Car Exterior Damage Detection Using Mask R-CNN

March 2020
Vol-6, Issue-2
Paper ID: 11563
ISSN: 2395-4396
Downloads: 59
Download PDF

Abstract & Details

Research Area
Computer Science and Engineering
Keywords
Car Exterior Damage Classification CNN Transfer Learning Convolutional Auto-encoders Mask R-CNN
Abstract
Recently, the production of image-based vehicle insurance is an important area with considerable scope for automation reach. In this paper we consider the issue of classifying car damage, where some of the categories may be fine-granular. To this reason, we are exploring deep learning-based techniques. Initially we try to train a CNN directly with a collection of training data. However, it's not working well due to a small collection of labeled data. Hence, we investigate the domain-specific pre-training effect accompanied by fine-tuning with a large number of annotated training-data. As Faster R-CNN and SVM have not identified damaged cars with high accuracy, and the Cascade R-CNN takes an immense amount of time to train and check the data that we are working on to fit. Hence, we are training data into a R-CNN Mask that produces adequate results compared to traditional Neural Networks. Though there is a lot of unknowns such as partial images, Hence the classifier was built to detect amorphous damages. The model is layered over 3 classifications of detecting the car and examining whether the damage dealt is high or low. Finally, the classifier is projected with the flask environment to make the working experience easier, since it runs on a localhost the compile time does not exceed 5 seconds irrespective of the quality of the image. Experimental results indicate that Mask R-CNN works better than convolutional R-CNN as transfer learning works better than domain specific fine-tuning such as Cascade and Faster R-CNN. We achieve 89.5 per cent accuracy with Mask R-CNN through transfer combination.

Author Information

# Name Institute / Affiliation
1 Pradhip Kumar.R SRM Valliammai Engineering College
2 Sanjeev Kumar Patel SRM Valliammai Engineering College
3 Shankar SRM Valliammai Engineering College
4 Ms.C.Pabitha SRM Valliammai Engineering College

How to Cite

Use the following formats to cite this article in your research.

APA Style
Kumar.R, Pradhip, Patel, Sanjeev Kumar, Shankar, & Ms.C.Pabitha (2020). Car Exterior Damage Detection Using Mask R-CNN. International Journal of Advance Research and Innovative Ideas In Education, 6(2), 862-868.
MLA Style
Kumar.R, Pradhip, et al. "Car Exterior Damage Detection Using Mask R-CNN." International Journal of Advance Research and Innovative Ideas In Education, vol. 6, no. 2, 2020, pp. 862-868.
IEEE Style
Pradhip Kumar.R, Sanjeev Kumar Patel, Shankar, and Ms.C.Pabitha, "Car Exterior Damage Detection Using Mask R-CNN," International Journal of Advance Research and Innovative Ideas In Education, vol. 6, no. 2, pp. 862-868, 2020.
Vancouver Style
Kumar.R Pradhip, Patel Sanjeev Kumar, Shankar, Ms.C.Pabitha. Car Exterior Damage Detection Using Mask R-CNN. International Journal of Advance Research and Innovative Ideas In Education. 2020;6(2):862-868.
Harvard Style
Kumar.R, Pradhip, Patel, Sanjeev Kumar, Shankar, & Ms.C.Pabitha (2020) 'Car Exterior Damage Detection Using Mask R-CNN', International Journal of Advance Research and Innovative Ideas In Education, 6(2), pp. 862-868.
Chicago Style
Kumar.R, Pradhip, et al. "Car Exterior Damage Detection Using Mask R-CNN." International Journal of Advance Research and Innovative Ideas In Education 6, no. 2 (2020): 862-868.
Turabian Style
Kumar.R, Pradhip, et al. "Car Exterior Damage Detection Using Mask R-CNN." International Journal of Advance Research and Innovative Ideas In Education 6, no. 2 (2020): 862-868.

Export Citation

Related Research

PReFace : AI -Assisted Plausible Facial Restoration and Damage Reconstruction System
Syeda Arbeena Kausar et al. 2026 Computer Science and Engineering (Computer Vision, Deep Learning and Image Processing)
Download PDF
Customer Churn Prediction Using Machine Learning
Dr. Roshni Khlhe et al. 2026 Machine Learning, Artificial Intelligence, Data Analytics, and Customer Churn Prediction.
Download PDF
Automated web vulnerability scanner
Jitendra Sahu et al. 2026 Computer science
Download PDF
BLOOD BANK DEMAND PREDICTION SYSTEM: MACHINE LEARNINGBASED BLOOD DEMAND FORECASTING
Uday Dharmapal Wankhede et al. 2026 Computer Science & Engineering
Download PDF