Automated Graffiti Detection: A Novel Approach to Maintaining Historical Architecture in Communities
Graffiti is common in many communities and even affects our historical and heritage structures. This leads to a decrease in the revenue associated with commercial activities or services (e.g., shops, restaurants, residences), and potentially reduces tourism in a region. Visual data, in the form of p...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/6/2983 |
| _version_ | 1797447154904596480 |
|---|---|
| author | Jongseong Choi Lazaros Toumanidis Chul Min Yeum Patrikakis Charalampos Ali Lenjani Xiaoyu Liu Panagiotis Kasnesis Ricardo Ortiz Ning-Jun Jiang Shirley J. Dyke |
| author_facet | Jongseong Choi Lazaros Toumanidis Chul Min Yeum Patrikakis Charalampos Ali Lenjani Xiaoyu Liu Panagiotis Kasnesis Ricardo Ortiz Ning-Jun Jiang Shirley J. Dyke |
| author_sort | Jongseong Choi |
| collection | DOAJ |
| description | Graffiti is common in many communities and even affects our historical and heritage structures. This leads to a decrease in the revenue associated with commercial activities or services (e.g., shops, restaurants, residences), and potentially reduces tourism in a region. Visual data, in the form of photographs, is becoming an efficient mechanism to record information. Photographs can be quickly captured, and are already frequently posted online by ordinary citizens (e.g., tourists, residents, visitors). Exploiting image data through automation and computer vision provides a new opportunity to simplify the current manual graffiti-monitoring processes, enabling automated detection, localization, and quantification of such markings. In this study, we developed a vision-based graffiti-detection technique using a convolutional neural network. Images collected from historical structures of interest within a community can be utilized to automatically inspect for graffiti markings. In the case in which citizens collect and contribute data, there is a high degree of duplication and repetition, and potentially a lack of GPS information. These hinder the direct use of the images for automating the process. To address these challenges, we built high-resolution, single-view façade images (orthophotos) before applying our robust graffiti detector. The robust graffiti detector was built using a database with 1022 images of damaged or contaminated structures gathered during a recent European Union project, entitled “Safeguarding Cultural Heritage through Technical and Organisational Resources Management” (STORM). A total of 818 images were used for training (10% of the training set was randomly chosen for the validation set), achieving 88% accuracy among the remaining 204 samples for testing. Using the trained detector, the technique developed was demonstrated using data collected from the Church of Agios Nikolaos (Leontariou), Kantza, Greece. |
| first_indexed | 2024-03-09T13:50:44Z |
| format | Article |
| id | doaj.art-1dc9b83aaab547338459dba0840505c5 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T13:50:44Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-1dc9b83aaab547338459dba0840505c52023-11-30T20:49:40ZengMDPI AGApplied Sciences2076-34172022-03-01126298310.3390/app12062983Automated Graffiti Detection: A Novel Approach to Maintaining Historical Architecture in CommunitiesJongseong Choi0Lazaros Toumanidis1Chul Min Yeum2Patrikakis Charalampos3Ali Lenjani4Xiaoyu Liu5Panagiotis Kasnesis6Ricardo Ortiz7Ning-Jun Jiang8Shirley J. Dyke9Department of Mechanical Engineering, SUNY Korea, State University of New York, Incheon 21985, KoreaDepartment of Electrical and Electronics Engineering, University of West Attica, 12241 Egaleo, GreeceDepartment of Civil and Environmental Engineering, University of Waterloo, Waterloo, ON N2L 2G1, CanadaDepartment of Electrical and Electronics Engineering, University of West Attica, 12241 Egaleo, GreeceSchool of Medicine, Stanford University, Stanford, CA 94305, USASchool of Mechanical Engineering, Purdue University, West Lafayette, IN 47906, USADepartment of Electrical and Electronics Engineering, University of West Attica, 12241 Egaleo, GreeceDepartment of Mechanical Engineering, SUNY Korea, State University of New York, Incheon 21985, KoreaInstitute of Geotechnical Engineering, Southeast University, Nanjing 211189, ChinaSchool of Mechanical Engineering, Purdue University, West Lafayette, IN 47906, USAGraffiti is common in many communities and even affects our historical and heritage structures. This leads to a decrease in the revenue associated with commercial activities or services (e.g., shops, restaurants, residences), and potentially reduces tourism in a region. Visual data, in the form of photographs, is becoming an efficient mechanism to record information. Photographs can be quickly captured, and are already frequently posted online by ordinary citizens (e.g., tourists, residents, visitors). Exploiting image data through automation and computer vision provides a new opportunity to simplify the current manual graffiti-monitoring processes, enabling automated detection, localization, and quantification of such markings. In this study, we developed a vision-based graffiti-detection technique using a convolutional neural network. Images collected from historical structures of interest within a community can be utilized to automatically inspect for graffiti markings. In the case in which citizens collect and contribute data, there is a high degree of duplication and repetition, and potentially a lack of GPS information. These hinder the direct use of the images for automating the process. To address these challenges, we built high-resolution, single-view façade images (orthophotos) before applying our robust graffiti detector. The robust graffiti detector was built using a database with 1022 images of damaged or contaminated structures gathered during a recent European Union project, entitled “Safeguarding Cultural Heritage through Technical and Organisational Resources Management” (STORM). A total of 818 images were used for training (10% of the training set was randomly chosen for the validation set), achieving 88% accuracy among the remaining 204 samples for testing. Using the trained detector, the technique developed was demonstrated using data collected from the Church of Agios Nikolaos (Leontariou), Kantza, Greece.https://www.mdpi.com/2076-3417/12/6/2983graffiticultural heritage assessmentconvolutional neural networkorthophoto generationobject detectioncitizen science |
| spellingShingle | Jongseong Choi Lazaros Toumanidis Chul Min Yeum Patrikakis Charalampos Ali Lenjani Xiaoyu Liu Panagiotis Kasnesis Ricardo Ortiz Ning-Jun Jiang Shirley J. Dyke Automated Graffiti Detection: A Novel Approach to Maintaining Historical Architecture in Communities Applied Sciences graffiti cultural heritage assessment convolutional neural network orthophoto generation object detection citizen science |
| title | Automated Graffiti Detection: A Novel Approach to Maintaining Historical Architecture in Communities |
| title_full | Automated Graffiti Detection: A Novel Approach to Maintaining Historical Architecture in Communities |
| title_fullStr | Automated Graffiti Detection: A Novel Approach to Maintaining Historical Architecture in Communities |
| title_full_unstemmed | Automated Graffiti Detection: A Novel Approach to Maintaining Historical Architecture in Communities |
| title_short | Automated Graffiti Detection: A Novel Approach to Maintaining Historical Architecture in Communities |
| title_sort | automated graffiti detection a novel approach to maintaining historical architecture in communities |
| topic | graffiti cultural heritage assessment convolutional neural network orthophoto generation object detection citizen science |
| url | https://www.mdpi.com/2076-3417/12/6/2983 |
| work_keys_str_mv | AT jongseongchoi automatedgraffitidetectionanovelapproachtomaintaininghistoricalarchitectureincommunities AT lazarostoumanidis automatedgraffitidetectionanovelapproachtomaintaininghistoricalarchitectureincommunities AT chulminyeum automatedgraffitidetectionanovelapproachtomaintaininghistoricalarchitectureincommunities AT patrikakischaralampos automatedgraffitidetectionanovelapproachtomaintaininghistoricalarchitectureincommunities AT alilenjani automatedgraffitidetectionanovelapproachtomaintaininghistoricalarchitectureincommunities AT xiaoyuliu automatedgraffitidetectionanovelapproachtomaintaininghistoricalarchitectureincommunities AT panagiotiskasnesis automatedgraffitidetectionanovelapproachtomaintaininghistoricalarchitectureincommunities AT ricardoortiz automatedgraffitidetectionanovelapproachtomaintaininghistoricalarchitectureincommunities AT ningjunjiang automatedgraffitidetectionanovelapproachtomaintaininghistoricalarchitectureincommunities AT shirleyjdyke automatedgraffitidetectionanovelapproachtomaintaininghistoricalarchitectureincommunities |