Investigation of Deep Learning Models for Vehicle Damage Classification
This paper presents a study of Deep Learning models of convolution neural networks (CNN) applied to vehicle damage classification (VDC). Number of real-world domains may benefit from the proposed solution such as: car rental, auto dealerships, auto insurance businesses, etc. DL has significant advan...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| منشور في: |
2023
|
| الوصول للمادة أونلاين: | http://hdl.handle.net/11675/10914 http://www.scopus.com/inward/record.url?scp=85160019316&partnerID=8YFLogxK |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1870679722300538880 |
|---|---|
| author | Rababaah, Aaron |
| author_facet | Rababaah, Aaron |
| author_role | author |
| dc.creator.none.fl_str_mv | Rababaah, Aaron |
| dc.date.none.fl_str_mv | 2023-01-01 2024-02-05T08:32:40Z 2024-02-05T08:32:40Z |
| dc.identifier.none.fl_str_mv | 10.1109/SPIN57001.2023.10116703 9781665490993 http://hdl.handle.net/11675/10914 http://www.scopus.com/inward/record.url?scp=85160019316&partnerID=8YFLogxK |
| dc.relation.none.fl_str_mv | Computer Science and Info Systems |
| dc.title.none.fl_str_mv | Investigation of Deep Learning Models for Vehicle Damage Classification |
| dc.type.none.fl_str_mv | Journal Article info:eu-repo/semantics/publishedVersion |
| description | This paper presents a study of Deep Learning models of convolution neural networks (CNN) applied to vehicle damage classification (VDC). Number of real-world domains may benefit from the proposed solution such as: car rental, auto dealerships, auto insurance businesses, etc. DL has significant advantages over conventional machine learning (ML) models. The primary advantage of DL models is their ability to learn and extract features automatically as opposed to hand-crafting them as in ML models. The study used MatLab as the development and testing environment. A CNN based architecture was constructed which comprised typical DL layers of: raw image input, convolution, activation, pooling, flattening and fully-connected layers. The study used real world images collected from online sources to conduct the experimental work to validate the proposed model. The results showed that the overall average accuracy of all tested models was 91.8% and the best model produced an impressive accuracy of 99.4%. Furthermore, confusion matrix metrics were used to further validate the best performing model and all metrics such as accuracy, precision, sensitivity, specificity were reliable. |
| id | AUKR_4e20779dd6d51fe5d45f43d493f8be7a |
| identifier_str_mv | 10.1109/SPIN57001.2023.10116703 9781665490993 |
| network_acronym_str | AUKR |
| network_name_str | AU Kuwait Rep |
| oai_identifier_str | oai:dspace.auk.edu.kw:11675/10914 |
| publishDate | 2023 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| spelling | Investigation of Deep Learning Models for Vehicle Damage ClassificationRababaah, Aaron This paper presents a study of Deep Learning models of convolution neural networks (CNN) applied to vehicle damage classification (VDC). Number of real-world domains may benefit from the proposed solution such as: car rental, auto dealerships, auto insurance businesses, etc. DL has significant advantages over conventional machine learning (ML) models. The primary advantage of DL models is their ability to learn and extract features automatically as opposed to hand-crafting them as in ML models. The study used MatLab as the development and testing environment. A CNN based architecture was constructed which comprised typical DL layers of: raw image input, convolution, activation, pooling, flattening and fully-connected layers. The study used real world images collected from online sources to conduct the experimental work to validate the proposed model. The results showed that the overall average accuracy of all tested models was 91.8% and the best model produced an impressive accuracy of 99.4%. Furthermore, confusion matrix metrics were used to further validate the best performing model and all metrics such as accuracy, precision, sensitivity, specificity were reliable.2024-02-05T08:32:40Z2024-02-05T08:32:40Z2023-01-01Journal Articleinfo:eu-repo/semantics/publishedVersion10.1109/SPIN57001.2023.101167039781665490993http://hdl.handle.net/11675/10914http://www.scopus.com/inward/record.url?scp=85160019316&partnerID=8YFLogxKComputer Science and Info Systemsoai:dspace.auk.edu.kw:11675/109142025-06-18T09:02:28Z |
| spellingShingle | Investigation of Deep Learning Models for Vehicle Damage Classification Rababaah, Aaron |
| status_str | publishedVersion |
| title | Investigation of Deep Learning Models for Vehicle Damage Classification |
| title_full | Investigation of Deep Learning Models for Vehicle Damage Classification |
| title_fullStr | Investigation of Deep Learning Models for Vehicle Damage Classification |
| title_full_unstemmed | Investigation of Deep Learning Models for Vehicle Damage Classification |
| title_short | Investigation of Deep Learning Models for Vehicle Damage Classification |
| title_sort | Investigation of Deep Learning Models for Vehicle Damage Classification |
| url | http://hdl.handle.net/11675/10914 http://www.scopus.com/inward/record.url?scp=85160019316&partnerID=8YFLogxK |