Affiliation:
1. J N N College of Engineering, Shimoga, India
Abstract
Analysis of the damaged vehicle that can be automatically claiming insurance that takes human resource, time and effort. Image processing and machine learning techniques are analysing the vehicle damage in the proposed solution. In Advanced solution helps to speed up the claiming process sufficiently. Consider a situation, if a person is driving a car they met an accident the vehicle owner can taken a few photos of the damaged car from a mobile phone that can be send to the insurance company and can just upload the photos to the system. The system can analyse the damage, severity of the damage as well as location of the damage. In this proposed project the insurance company can machine-driven the car damage analysis process without the need for humans to analyse the damage done to the car. Therefore, it is a very challenging task for quality of computer vision techniques and also Machine learning technologies.
Reference6 articles.
1. A.Neela Madheswari, J.haripriya, G.Kiruthika, R.M.Meyammai Mahendra Engineering college, India,exterior vehicular damage detection using deep learning, department of computer science and engineering.
2. Girish N, Mohammed Aqeel Arshad, car damage detection using machine learning. International journal of advances research in computer and communication engineering,vol. 10, issue 8, August 2021 DOI 10.17148/IJARCCE.2021.10808.
3. Phyu Mar Kyu ,car damage detection and classification, faculty of information technology king Mongkut’s institute of technology ladkrabang Bangkok,Thailand 62606003@kmitl.ac.in.
4. S. Jayawardena, Image based automatic vehicle damage detection. PhD thesis, College of Engineering and Computer Science (CECS), 12 2013.
5. S. Gontscharov, H Baumgartel, A.Kneifel, and K.-L. Krieger, Algorithm development for minor damage identification in vehicle bodies using adaptive sensor data processing," Procedia Technology, vol. 15, pp. 586 {594, 2014. 2nd International Conference on System-Integrated Intelligence: Challenges for Product and Production Engineering.