Final Phase PPT.pptxxxxxxxxxxxxxxxxxxxxxxxxxxxx

"Smart claim" refers to a modern approach to managing insurance claims, often using technology like artificial intelligence (AI) and automation to streamline the process. These systems aim to improve efficiency and accuracy by automating tasks like status checking, fraud detection, and decision-making, which can lead to faster processing, reduced costs, and a better customer experience.

1. EAST WEST INSTITUTE OF TECHNOLOGY (Affiliated to Visvesvaraya Technological University, Belgaum, Karnataka) Submitted By PRASHANTH (1EW21CS110) ABHISHEKA B C (1EW22CS400) KARTHIK G (1EW22CS407) LAKSHMINARSHMIA P K (1EW22CS410) Under the Guidance of Prof. LAXMI Assistant Professor Dept of CSE,EWIT 2024-25 DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING PROJECT PRESENTATION ON “ BLOOD GROUP DETECTION BY USING FINGERPRINT ”

2. LIST OF CONTENTS INTRODUCTION ABSTRACT LITERATURE SURVEY PROBLEM STATEMENT OBJECTIVES METHODOLOGIES PROPOSED SYSTEM IMPLEMENTATION CONCLUSION REFERENCES 30-12-2024 3 2

3. INTRODUCTION Blood group detection using fingerprint patterns is a non-invasive method that leverages deep learning for accurate predictions. This approach utilizes advanced image processing techniques to analyze fingerprint features linked to specific blood groups. Traditional methods of blood group detection involve blood sample analysis, which can be invasive, time-consuming, and require specialized equipment. This novel methodology aims to provide a non-invasive, rapid, and accessible alternative by analyzing the unique features of fingerprints.

4. NEED FOR BLOOD GROUP CLASSIFICATION Blood group identification is critical for medical procedures such as blood transfusions, organ transplants, and managing complications during pregnancy. Traditional methods of blood group identification, though effective, are time-consuming and prone to human error, especially in emergency situations. Thus, there is a growing need for more efficient, automated, and reliable blood group prediction systems. 30-12-2024 3 4

5. History of Blood Group Classification The ABO blood group system was discovered by Karl Landsteiner in 1901, categorizing blood into four groups: A, B, AB, and O. In 1940, Landsteiner and Wiener introduced the Rh system, adding Rh-positive ( Rh +) and Rh-negative ( Rh -) classifications, further improving blood compatibility. 30-12-2024 3 5

6. ABSTRACT This project explores using deep learning to predict blood groups from fingerprint images, providing a non-invasive alternative to traditional methods. Utilizing Convolutional Neural Networks (CNNs), the approach identifies patterns in fingerprints to classify blood groups (A, B, AB, O). A dataset of fingerprint images paired with blood group labels is pre-processed through normalization and augmentation to enhance image quality and diversity. The CNN model is trained to detect features correlating with blood groups, offering a fast, accurate, and accessible solution for blood group detection. This innovation is particularly useful in resource-limited settings or emergencies requiring rapid blood typing. 30-12-2024 3 6

7. LITE R ATURE SURVEY Title Author Year of Publication Description Advantages Disadvantages Artificial Intelligence and Image Processing Techniques for Blood Group Prediction Tannmay Gupta 2024 This paper proposes using artificial intelligence (AI) and image processing techniques to automate blood group classification, traditionally done manually. Reduces manual errors Speeds up blood group detection Provides more accurate results using AI techniques Requires a robust dataset for training May not work well with poor-quality images Initial setup costs can be high Blood Group Detection Through Fingerprint Images Using Image Processing (KNN) G. Mounika, M. Anusha, D. Gopika, B. Siva Kumari 2024 This study proposes using image processing and the K-Nearest Neighbors (KNN) algorithm to detect blood groups based on fingerprint patterns. Non-invasive and cost-effective method for blood group detection. High accuracy due to the KNN algorithm. Reduces the need for traditional blood tests. Relies on a well- labeled training dataset. Accuracy depends on the quality of the fingerprint image. 30-12-2024 3 7

8. Title Author Year of Publication Description Advantages Disadvantages Blood Group Determination Using Fingerprint T. Nihar , K. Yeswanth , K. Prabhakar 2024 This paper presents a method to determine blood groups through fingerprint analysis, using biometric and machine learning techniques. Ridge patterns and antigens in sweat are used to classify blood groups. Fast and easy blood group detection Useful in emergencies and forensic cases Needs advanced equipment. Requires validation with large datasets Accuracy depends on data and technology Fingerprint Based Blood Group Prediction Using Deep Learning Swathi P, Sushmita K, Prof. Kavita V Horadi 2024 This study explores using fingerprint patterns and deep learning techniques, specifically CNN, to predict an individual's blood group. It highlights the uniqueness of fingerprints as a biometric identifier and their potential to be correlated with blood types (ABO and Rh systems). Reliable and non-invasive biometric identification. Accuracy depends on fingerprint image quality. Focuses mainly on the ABO blood group system. 30-12-2024 3 8

9. Titie Author Year of Publication Description Advantages Disadvantages Blood Group Detection through Finger Print Images using Image Processing Dr. M Prasad, Amrutha 2023 This project proposes a non-invasive blood group detection system using fingerprint images and CNN-based image processing techniques. It aims to automate and improve blood typing. Faster than traditional methods. Automated and requires less human intervention. Requires large and well- labeled datasets for accurate predictions. A Novel Approach for ABO Blood Group Prediction using Fingerprint through Optimized Convolutional Neural Network Vijaykumar Patil, D. R. Ingle 2022 This study proposes a method to predict ABO blood groups based on fingerprint patterns using an optimized CNN. It compares the performance of the proposed model with other CNN architectures and achieves 95.27% accuracy. Innovative approach combining fingerprint analysis with blood group prediction. Uses deep learning for automatic feature extraction. Relies on the quality of the fingerprint data. Requires significant computational resources. Limited to ABO blood group prediction. 30-12-2024 3 9

10. PROBLEM IDENTIFICATION Traditional blood group detection is invasive, time-consuming, and challenging in remote areas due to the need for specialized equipment and trained personnel. There is a need for a rapid, non-invasive, and easily accessible method for blood group detection, especially in emergency or resource-limited settings. This project proposes using CNN to analyze fingerprint images for predicting blood groups, offering a faster and more accessible alternative.

11. OBJECTIVES OF THE PROJECT Develop a Non-Invasive Blood Group Detection System Utilize Deep Learning for Fingerprint Analysis Build a Comprehensive Dataset Achieve High Classification Accuracy Provide a Rapid and Accessible Alternative Improve Healthcare Efficiency

12. PROPOSED SYSTEM SYSTEM ARCHITECTURE 30-12-2024 3 12

13. CLASS DIAGRAM 30-12-2024 3 13

14. FLOW CHART 30-12-2024 14

15. SEQUENCE DIAGRAM 30-12-2024 15

16. IMPLEMENTATION 30-12-2024 16 IMPORTING NECESSARY LIBRARIES AND SETTING UP DEVICE (CUDA OR CPU)

17. 30-12-2024 17 LOADING AND SPLITTING THE DATASET

18. 30-12-2024 3 18 DEFINING THE SIMPLE CNN MODEL

19. 30-12-2024 3 19 TRAINING MODEL

20. 30-12-2024 20 Fig : Methodology Fig : Dataset RESULTS

21. 30-12-2024 3 21 Fig : User Sign Up page Fig : Login

22. 30-12-2024 22 Fig : Blood Group Prediction Page Fig : Fingerprint Uploaded

23. 30-12-2024 3 23 Fig : Predicate Blood group

24. 30-12-2024 24

25. CONCLUSION This project introduces an innovative method for blood group detection using fingerprint biometrics and deep learning, offering a rapid, non-invasive alternative to traditional blood typing. By applying convolutional neural networks (CNNs), the model detects patterns in fingerprints linked to blood group markers. The solution ensures accessibility, privacy, and data security. Although challenges remain in accuracy and dataset diversity, this study paves the way for future research and improvements. Overall, it highlights the potential of AI and biometrics to enhance personalized healthcare and emergency response globally.

26. REFERENCES [1] Artificial Intelligence and Image Processing Techniques for Blood Group Prediction. Gupta, T. (2024). Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab, India.  [2] Blood Group Determination Using Fingerprint Nihar , T., Yeswanth , K., & Prabhakar , K. (2024). Blood group determination using fingerprint. MATEC Web of Conferences, 392, 01069. https://doi.org/10.1051/matecconf/202439201069 [3] Blood group detection through fingerprint images using image processing (KNN). Mounika , G., Anusha , M., Gopika , D., & Siva Kumari , B. (2024). International Research Journal of Engineering and Technology (IRJET), 11(03), 1225-1230. e-ISSN: 2395-0056, p-ISSN: 2395-0072. Retrieved from www.irjet.net . [4] Blood Group Detection Through Fingerprint Images Using Image Processing. Prasad, M., & Amrutha , (2023). International Journal for Research in Applied Science & Engineering Technology (IJRASET), 11(7), 1350-1354. https://doi.org/10.22214/ijraset.2023.54878 [5] A novel approach for ABO blood group prediction using fingerprint through optimized convolutional neural network. Patil , V., & Ingle, D. R. (2022). International Journal of Intelligent Systems and Applications in Engineering, 10(1), 60–68. https://doi.org/10.1039/b000000x [6] Fingerprint Based Blood Group Prediction Using Deep Learning. Swathi , P., Sushmita , K., & Horadi , K. V. (2024). International Journal of Advanced Research in Science, Communication and Technology (IJARSCT), 4(1), February 2024. ISSN (Online) 2581-9429. 30-12-2024 26

27. [7] Blood group detection using image processing. Priyadharashini , M., Priyadarshini , S., Sathya , M., & Karthikeyan , P. (2023). International Journal of Research and Analytical Reviews (IJRAR), 10(1), 766-768. https://doi.org/10.0000/ijrar23a2574 [8] Implementation of Blood Group Detection using CNN and Python. Usha , K., Kollapudi , H. S. S., & Mourya , B. A. (2023). Journal of Emerging Technologies and Innovative Research (JETIR), 10(5), 1-9. https://www.jetir.org/papers/JETIR2305728  [9] Blood Group Detection Using Image Processing and Deep Learning. Ganta , J. S., Roopa , M. Y., Rishitha , M., & Pulivarthi , J. S. (2024). International Research Journal of Engineering and Technology (IRJET), 11(4), 97-104. https://www.irjet.net [10] Sarker , I.H. "Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications, and Research Directions." SN COMPUT. SCI., 2, 420 (2021). https://doi.org/10.1007/s42979-021-00815-1 [11] Alzubaidi , L., Zhang, J., Humaidi , A.J., et al. "Review of deep learning: concepts, CNN architectures, challenges, applications, future directions." J Big Data, 8, 53 (2021). https://doi.org/10.1186/s40537-021-00444-8 [12] Chellappa , R., Theodoridis , S., and van Schaik , A. "Advances in Machine Learning and Deep Neural Networks," Proceedings of the IEEE, vol. 109, no. 5, pp. 607-611, May 2021. https://doi.org/10.1109/JPROC.2021.3072172 [13] Swathi , P., Sushmita , K., and Horadi , K.V. "Fingerprint Based Blood Group Prediction Using Deep Learning." International Journal of Advanced Research in Science, Communication and Technology (IJARSCT), vol. 4, no. 1, February 2024. ISSN (Online) 2581-9429. 30-12-2024 3 27

28. THANK YOU 30-12-2024 28