International Journal of Intelligent Systems and Applications (IJISA)
IJISA Vol. 18, No. 1, 8 Feb. 2026
Cover page and Table of Contents: PDF (size: 1149KB)
Non-invasive A, B and O Blood Group Identification from Ocular Images Using a Hybrid Multi-modal Deep Learning Approach
PDF (1149KB), PP.28-44
Views: 0 Downloads: 0
Author(s)
Venkatesh Koreddi
1,*
Kattupalli Sudhakar
1
M. Lavanya
1
G. Gayathri
1
K. Sri Venkata Naga Gowri Deepika
1
K. Naga Surya Sabari Prasad
1
G. Balasri Lakshmi Vishnupriya
1
Index Terms
Blood Group Detection, Ocular Image Analysis, Deep Learning in Hematology, Multi-modal Attention Network, Contactless Biometric Diagnostics and O Classification
Abstract
Traditional blood group identification methods, such as serological testing or fingerprint based biometric analysis, require physical contact, specialized equipment and laboratory processing. To remove these boundaries, this study proposes a novel, which is a completely contact -free approach to determine A, B and O blood groups using ocular image analysis. Unlike the previous methods that rely on fingerprint or vein pattern, our technique takes advantage of iris color, conjunctival vasculature, limbal ring intensity, and other eye field features to classify blood group types. A custom dataset of 3,000 eye images was collected from diverse demographics under different lighting conditions. The key features were extracted using hyperspectral imaging and deep learning-based segmentation. We introduce a hybrid multi-modal attention network (HMAN), which integrates transformer-based spatial encoding, convolutional feature extraction, and self-attention mechanisms to enhance classification accuracy. The proposed model obtained 97.1%accuracy, improved ResNet-50 (92.3%) and KushalNet-B4 (94.5%). Ablation studies confirmed that multi-modal feature fusion improves discriminatory capacity for blood group-specific patterns.
This work establishes the first AI-operated, non-invasive blood group detection framework with emergency medical, blood donor screening, and potential applications in biometric diagnostics. Future research will focus on real-time deployment, dataset expansion, and multi-modal physiological feature integration to improve robustness. Our findings represent a major advancement in contact-free medical diagnosis, which paves the way for AI enhance hematological classification.
Cite This Paper
Venkatesh Koreddi, Kattupalli Sudhakar, M. Lavanya, G. Gayathri, K. Sri Venkata Naga Gowri Deepika, K. Naga Surya Sabari Prasad, G. Balasri Lakshmi Vishnupriya, "Non-invasive A, B and O Blood Group Identification from Ocular Images Using a Hybrid Multi-modal Deep Learning Approach", International Journal of Intelligent Systems and Applications(IJISA), Vol.18, No.1, pp.28-44, 2026. DOI:10.5815/ijisa.2026.01.03
Reference
[1]Jalali, M., Prokscha, A., Yan, Y., Kubiczek, T., Taro Svejda, J., Preu, S., Balzer, J., Kaiser, T., Erni, D.: Non-invasive glucose sensing via the fingernail bed using thz radiation. In: Current Directions in Biomedical Engineering, vol. 9, pp. 507– 510 (2023). De Gruyter.
[2]Kondermann, C., Kondermann, D., Yan, M.: Blood vessel classification into arterioles and veins in retinal images. In: Medical Imaging 2007: Image Processing, vol. 6512, pp. 1401–1409 (2007). SPIE
[3]Cadd, S., Li, B., Beveridge, P., O’Hare, W.T., Campbell, A., Islam, M.: The non-contact detection and identification of blood-stained fingerprints using visible wavelength reflectance hyperspectral imaging: Part 1. Science & Justice 56(3), 181–190 (2016)
[4]Kaiser, V., Bauernfeind, G., Kreilinger, A., Kaufmann, T., Ku¨bler, A., Neuper, C., Mu¨ller-Putz, G.R.: Cortical effects of user training in a motor imagery-based brain–computer interface measured by fnirs and eeg. Neuroimage 85, 432–444 (2014).
[5]Haque, M.R., Raju, S.T.U., Golap, M.A.-U., Hashem, M.: A novel technique for non-invasive measurement of human blood component levels from fingertip video using dnn based models. IEEE Access 9, 19025–19042 (2021)
[6]Maiti, A., Elberink, S.O., Vosselman, G.: Transfusion: Multi-modal fusion net- work for semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6537–6547 (2023)
[7]Akita, K., Kuga, H.: Pattern recognition of blood vessel networks in ocular fundus images. In: Medical Imaging and Image Interpretation, vol. 375, pp. 436–443 (1982). SPIE
[8]Kurtuldu, H., Oktan, A.D., Candan, H., Cihangiro˘glu, B.S.: Red blood cell analysis by hyperspectral imaging. Natural and Applied Sciences Journal 1(2), 1–7 (2018)
[9]Hasan, M.K., Aziz, M.H., Zarif, M.I.I., Hasan, M., Hashem, M., Guha, S., Love, R., Ahamed, S.: Help me: Recommendations for non-invasive hemoglobin level prediction in a mobile-phone environment. JMIR Mhealth Uhealth (2019)
[10]Patil, V., Ingle, D.: An association between fingerprint patterns with blood group and lifestyle-based diseases: a review. Artificial intelligence review 54(3), 1803– 1839 (2021)
[11]Lee, J.Y., Clarke, M.L., Tokumasu, F., Lesoine, J.F., Allen, D.W., Chang, R., Litorja, M., Hwang, J.: Absorption-based hyperspectral imaging and analysis of single erythrocytes. IEEE Journal of Selected Topics in Quantum Electronics 18(3), 1130–1139 (2011)
[12]Perdomo Charry, O.J., Gonz´alez, F.A.: A systematic review of deep learning methods applied to ocular images. Ciencia e Ingenieria Neogranadina 30(1), 9–26 (2020)
[13]Singh, K., Singh, A.: Artificial intelligence in hematology: A critical perspective. Journal of Clinical and Experimental Hematology 3(1), 60–66 (2024)
[14]Madan, S., Lentzen, M., Brandt, J., Rueckert, D., Hofmann-Apitius, M., Fr¨ohlich, H.: Transformer models in biomedicine. BMC Medical Informatics and Decision Making 24(1), 214 (2024)
[15]Blue, M.N.M.: Validity of body composition assessment in racial and ethnic minority populations. PhD thesis, The University of North Carolina at Chapel Hill (2020)
[16]Kent, A.R., Elsing, S.H., Hebert, R.L.: Conjunctival vasculature in the assessment of anemia. Ophthalmology 107(2), 274–277 (2000)
[17]Hemalatha, S., Nimalanantham, N., Pawin, A.: Blood group typing using CNN. In: 2025 3rd International Conference on Intelligent Systems, Advanced Computing and Communication (ISACC), pp. 151–156 (2025). IEEE
[18]Daeschlein, G., Langner, I., Wild, T., Podewils, S., Sicher, C., Kiefer, T., Ju¨nger, M.: Hyperspectral imaging as a novel diagnostic tool in the microcirculation of wounds. Clinical hemorheology and microcirculation 67(3-4), 467–474 (2017)
[19]Jain, P., Bauskar, S., Gyanchandani, M.: Neural network-based non-invasive method to detect anemia from images of eye conjunctiva. International Journal of Imaging Systems and Technology 30(1), 112– 125 (2020)
[20]Khan, A.I., Khan, M., Khan, R.: Artificial intelligence in point-of-care testing. Annals of Laboratory Medicine 43(5), 401–407 (2023)
[21]Du, J., Li, W., Lu, K., Xiao, B.: An overview of multi-modal medical image fusion. Neurocomputing 215, 3–20 (2016)
[22]Rosales, M.A.: Human blood type classification using feature selection and optimized machine learning model. In: 2024 IEEE International Conference on Imaging Systems and Techniques (IST), pp. 1–6 (2024). IEEE
[23]Lin, D., Zheng, Z., Wang, Q., Huang, H., Huang, Z., Yu, Y., Qiu, S., Wen, C., Cheng, M., Feng, S.: Label-free optical sensor based on red blood cells, laser tweezers Raman spectroscopy analysis for abo blood typing. Optics Express 24(21), 24750–24759 (2016)
[24]Garcia-Martin, R., Sanchez-Reillo, R.: Wrist vascular biometric recognition using a portable contactless system. Sensors 20(5), 1469 (2020)
[25]Cui, R., Yu, H., Xu, T., Xing, X., Cao, X., Yan, K., Chen, J.: Deep learning in medical hyperspectral images: A review. Sensors 22(24), 9790 (2022)
[26]Hagan, S., Martin, E., Enr´ıquez-de-Salamanca, A.: Tear fluid biomarkers in ocular and systemic disease: potential use for predictive, preventive and personalised medicine. Epma Journal 7, 1–20 (2016)
[27]Obstfeld, A.E.: Hematology and machine learning. The Journal of Applied Laboratory Medicine 8(1), 129–144 (2023)
[28]Pinto, C., Parab, J., Naik, G.: Non-invasive hemoglobin measurement using an embedded platform. Sensing and Bio-Sensing Research 29, 100370 (2020)
[29]Henry, E.U., Emebob, O., Omonhinmin, C.A.: Vision transformers in medical imaging: A review. arXiv preprint arXiv:2211.10043 (2022)
[30]Holmes, O., Mason, R., Price, D.: Scleral tortuosity in blood group AB. Clin. Anat. 34(6), 912–918 (2021) https://doi.org/10.1002/ca.23762
[31]Zekavat, S.M., Raghu, V.K., Trinder, M., Ye, Y., Koyama, S., Honigberg, M.C., Yu, Z., Pampana, A., Urbut, S., Haidermota, S., et al.: Deep learning of the retina enables phenome-and genome-wide analyses of the microvasculature. Circulation 145(2), 134–150 (2022)
[32]Nayak, S., Blumenfeld, N.R., Laksanasopin, T., Sia, S.K.: Point-of-care diagnostics: recent developments in a connected age. Analytical chemistry 89(1), 102–123 (2017)
[33]Owen, C.: Quantitative analysis of conjunctival vasculature. PhD thesis, City, University of London (1998)
[34]Sicher, C., Rutkowski, R., Lutze, S., Podewils, S., Wild, T., Kretching, M., Daeschlein, G.: Hyperspectral imaging as a possible tool for visualization of changes in hemoglobin oxygenation in patients with deficient hemodynamics– proof of concept. Biomedical Engineering/Biomedizinische Technik 63(5), 609– 616 (2018)
[35]Bjorgan, A., Randeberg, L.L.: Towards real-time medical diagnostics using hyperspectral imaging technology. In: European Conference on Biomedical Optics, p. 953712 (2015). Optica Publishing Group
[36]Shojaei, A., Moradi, A., Gohari, M.: Biometric indices and their relation with age, sex, and ethnicity. Journal of Ophthalmic and Optometric Sciences 1(3), 5–12
[37]Breslauer, D.N., Maamari, R.N., Switz, N.A., Lam, W.A., Fletcher, D.A.: Mobile phone-based clinical microscopy for global health applications. PloS one 4(7), 6320 (2009)
[38]Bharathi, P.G., Berks, M., Dinsdale, G., Murray, A., Manning, J., Wilkinson, S., Cutolo, M., Smith, V., Herrick, A.L., Taylor, C.J.: A deep learning system for quantitative assessment of microvascular abnormalities in nailfold capillary images. Rheumatology 62(6), 2325–2329 (2023)
[39]Ujgare, N.S., Singh, N.P., Verma, P.K., Patil, M., Verma, A.: Non-invasive blood group prediction using optimized efficientnet architecture: A systematic approach. Int. J. Inf. Gen. Signal Process. (2024).
[40]Yoon, J.: Hyperspectral imaging for clinical applications. BioChip Journal 16(1), 1–12 (2022)
[41]Zhu, Y., Yin, X., Wee-Chung Liew, A., Tian, H.: Privacy-preserving in medical image analysis: A review of methods and applications. In: International Conference on Parallel and Distributed Computing: Applications and Technologies, pp. 166–178 (2024). Springer.
[42]Abdelmonem, M., Cai, W., Kilambi, S., Yoshizuka, S., Nguyen, A., Quach, T., Howard, E., Chang, S., Vukic, K., Shan, H., et al.: Blood type verification rejection rate reduction. American Journal of Clinical Pathology 160(Supplement 1), 106– 107 (2023)
[43]Siddiqui, E.F., Ahmed, T., Nayak, S.K.: A decision tree approach for enhancing real-time response in Exigent healthcare unit using edge computing. Measurement: Sensors 32, 100979 (2024)
[44]Naili, Y.T., Mangkunegara, I.S., Purwono, P., Baballe, M.A.: Regulatory challenges in AI-based diagnostics: Legal implications of ai use in medical diagnostics. In: BIO Web of Conferences, vol. 152, p. 01034 (2025). EDP Sciences
[45]Marois, M., Jacques, S.L., Paulsen, K.D.: Optimal wavelength selection for optical spectroscopy of hemoglobin and water within a simulated light-scattering tissue. Journal of biomedical optics 23(7), 071202–071202 (2018)