390/DIAGNOSTICS15010084
25. Aliser, A. and Duranay, Z.B. Fire/Flame Detection with Attention-Based Deep Semantic Segmentation // Iranian Journal of Science and Technology – Transactions of Electrical Engineering, 2024, Vol. 48, # 2, pp. 705–717, doi: 10.1007/S40998-024-00697-Y/TABLES/3
26. Praharsha, C.H., Poulose, A. CBAM VGG16: An efficient driver distraction classification using CBAM embedded VGG16 architecture // Comput. Biol. Med., Elsevier Ltd, 2024, Vol. 180.
27. Li, H. et al. Reducing Video Coding Complexity Based on CNN-CBAM in HEVC // Multidisciplinary Digital Publishing Institute, Applied Sciences, 2023, Vol. 13, p. 10135.
28. Cömert, Z., Efil, F., Türkoğlu, M. Convolutional Block Attention Module and Parallel Branch Architectures for Cervical Cell Classification // Int. J. Imaging Syst. Technol., 2025, Vol. 35, # 2.
29. Göçmen, R., Çıbuk, M., Akin, E. Comparative Analysis of Deep Learning Algorithms in Fire Detection // Balkan Journal of Electrical and Computer Engineering. MUSA YILMAZ, 2024, Vol. 12, # 3, pp. 255–261.
30. Erdem, B., Karabatak, M. Cheating Detection in Online Exams Using Deep Learning and Machine Learning // Applied Sciences (Switzerland), Multidisciplinary Digital Publishing Institute (MDPI), 2025. Vol. 15, # 1, p. 400.
31. Wang, S., Zhang, X., Zhao, R. Lightweight CNNCBAM-BiLSTM EEG emotion recognition based on multiband DE features // Biomed Signal Process Control, Elsevier Ltd, 2025, Vol. 103.
32. Acevedo, A. et al. Recognition of peripheral blood cell images using convolutional neural networks // Comput Methods Programs Biomed, Elsevier, 2019, Vol. 180, p. 105020.
33. Kaynaklı, M., Palta, O., Cengiz, Ç. Solar Radiation and Temperature Effects on Agricultural Irrigation Systems // Bitlis Eren University Journal of Science and Technology, Bitlis Eren University, 2016, Vol. 6, # 1, pp. 53–58.
34. Cengiz, M.S. Simulation and Design Study for Interior Zone Luminance in Tunnel Lighting // Light & Engineering, 2019, Vol. 27, # 2, pp. 42–51.
35.Yurci, Y., Kaynaklı, M., Palta, O., Efe, S. B., & Cengiz, Ç. The performance-cost effect of the scada system on distribution networks. //IOSR Journal of Electrical and Electronics Engineering, 2016, 11(6), pp. 32–38.
36. Cengiz, Ç. (2024). The Relationship Between Electricity Consumption from Outdoor Lighting and Economic Growth // Light & Engineering, 2024, Vol. 32, # 4, pp. 14–21
37.Macawile, M.J. et al. White blood cell classification and counting using convolutional neural network // 3rd International Conference on Control and Robotics Engineering, ICCRE 2018, Institute of Electrical and Electronics Engineers Inc., pp. 259–263.
38. Çınar, A., Tuncer, S.A. Classification of lymphocytes, monocytes, eosinophils, and neutrophils on white blood cells using hybrid Alexnet-GoogleNet-SVM // SN Appl. Sci., Springer Nature, 2021. Vol. 3, # 4, pp. 1–11.
39. Habibzadeh Motlagh, M. et al. Automatic white blood cell classification using pre-trained deep learning models: ResNet and Inception // SPIE, 2018, Vol. 10696, pp. 274–281, https://doi.org/10.1117/12.2311282
40. Vogado, L.H.S. et al. Leukemia diagnosis in blood slides using transfer learning in CNNs and SVM for classification // Eng. Appl. Artif. Intell., Pergamon, 2018, Vol. 72, pp. 415–422.
41. Hegde, R.B. et al. Feature extraction using traditional image processing and convolutional neural network methods to classify white blood cells: a study // Australas Phys. Eng. Sci/ Med., Springer Netherlands, 2019. Vol. 42, # 2, pp. 627–638.
42. Sharma, S. et al. [Retracted] Deep Learning Model for the Automatic Classification of White Blood Cells // Comput. Intell. Neurosci., John Wiley & Sons, Ltd, 2022, Vol. 2022, # 1, p. 7384131.
43. Chen, Y. et al. DAFFNet: A dual attention feature fusion network for classification of white blood cells // Biomed Signal Process Control, Elsevier, 2025. Vol. 106, p. 107699.
44. Fan, H. et al. LeukocyteMask: An automated localization and segmentation method for leukocyte in blood smear images using deep neural networks // J. Biophotonics, Wiley-VCH Verlag, 2019. Vol. 12, # 7, p. e201800488.
45. Khalil, A.J., Abu-Naser, S.S. Diagnosis of Blood Cells Using Deep Learning // International Journal of Academic Engineering Research (IJAER), 2022, Vol. 6, pp. 69–84.

• Previous article
• Next article

• lighting
• CBAM
• CNN
• deep learning
• white blood cell classification
• microscopic image analysis