Pub Date : 2022-05-09DOI: 10.48550/arXiv.2205.04222
Silvan Mertes, A. Margraf, Steffen Geinitz, Elisabeth Andr'e
Visual inspection software has become a key factor in the manufacturing industry for quality control and process monitoring. Semantic segmentation models have gained importance since they allow for more precise examination. These models, however, require large image datasets in order to achieve a fair accuracy level. In some cases, training data is sparse or lacks of sufficient annotation, a fact that especially applies to highly specialized production environments. Data augmentation represents a common strategy to extend the dataset. Still, it only varies the image within a narrow range. In this article, a novel strategy is proposed to augment small image datasets. The approach is applied to surface monitoring of carbon fibers, a specific industry use case. We apply two different methods to create binary labels: a problem-tailored trigonometric function and a WGAN model. Afterwards, the labels are translated into color images using pix2pix and used to train a U-Net. The results suggest that the trigonometric function is superior to the WGAN model. However, a precise examination of the resulting images indicate that WGAN and image-to-image translation achieve good segmentation results and only deviate to a small degree from traditional data augmentation. In summary, this study examines an industry application of data synthesization using generative adversarial networks and explores its potential for monitoring systems of production environments. keywords{Image-to-Image Translation, Carbon Fiber, Data Augmentation, Computer Vision, Industrial Monitoring, Adversarial Learning.
{"title":"Alternative Data Augmentation for Industrial Monitoring using Adversarial Learning","authors":"Silvan Mertes, A. Margraf, Steffen Geinitz, Elisabeth Andr'e","doi":"10.48550/arXiv.2205.04222","DOIUrl":"https://doi.org/10.48550/arXiv.2205.04222","url":null,"abstract":"Visual inspection software has become a key factor in the manufacturing industry for quality control and process monitoring. Semantic segmentation models have gained importance since they allow for more precise examination. These models, however, require large image datasets in order to achieve a fair accuracy level. In some cases, training data is sparse or lacks of sufficient annotation, a fact that especially applies to highly specialized production environments. Data augmentation represents a common strategy to extend the dataset. Still, it only varies the image within a narrow range. In this article, a novel strategy is proposed to augment small image datasets. The approach is applied to surface monitoring of carbon fibers, a specific industry use case. We apply two different methods to create binary labels: a problem-tailored trigonometric function and a WGAN model. Afterwards, the labels are translated into color images using pix2pix and used to train a U-Net. The results suggest that the trigonometric function is superior to the WGAN model. However, a precise examination of the resulting images indicate that WGAN and image-to-image translation achieve good segmentation results and only deviate to a small degree from traditional data augmentation. In summary, this study examines an industry application of data synthesization using generative adversarial networks and explores its potential for monitoring systems of production environments. keywords{Image-to-Image Translation, Carbon Fiber, Data Augmentation, Computer Vision, Industrial Monitoring, Adversarial Learning.","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"21 1","pages":"1-23"},"PeriodicalIF":0.0,"publicationDate":"2022-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78843002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-26DOI: 10.48550/arXiv.2204.12237
Silvan Mertes, Dominik Schiller, F. Lingenfelser, Thomas Kiderle, Valentin Kroner, Lama Diab, Elisabeth Andr'e
Generative adversarial networks offer the possibility to generate deceptively real images that are almost indistinguishable from actual photographs. Such systems however rely on the presence of large datasets to realistically replicate the corresponding domain. This is especially a problem if not only random new images are to be generated, but specific (continuous) features are to be co-modeled. A particularly important use case in emph{Human-Computer Interaction} (HCI) research is the generation of emotional images of human faces, which can be used for various use cases, such as the automatic generation of avatars. The problem hereby lies in the availability of training data. Most suitable datasets for this task rely on categorical emotion models and therefore feature only discrete annotation labels. This greatly hinders the learning and modeling of smooth transitions between displayed affective states. To overcome this challenge, we explore the potential of label interpolation to enhance networks trained on categorical datasets with the ability to generate images conditioned on continuous features.
{"title":"Intercategorical Label Interpolation for Emotional Face Generation with Conditional Generative Adversarial Networks","authors":"Silvan Mertes, Dominik Schiller, F. Lingenfelser, Thomas Kiderle, Valentin Kroner, Lama Diab, Elisabeth Andr'e","doi":"10.48550/arXiv.2204.12237","DOIUrl":"https://doi.org/10.48550/arXiv.2204.12237","url":null,"abstract":"Generative adversarial networks offer the possibility to generate deceptively real images that are almost indistinguishable from actual photographs. Such systems however rely on the presence of large datasets to realistically replicate the corresponding domain. This is especially a problem if not only random new images are to be generated, but specific (continuous) features are to be co-modeled. A particularly important use case in emph{Human-Computer Interaction} (HCI) research is the generation of emotional images of human faces, which can be used for various use cases, such as the automatic generation of avatars. The problem hereby lies in the availability of training data. Most suitable datasets for this task rely on categorical emotion models and therefore feature only discrete annotation labels. This greatly hinders the learning and modeling of smooth transitions between displayed affective states. To overcome this challenge, we explore the potential of label interpolation to enhance networks trained on categorical datasets with the ability to generate images conditioned on continuous features.","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"101 1","pages":"67-87"},"PeriodicalIF":0.0,"publicationDate":"2022-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89928229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1007/978-3-031-37317-6_3
Daniel Lehmann, M. Ebner
{"title":"Reliable Classification of Images by Calculating Their Credibility Using a Layer-Wise Activation Cluster Analysis of CNNs","authors":"Daniel Lehmann, M. Ebner","doi":"10.1007/978-3-031-37317-6_3","DOIUrl":"https://doi.org/10.1007/978-3-031-37317-6_3","url":null,"abstract":"","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"50 1","pages":"33-55"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84586972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.5220/0011135500003277
L. S. D. Souza, S. N. Alves-Souza, L. V. L. Filgueiras, L. Velloso, M. F. Carvalho, Luciano Garcia, Marcia Ito, J. Jarske, T. L. Santos, H. Fernandes, Gabriela Araújo, Wesley Barbosa
{"title":"Forecast of Dengue Cases based on the Deep Learning Approach: A Case Study for a Brazilian City","authors":"L. S. D. Souza, S. N. Alves-Souza, L. V. L. Filgueiras, L. Velloso, M. F. Carvalho, Luciano Garcia, Marcia Ito, J. Jarske, T. L. Santos, H. Fernandes, Gabriela Araújo, Wesley Barbosa","doi":"10.5220/0011135500003277","DOIUrl":"https://doi.org/10.5220/0011135500003277","url":null,"abstract":"","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"57 1","pages":"71-76"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87700410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.5220/0011316900003277
Murielle Lokonon, V. R. Houndji
: Unified Modeling Language (UML) is a standardized modeling language used to design software systems. However, software engineering learners often have difficulties understanding UML and often repeat the same mistakes. Several solutions automatically correct UML diagrams. These solutions are generally restricted to the modeling tool used or need teachers’ intervention for providing exercises, answers, and other rules to consider for diagrams corrections. This paper proposes a tool that allows the automatic correction of UML diagrams by taking an image as input. The aim is to help UML practicers get automatic feedback on their diagrams regardless of how they have represented them. We have conducted our experiments on the use case diagrams. We have first built a dataset of images of the most elements encountered in the use case diagrams. Then, based on this dataset, we have trained some machine learning models using the Detectron2 library developed by Facebook AI Research (FAIR). Finally, we have used the model with the best performances and a predefined list of errors to set up a tool that can syntactically correct any use case diagram with relatively good precision. Thanks to its genericity, the use of this tool is easier and more practical than the state-of-the-art UML diagrams correction systems.
{"title":"Automatic UML Defects Detection based on Image of Diagram","authors":"Murielle Lokonon, V. R. Houndji","doi":"10.5220/0011316900003277","DOIUrl":"https://doi.org/10.5220/0011316900003277","url":null,"abstract":": Unified Modeling Language (UML) is a standardized modeling language used to design software systems. However, software engineering learners often have difficulties understanding UML and often repeat the same mistakes. Several solutions automatically correct UML diagrams. These solutions are generally restricted to the modeling tool used or need teachers’ intervention for providing exercises, answers, and other rules to consider for diagrams corrections. This paper proposes a tool that allows the automatic correction of UML diagrams by taking an image as input. The aim is to help UML practicers get automatic feedback on their diagrams regardless of how they have represented them. We have conducted our experiments on the use case diagrams. We have first built a dataset of images of the most elements encountered in the use case diagrams. Then, based on this dataset, we have trained some machine learning models using the Detectron2 library developed by Facebook AI Research (FAIR). Finally, we have used the model with the best performances and a predefined list of errors to set up a tool that can syntactically correct any use case diagram with relatively good precision. Thanks to its genericity, the use of this tool is easier and more practical than the state-of-the-art UML diagrams correction systems.","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"4 1","pages":"193-198"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78420768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.5220/0011188100003277
Jurij Kuzmic, G. Rudolph
{"title":"Real-time Distance Measurement in a 2D Image on Hardware with Limited Resources for Low-power IoT Devices (Radar Control System)","authors":"Jurij Kuzmic, G. Rudolph","doi":"10.5220/0011188100003277","DOIUrl":"https://doi.org/10.5220/0011188100003277","url":null,"abstract":"","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"4 1","pages":"94-101"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72749494","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1007/978-3-031-37317-6_2
João Marques, Francisco Faria, Rita Machado, Heitor Cardoso, Alexandre Bernardino, Plinio Moreno
{"title":"Active Collection of Well-Being and Health Data in Mobile Devices","authors":"João Marques, Francisco Faria, Rita Machado, Heitor Cardoso, Alexandre Bernardino, Plinio Moreno","doi":"10.1007/978-3-031-37317-6_2","DOIUrl":"https://doi.org/10.1007/978-3-031-37317-6_2","url":null,"abstract":"","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"17 1","pages":"17-32"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89799122","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.5220/0011266100003277
Gabriele Galatolo, Matteo Papi, Andrea Spinelli, Guglielmo Giomi, A. Zedda, M. Calderisi
: Some road sections are a veritable forest of road signs: just think how many indications you can come across on an urban or extra-urban route, near a construction site or a road diversion. The automatic recognition of vertical traffic signs is an extremely useful task in the automotive industry for many practical applications, such as supporting the driver while driving with an in-car advisory system or the creation of a register of signals for a particular road section to speed up maintenance and replacement of installations. Recent developments in deep learning have brought huge progress in the image processing area, which triggered successful applications like traffic sign recognition (TSR). The TSR is a specific image processing task in which real traffic scenes (images or frames from videos taken from vehicle cameras in uncontrolled lighting and occlusion conditions) are processed in order to detect and recognize traffic signs within it. Traffic Sign Recognition is a very recent technology facilitated by the Vienna Convention on Road Signs and Signals of 1968: during that international meeting, it was decided to standardize traffic signs so that they could be recognised more easily abroad. Finally, this work summarizes our proposal of a practical pipeline for the development of an automatic traffic sign recognition software.
{"title":"Creating an Automatic Road Sign Inventory System using a Fully Deep Learning-based Approach","authors":"Gabriele Galatolo, Matteo Papi, Andrea Spinelli, Guglielmo Giomi, A. Zedda, M. Calderisi","doi":"10.5220/0011266100003277","DOIUrl":"https://doi.org/10.5220/0011266100003277","url":null,"abstract":": Some road sections are a veritable forest of road signs: just think how many indications you can come across on an urban or extra-urban route, near a construction site or a road diversion. The automatic recognition of vertical traffic signs is an extremely useful task in the automotive industry for many practical applications, such as supporting the driver while driving with an in-car advisory system or the creation of a register of signals for a particular road section to speed up maintenance and replacement of installations. Recent developments in deep learning have brought huge progress in the image processing area, which triggered successful applications like traffic sign recognition (TSR). The TSR is a specific image processing task in which real traffic scenes (images or frames from videos taken from vehicle cameras in uncontrolled lighting and occlusion conditions) are processed in order to detect and recognize traffic signs within it. Traffic Sign Recognition is a very recent technology facilitated by the Vienna Convention on Road Signs and Signals of 1968: during that international meeting, it was decided to standardize traffic signs so that they could be recognised more easily abroad. Finally, this work summarizes our proposal of a practical pipeline for the development of an automatic traffic sign recognition software.","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"10 2 1","pages":"102-109"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78978222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.5220/0011142000003277
K. Loumponias, Andreas Kosmatopoulos, T. Tsikrika, S. Vrochidis, Y. Kompatsiaris
{"title":"A Faster Converging Negative Sampling for the Graph Embedding Process in Community Detection and Link Prediction Tasks","authors":"K. Loumponias, Andreas Kosmatopoulos, T. Tsikrika, S. Vrochidis, Y. Kompatsiaris","doi":"10.5220/0011142000003277","DOIUrl":"https://doi.org/10.5220/0011142000003277","url":null,"abstract":"","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"21 1","pages":"86-93"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84417632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.1007/978-3-031-37317-6_6
Dhvani Katkoria, Jaya Sreevalsan-Nair
{"title":"Evaluating and Improving RoSELS for Road Surface Extraction from 3D Automotive LiDAR Point Cloud Sequences","authors":"Dhvani Katkoria, Jaya Sreevalsan-Nair","doi":"10.1007/978-3-031-37317-6_6","DOIUrl":"https://doi.org/10.1007/978-3-031-37317-6_6","url":null,"abstract":"","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"58 1","pages":"98-120"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85776931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：