Patient Recognition oral.pptx ecognition-TCs

ecognition-TCs

1. Title: Patient Recognition and Smart Health Care System Sudhanshu Kumar, Monika Bhattacharya, Anju Agarwal, and Ravneet Kaur Modelling and Simulation Lab, Department of Electronics Science, Acharya Narendra Dev College, University of Delhi, Delhi-110019

2. Introduction Patient Recognition and Smart Health Care System that leverages AI to establish a secure, efficient, and reliable repository for medical records. Designed for clinics, hospitals, and diagnostic laboratories, this system streamlines healthcare operations, reduces human error, and ensures tamper-proof records while significantly improving time efficiency.

3. What is a Patient Recognition System? "A Patient recognition system is an advanced method of managing patient records by using facial recognition technology and SQL. It captures images of individuals as they enter a facility, and automatically logs their data based on facial matches." "The system scans and stores facial features of authorized individuals in a database. When someone approaches, the system compares the live image with stored data and login and patient able to see there visualize medical data if a match is found."

4. METHODOLOGY

5. RESULT Using OPENCV MODEL Testing results show that for the input image with the resolution 1920×1080, real-time face detection can be implemented, and detection accuracy is 83 % Classification Report: Accuracy: 0.83 Precision: 0.81 Recall: 0.80 F1-Score: 0.82 Using Dlib (ResNet-128D) Testing results show that for the input image with the resolution 1920×1080, real-time face detection can be implemented, and detection accuracy is 85 % Classification Report: Accuracy: 0.86 Precision: 0.82 Recall: 0.78 F1-Score: 0.87

6. Future Scope of Face Recognition Advancements in AI: As AI and machine learning continue to evolve, face recognition systems are becoming more accurate and efficient. Future advancements may include real-time processing, improved accuracy, and the ability to recognize faces in even more challenging conditions. Broader Applications: Beyond attendance, face recognition is expected to be integrated into more aspects of everyday life, such as personalized customer experiences, healthcare monitoring, and smart cities. 19th August,2024

7. FUTURE SCOPE Reinforcement Learning : Adapt to new patient features dynamically. Blockchain : Immutable audit trails for enhanced security. IoT Integration : Wearables for real-time health monitoring.

8. Acknowledgement We would like to extend our heartfelt appreciation and profound gratitude to our esteemed mentors, Prof. Ravneet Kaur and Dr. Monika Bhattacharya, and Prof. Anju Agarwal for their unwavering support and invaluable guidance throughout our journey.  A special note of thanks to Dr. Amit Garg and all the faculty members of my department whose exemplary mentorship, diligent monitoring, and constant encouragement have been instrumental in the successful completion of our project.  We also express our sincere thanks to the dedicated support staff members whose assistance played a pivotal role in making our project a resounding success. Our heartfelt thanks to our friends for helping us with the project. Our deepest gratitude goes to our esteemed Principal Dr. Ravi Toteja , for providing us with the invaluable opportunity to embark on this meaningful project. Their blessings and unwavering support will undoubtedly propel us further in the journey of life. Lastly, a big thanks to all for the invaluable contributions to this research project.

9. References Rovai , M. (2019, September 20). Real-Time Face Recognition: An End-To-End Project. Medium. https://towardsdatascience.com/real-time-face-recognition-an-end-to-end-project-b738bb0f7348 Python, R. (n.d.). Face Recognition with Python, in Under 25 Lines of Code – Real Python. Realpython.com. https://realpython.com/face-recognition-with-python/ Real Python. (2018, December 5). Sending Emails With Python. Realpython.com; Real Python. https://realpython.com/python-send-email/ “Unsupported image type, must be 8bit gray or RGB image.” · Issue #136 · ageitgey / face_recognition . (n.d.). GitHub. Retrieved July 28, 2024, from https://github.com/ageitgey/face_recognition/issues/136 https://link.springer.com/article/10.1007/s40745-015-0064-6 https://link.springer.com/article/10.1007/s42979-021-00448-4

10. BY SUDHANSHU KUMAR