Car damage analysis for insurance market using convolutional neural networks

C. T. Artan; Tolga Kaya

doi:10.1007/978-3-030-23756-1_39

Car damage analysis for insurance market using convolutional neural networks

C. T. Artan^*, Tolga Kaya

^*Corresponding author for this work

Department of Management Engineering

Istanbul Technical University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Citations (Scopus)

Abstract

As the level of competition increases, image-based vehicle claim processing is gaining an important role in the insurance industry especially in handling small but more frequent insurance claims. In this study, we explore the applicability of Convolutional Neural Networks (CNNs) to determine the level of damage using damaged car images. We have used transfer learning to analyze the advantages of available object recognition models to detect and classify damage according to the damage area and the level of damage.

Original language	English
Title of host publication	Intelligent and Fuzzy Techniques in Big Data Analytics and Decision Making - Proceedings of the INFUS 2019 Conference
Editors	Cengiz Kahraman, Sezi Cevik Onar, Basar Oztaysi, Irem Ucal Sari, Selcuk Cebi, A.Cagri Tolga
Publisher	Springer Verlag
Pages	313-321
Number of pages	9
ISBN (Print)	9783030237554
DOIs	https://doi.org/10.1007/978-3-030-23756-1_39
Publication status	Published - 2020
Event	International Conference on Intelligent and Fuzzy Systems, INFUS 2019 - Istanbul, Turkey Duration: 23 Jul 2019 → 25 Jul 2019

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	1029
ISSN (Print)	2194-5357
ISSN (Electronic)	2194-5365

Conference

Conference	International Conference on Intelligent and Fuzzy Systems, INFUS 2019
Country/Territory	Turkey
City	Istanbul
Period	23/07/19 → 25/07/19

Bibliographical note

Publisher Copyright:
© 2020, Springer Nature Switzerland AG.

Keywords

AI for insurance
Car damage analysis
Convolutional neural networks (CNNs)
Deep learning
Transfer learning
Visual recognition

Access to Document

10.1007/978-3-030-23756-1_39

Cite this

Artan, C. T., & Kaya, T. (2020). Car damage analysis for insurance market using convolutional neural networks. In C. Kahraman, S. Cevik Onar, B. Oztaysi, I. U. Sari, S. Cebi, & A. C. Tolga (Eds.), Intelligent and Fuzzy Techniques in Big Data Analytics and Decision Making - Proceedings of the INFUS 2019 Conference (pp. 313-321). (Advances in Intelligent Systems and Computing; Vol. 1029). Springer Verlag. https://doi.org/10.1007/978-3-030-23756-1_39

Artan, C. T. ; Kaya, Tolga. / Car damage analysis for insurance market using convolutional neural networks. Intelligent and Fuzzy Techniques in Big Data Analytics and Decision Making - Proceedings of the INFUS 2019 Conference. editor / Cengiz Kahraman ; Sezi Cevik Onar ; Basar Oztaysi ; Irem Ucal Sari ; Selcuk Cebi ; A.Cagri Tolga. Springer Verlag, 2020. pp. 313-321 (Advances in Intelligent Systems and Computing).

@inproceedings{02593a76cc094f0f85bf9b003d7a2b9e,

title = "Car damage analysis for insurance market using convolutional neural networks",

abstract = "As the level of competition increases, image-based vehicle claim processing is gaining an important role in the insurance industry especially in handling small but more frequent insurance claims. In this study, we explore the applicability of Convolutional Neural Networks (CNNs) to determine the level of damage using damaged car images. We have used transfer learning to analyze the advantages of available object recognition models to detect and classify damage according to the damage area and the level of damage.",

keywords = "AI for insurance, Car damage analysis, Convolutional neural networks (CNNs), Deep learning, Transfer learning, Visual recognition",

author = "Artan, {C. T.} and Tolga Kaya",

note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Switzerland AG.; International Conference on Intelligent and Fuzzy Systems, INFUS 2019 ; Conference date: 23-07-2019 Through 25-07-2019",

year = "2020",

doi = "10.1007/978-3-030-23756-1_39",

language = "English",

isbn = "9783030237554",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer Verlag",

pages = "313--321",

editor = "Cengiz Kahraman and {Cevik Onar}, Sezi and Basar Oztaysi and Sari, {Irem Ucal} and Selcuk Cebi and A.Cagri Tolga",

booktitle = "Intelligent and Fuzzy Techniques in Big Data Analytics and Decision Making - Proceedings of the INFUS 2019 Conference",

address = "Germany",

}

Artan, CT & Kaya, T 2020, Car damage analysis for insurance market using convolutional neural networks. in C Kahraman, S Cevik Onar, B Oztaysi, IU Sari, S Cebi & AC Tolga (eds), Intelligent and Fuzzy Techniques in Big Data Analytics and Decision Making - Proceedings of the INFUS 2019 Conference. Advances in Intelligent Systems and Computing, vol. 1029, Springer Verlag, pp. 313-321, International Conference on Intelligent and Fuzzy Systems, INFUS 2019, Istanbul, Turkey, 23/07/19. https://doi.org/10.1007/978-3-030-23756-1_39

Car damage analysis for insurance market using convolutional neural networks. / Artan, C. T.; Kaya, Tolga.
Intelligent and Fuzzy Techniques in Big Data Analytics and Decision Making - Proceedings of the INFUS 2019 Conference. ed. / Cengiz Kahraman; Sezi Cevik Onar; Basar Oztaysi; Irem Ucal Sari; Selcuk Cebi; A.Cagri Tolga. Springer Verlag, 2020. p. 313-321 (Advances in Intelligent Systems and Computing; Vol. 1029).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Car damage analysis for insurance market using convolutional neural networks

AU - Artan, C. T.

AU - Kaya, Tolga

PY - 2020

Y1 - 2020

N2 - As the level of competition increases, image-based vehicle claim processing is gaining an important role in the insurance industry especially in handling small but more frequent insurance claims. In this study, we explore the applicability of Convolutional Neural Networks (CNNs) to determine the level of damage using damaged car images. We have used transfer learning to analyze the advantages of available object recognition models to detect and classify damage according to the damage area and the level of damage.

AB - As the level of competition increases, image-based vehicle claim processing is gaining an important role in the insurance industry especially in handling small but more frequent insurance claims. In this study, we explore the applicability of Convolutional Neural Networks (CNNs) to determine the level of damage using damaged car images. We have used transfer learning to analyze the advantages of available object recognition models to detect and classify damage according to the damage area and the level of damage.

KW - AI for insurance

KW - Car damage analysis

KW - Convolutional neural networks (CNNs)

KW - Deep learning

KW - Transfer learning

KW - Visual recognition

UR - http://www.scopus.com/inward/record.url?scp=85069463125&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-23756-1_39

DO - 10.1007/978-3-030-23756-1_39

M3 - Conference contribution

AN - SCOPUS:85069463125

SN - 9783030237554

T3 - Advances in Intelligent Systems and Computing

SP - 313

EP - 321

BT - Intelligent and Fuzzy Techniques in Big Data Analytics and Decision Making - Proceedings of the INFUS 2019 Conference

A2 - Kahraman, Cengiz

A2 - Cevik Onar, Sezi

A2 - Oztaysi, Basar

A2 - Sari, Irem Ucal

A2 - Cebi, Selcuk

A2 - Tolga, A.Cagri

PB - Springer Verlag

T2 - International Conference on Intelligent and Fuzzy Systems, INFUS 2019

Y2 - 23 July 2019 through 25 July 2019

ER -

Artan CT, Kaya T. Car damage analysis for insurance market using convolutional neural networks. In Kahraman C, Cevik Onar S, Oztaysi B, Sari IU, Cebi S, Tolga AC, editors, Intelligent and Fuzzy Techniques in Big Data Analytics and Decision Making - Proceedings of the INFUS 2019 Conference. Springer Verlag. 2020. p. 313-321. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-3-030-23756-1_39

Car damage analysis for insurance market using convolutional neural networks

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this