[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125562-en":3,"doc-seo-125562-105":30,"detail-sidebar-cat-0-en-105":95},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125562,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1784791008015729253",8,"Research & Report","Towards an automated machine learning and image processing supported procedure for crack monitoring","Automated, remotely controlled procedures for crack detection and analysis reduce the time-consuming and subjective nature of operator-based visual inspections. Machine learning offers strong potential for crack measurement, but effective training depends on large datasets. This work evaluates an easy-to-implement workflow combining machine learning and image processing for real-time crack monitoring from temporal sequences of digital images. A modular pipeline automates acquisition, optimization, and detection with operator input limited to classifier training, achieving ~99% detection in controlled settings and 12–96% on real sites, limited mainly by false positives under varying illumination.","5th Joint International Symposium on Deformation Monitoring (JISDM), 20-22 June 2022, Valencia, Spain  \nDOI: [http://doi.org/10.4995/JISDM2022.2022.13828](http://doi.org/10.4995/JISDM2022.2022.13828)  \nTowards an automated machine learning and image processing supported  \nprocedure for crack monitoring  \nLuigi Parente, Cristina Castagnetti, Eugenia Falvo, Francesca Grassi, Francesco Mancini,  \nPaolo Rossi, Alessandro Capra  \nDepartment of Engineering “Enzo Ferrari”, University of Modena and Reggio Emilia, Via Pietro Vivarelli 10, 41125 Modena, Italy,([luigi.parente@unimore.it](luigi.parente@unimore.it); [cristina.castagnetti@unimore.it](cristina.castagnetti@unimore.it); [eugenia.falvo@unimore.it](eugenia.falvo@unimore.it);  \n[francesca.grassi94@unimore.it](francesca.grassi94@unimore.it); [francesco.mancini@unimore.it](francesco.mancini@unimore.it); [paolo.rossi@unimore.it](paolo.rossi@unimore.it); [alessandro.capra@unimore.it](alessandro.capra@unimore.it))  \nKey words: detection; crack; image processing; machine learning; automation; monitoring; open-source  \nABSTRACT  \nDevelopment of automated and remotely controlled procedures for accurate crack detection and analysis isan advantageous solution when compared to time-consuming and subjective crack examination conducted by operators. Recent studies have demonstrated that Machine Learning (ML) algorithms have sufficient potential for crack measurements. However, training of large amount of data is essential. When working on single sites with permanently installed fixed cameras adoption of ML solutions may be redundant. The purpose of this work is to assess the performance of a procedure for crack detection based on an easy to implement workflow supported by the use of ML and image processing algorithms. The datasets used in this work are composed of temporal sequence of single digital images. The workflow proposed includes three main modules covering acquisition, optimization and crack detection. Each module is automated and basic manual input by an operator is only required to train the classifier. The processing modules are implemented in modular open-source programs (e.g., ImageJ and Ilastik) . Results obtained in controlled conditions led to a satisfactory level of detection (about 99% of the crack pattern detected) . Experiments conducted on real-sites highlighted variable detection capabilities of the proposed approach (from 12 to 96%) . The main limitation of the approach is the production of false-positive detection due to significant variation in illumination conditions. Further work is being conducted to define scalability of the approach and to verify deformation detection capabilities.  \nI. INTRODUCTION  \nAging of the built environment worldwide demands for the adoption of cost-effective structural health monitoring approaches to ensure long-term integrity and adequate levels of safety. Crack patterns initiation and propagation are indicators of the structural integrity and health of a built element. Traditional crack visual inspections are conducted on the site by operators using conventional tools (such as measuring magnifiers, strain gauges, crack rulers, etc. ) . This task can produce subjective judgment on the state of the crack and introduces gross errors in the measurement. Recent technological advances in software and sensors offer the unprecedented opportunity to acquire considerable amount of high-quality optical data and process them in real-time with less subjective methods (Nex et al., 2019) . For example, adoption of image processing (IP) techniques has been employed in the past for a range of monitoring applications (e.g., Deshmukh and Mane, 2020; Garrido et al., 2019; Guidiet al., 2014) . Many researchers have proposed valid IPbased solutions for accurate segmentation of the crack from digital images (Mohan and Poobal, 2018) . However, the main limitation of detecting a set of cracks though IP algorithms lies in the little scalability of the approach","cbCaiaYrP7nNPO33","https://ap.wps.com/l/cbCaiaYrP7nNPO33","pdf",1465173,1,6,"English","en",105,"# Abstract\n## Introduction\n## Background and Motivation\n## Proposed Workflow and Modules\n## Results and Limitations","[{\"question\":\"Why are automated crack monitoring procedures preferred over traditional visual inspections?\",\"answer\":\"Traditional inspections are time-consuming and can be subjective, leading to gross measurement errors. Automated approaches aim to improve accuracy and reduce operator-dependent judgment.\"},{\"question\":\"What does the proposed workflow include for crack monitoring?\",\"answer\":\"The workflow consists of three automated modules covering acquisition, optimization, and crack detection. Manual input is mainly required to train the classifier.\"},{\"question\":\"What performance was reported in controlled conditions and on real sites?\",\"answer\":\"In controlled conditions, detection reached about 99% of the crack pattern. On real sites, detection performance varied from 12% to 96%.\"},{\"question\":\"What is the main limitation of the approach described?\",\"answer\":\"False-positive detections can occur due to significant variations in illumination conditions, which affect image processing and detection reliability.\"}]","Towards an automated machine learning and image processing supported procedure for crack monitoring | PDF",1785899871,15,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":90,"head_meta":92,"extra_data":94,"updated_unix":28},"towards-an-automated-machine-learning-and-image-processing-supported-procedure-for-crack-monitoring","",{"@graph":36,"@context":89},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/towards-an-automated-machine-learning-and-image-processing-supported-procedure-for-crack-monitoring/125562/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"Why are automated crack monitoring procedures preferred over traditional visual inspections?","Question",{"text":75,"@type":76},"Traditional inspections are time-consuming and can be subjective, leading to gross measurement errors. Automated approaches aim to improve accuracy and reduce operator-dependent judgment.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does the proposed workflow include for crack monitoring?",{"text":80,"@type":76},"The workflow consists of three automated modules covering acquisition, optimization, and crack detection. Manual input is mainly required to train the classifier.",{"name":82,"@type":73,"acceptedAnswer":83},"What performance was reported in controlled conditions and on real sites?",{"text":84,"@type":76},"In controlled conditions, detection reached about 99% of the crack pattern. On real sites, detection performance varied from 12% to 96%.",{"name":86,"@type":73,"acceptedAnswer":87},"What is the main limitation of the approach described?",{"text":88,"@type":76},"False-positive detections can occur due to significant variations in illumination conditions, which affect image processing and detection reliability.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,118,123,126,131,134,138],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},"Technology",50,"technology",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":124,"slug":125},30,"research-report",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":129,"slug":130},9,"Religion & Spirituality",20,"religion-spirituality",{"id":129,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":129,"slug":133},"World Cup","world-cup",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":135,"slug":137},10,"Lifestyle","lifestyle",{"id":139,"doc_module":4,"doc_module_name":46,"category_name":140,"show_sort_weight":110,"slug":141},19,"General","general"]