1. Selvan, M. A. (2024). Deep Learning Techniques for Comprehensive Emotion Recognition and Behavioral Regulation.
2. Selvan, M. A. (2024). SVM-Enhanced Intrusion Detection System for Effective Cyber Attack Identification and Mitigation.
3. Selvan, M. A. (2024). IoT-Integrated Smart Home Technologies with Augmented Reality for Improved User Experience.
4. Selvan, M. A. (2024). Multipath Routing Optimization for Enhanced Load Balancing in Data-Heavy Networks.
5. Selvan, M. A. (2024). Transforming Consumer Behavior Analysis with Cutting-Edge Machine Learning.
6. FELIX, A. S. M. M. D., & KALAIVANAN, X. D. M. S. Averting Eavesdrop Intrusion in Industrial Wireless Sensor Networks.
7. Selvan, M. A. (2021). Robust Cyber Attack Detection with Support Vector Machines: Tackling Both Established and Novel Threats.
8. Selvan, M. A. (2023). INDUSTRY-SPECIFIC INTELLIGENT FIRE MANAGEMENT SYSTEM.
9. Selvan, M. A. (2023). FIRE MANAGEMENT SYSTEM FOR INDUTRIAL SAFETY APPLICATIONS.
10. Selvan, M. A. (2023). CONTAINMENT ZONE ALERTING APPLICATION A PROJECT BASED LEARNING REPORT.
11. Selvan, M. A. (2023). A PBL REPORT FOR CONTAINMENT ZONE ALERTING APPLICATION.
12. Reka, R., R. Karthick, R. Saravana Ram, and Gurkirpal Singh. “Multi head self-attention gated graph convolutional network based multi‑attack intrusion detection in MANET.” Computers & Security 136 (2024): 103526.
13. Meenalochini, P., R. Karthick, and E. Sakthivel. “An Efficient Control Strategy for an Extended Switched Coupled Inductor Quasi-Z-Source Inverter for 3 Φ Grid Connected System.” Journal of Circuits, Systems and Computers 32.11 (2023): 2450011.
14. Karthick, R., et al. “An optimal partitioning and floor planning for VLSI circuit design based on a hybrid bio-inspired whale optimization and adaptive bird swarm optimization (WO-ABSO) algorithm.” Journal of Circuits, Systems and Computers 32.08 (2023): 2350273.
15. Rajagopal RK, Karthick R, Meenalochini P, Kalaichelvi T. Deep Convolutional Spiking Neural Network optimized with Arithmetic optimization algorithm for lung disease detection using chest X-ray images. Biomedical Signal Processing and Control. 2023 Jan 1;79:104197.
16. Karthick, R., and P. Meenalochini. “Implementation of data cache block (DCB) in shared processor using field-programmable gate array (FPGA).” Journal of the National Science Foundation of Sri Lanka 48.4 (2020).
17. Karthick, R., A. Senthilselvi, P. Meenalochini, and S. Senthil Pandi. “Design and analysis of linear phase finite impulse response filter using water strider optimization algorithm in FPGA.” Circuits, Systems, and Signal Processing 41, no. 9 (2022): 5254-5282.
18. Karthick, R., and M. Sundararajan. “SPIDER-based out-of-order execution scheme for HtMPSOC.” International Journal of Advanced Intelligence paradigms 19.1 (2021): 28-41.
19. Karthick, R., Dawood, M.S. & Meenalochini, P. Analysis of vital signs using remote photoplethysmography (RPPG). J Ambient Intell Human Comput 14, 16729–16736 (2023). https://doi.org/10.1007/s12652-023-04683-w
20. Elechi, P., & Onu, K. E. (2022). Unmanned Aerial Vehicle Cellular Communication Operating in Non-terrestrial Networks. In Unmanned Aerial Vehicle Cellular Communications (pp. 225-251). Cham: Springer International Publishing.
21. Prasad, B. V. V. S., Mandapati, S., Haritha, B., & Begum, M. J. (2020, August). Enhanced Security for the authentication of Digital Signature from the key generated by the CSTRNG method. In 2020 Third International Conference on Smart Systems and Inventive Technology (ICSSIT) (pp. 1088-1093). IEEE.
22. Khandelwal, A. R., Mutneja, L., Thakar, P., & Patil, P. (2019). Basics and Applications of Big Data.
23. Meena, S. B., Patil, P. R., Kandharkar, S. R., Hemalatha, N., Khade, A., Dixit, K. K., & Chinthamu, N. (2024). The Evolution Of Smart Grid Technologies: Integrating Renewable Energy Sources, Energy Storage, And Demand Response Systems For Efficient Energy Distribution. Nanotechnology Perceptions, 1098-1109.
24. Virmani, D., Ghori, M. A. S., Tyagi, N., Ambilwade, R. P., Patil, P. R., & Sharma, M. K. (2024, March). Machine Learning: The Driving Force Behind Intelligent Systems and Predictive Analytics. In 2024 International Conference on Trends in Quantum Computing and Emerging Business Technologies (pp. 1-6). IEEE.
25. Kalluru, S. R., & Gurijala, P. K. R. Increasing Efficiency of Goods Receipt with Mobility Solutions.
26. Gurijala, P. K. R., & Kalluru, S. R. Enhancing Manufacturing Efficiency with Mobility Applications.
27. Gurijala, P. K. R., Kalluru, S. R., & Dave, R. Maximizing Procurement Efficiency through Purchase Requisitions Load Building.
28. Kalluru, S. R., & Gurijala, P. K. R. Improving Putaway Efficiency Through Innovative Solutions.
29. Lanka, S., Konjeti, P. C., & Pinto, C. A. (2024, June). A Review: Complete Analysis of the Cache Architecture for Better Performance. In 2024 Second International Conference on Inventive Computing and Informatics (ICICI) (pp. 768-771). IEEE.
Page No: 567 - 574
Abstract : The core objective of this project is to recognize and reconstruct distorted facial images, particularly in the context of accidents. This involves using deep learning techniques to analyze the features of a distorted face and regenerate it into a recognizable form. Deep learning models are well-suited for this task due to their ability to learn complex patterns and representations from data the input data consists of distorted facial images, typically obtained from MRI scans of accident victims. These images may contain various types of distortions such as swelling, bruising, or other injuries that affect facial appearance. By using MRI images, the project can focus on medical applications where accurate facial reconstruction is crucial for diagnosis or identification purposes.Two common pre-trained deep learning models, VGG19 and 3D CNN, are chosen for this project. VGG19 is a convolutional neural network (CNN) known for its effectiveness in image classification tasks, while 3D CNNs are capable of capturing spatial and temporal features from volumetric data like MRI scans. By leveraging these pre-trained models, the project can benefit from their learned representations and potentially achieve better reconstruction accuracy. The performance of the deep learning models is evaluated using metrics such as accuracy and error rate. Accuracy measures how well the models are able to reconstruct the facial features compared to the original images, while the error rate indicates the frequency of incorrect reconstructions. By quantifying these metrics, the project can assess the effectiveness of each algorithm in reconstructing distorted faces. The accuracy levels of VGG19 and 3D CNN are compared using the performance metrics. This comparison helps in identifying which model performs better in the task of facial reconstruction from distorted images. Visualizing the results in the form of a graph provides a clear and concise way to understand the comparative performance of the algorithms. The ultimate goal of this project is to develop a system that can accurately reconstruct distorted faces, which can be invaluable in identifying accident victims or assisting in medical treatments. By providing a reliable method for facial reconstruction, this technology can potentially save lives and improve outcomes for individuals involved in accidents.
Keyword Convolutional Neural Network (CNN), VGG19, Deep Learning, MRI Images, Local Binary Pattern
Reference: