Image analysis and processing : ICIAP international workshops, Lecce, Italy, May 23-27, 2022, revised selected papers, Part I. / / edited by Pier Luigi Mazzeo [and three others]

• Record Nr.: UNINA9910586580403321
• Pubbl/distr/stampa: Cham, Switzerland : , : Springer, , [2022]; ©2022
• ISBN: 3-031-13321-8
• Descrizione fisica: 1 online resource (586 pages)
• Collana: Lecture Notes in Computer Science ; ; v.13373
• Disciplina: 621.367
• Soggetti: Image analysis; Image processing
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: Intro -- Preface -- Organization -- Contents - Part I -- Contents - Part II -- GoodBrother Workshop on Visual Intelligence for Active and Assisted Living -- Case Study of a Low-Cost IoT Device with a Thermal Vision to Monitor Human Stool Behavior in the Home -- 1 Introduction -- 2 Related Works -- 2.1 Gas and Temperature Monitoring Devices -- 2.2 IoT System in the Context of Monitoring Diseases in AAL -- 3 Approach to Monitor Human Stool Behavior at Home -- 3.1 Database. MongoDB -- 3.2 IoT Platform. Thinger.io -- 4 Case Study -- 5 Limitations of the Study and Future Work -- 6 Conclusions -- References -- Adults' Pain Recognition via Facial Expressions Using CNN-Based AU Detection -- 1 Introduction -- 2 Materials -- 3 Methodology -- 3.1 Face Detection -- 3.2 Analysis of Non-detected Faces -- 4 Results -- 4.1 Benchmark Results -- 4.2 Classification Results -- 5 Conclusions -- References -- In-bed Posture and Night Wandering Monitoring Using Force-Sensing Resistors -- 1 Introduction -- 2 Prototype Description -- 2.1 Force-Sensing Resistors -- 2.2 Sensor Positioning -- 2.3 MCU and Connectivity -- 2.4 Instrumentation for Preliminary Measurements -- 3 Results -- 4 Conclusions and Further Work -- References -- Classifying Sport-Related Human Activity from Thermal Vision Sensors Using CNN and LSTM -- 1 Introduction -- 2 Related Works -- 3 Materials and Methods ; -- 3.1 IoT Thermal Vision Sensor -- 3.2 Data Collection and Augmentation -- 3.3 DL Model for Learning from Image Sequences -- 4 Case Study -- 4.1 Results -- 5 Conclusions and Ongoing Works -- References -- MIRATAR: A Virtual Caregiver for Active and Healthy Ageing -- 1 Introduction -- 2 MIRATAR Concept and Vision -- 3 The MIRATAR Virtual Caregiver -- 4 Conclusions and Future Work -- References -- From Garment to Skin: The visuAAL Skin Segmentation Dataset -- 1 Introduction.; 2 Skin Detection and Segmentation Datasets -- 3 Approach -- 4 Case Example: The visuAAL Skin Segmentation Dataset -- 4.1 Fashion and Garment Datasets -- 4.2 Dataset Quality Assessment -- 4.3 The visuAAL Skin Segmentation Dataset -- 5 Baseline -- 6 Conclusion -- References -- A Mobile Food Recognition System for Dietary Assessment -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Dataset and Analysis -- 3.2 Learning Model -- 4 Experiments and Results -- 4.1 Experimental Setup -- 4.2 Results -- 5 Conclusion -- References -- Smart Diet Management Through Food Image and Cooking Recipe Analysis -- 1 Introduction -- 2 Objectives -- 3 Related Work -- 4 Methodology -- 4.1 Ingredient Image Classification Model -- 4.2 Recipe Processing Using NLP -- 4.3 Additional Validation -- 5 Results -- 6 Conclusion -- References -- An Approach for Improving the Older people's Perception of Video-Based Applications in AAL Systems - Initial Study -- 1 Introduction -- 2 Method and Devices for Falls Detection -- 3 Results -- 4 Discussion -- 5 Conclusion -- References -- Parts Can Worth Like the Whole - PART 2022 -- Spectral Analysis of Masked Signals in the Context of Image Inpainting -- 1 Introduction -- 2 Use of the Masked Fourier Transform -- 2.1 Average of Squared Differences with masks -- 2.2 Normalized Cross Correlation with Masks -- 3 Inpainting with the Masked Fourier Transform -- 4 Experimental Results -- 5 Conclusion -- References -- Bringing Attention to Image Anomaly Detection -- 1 Introduction -- 2 Related Work -- 3 Methods -- 3.1 Masked Regions Generator -- 3.2 Model -- 4 Experiments -- 4.1 Datasets -- 4.2 Training Setup -- 4.3 Anomaly Localization Process -- 4.4 Metrics -- 4.5 Results -- 5 Conclusions and Future Works -- References -- Workshop on Fine Art Pattern Extraction and Recognition - FAPER.; Recognizing the Emotions Evoked by Artworks Through Visual Features and Knowledge Graph-Embeddings -- 1 Introduction -- 2 Related Work -- 3 Materials -- 3.1 ArtEmis -- 3.2 ArtGraph -- 3.3 Combining ArtEmis and ArtGraph -- 4 Methods -- 5 Experiments -- 5.1 Setup -- 5.2 Results -- 6 Conclusion and Future Work -- References -- Classification of Pottery Fragments Described by Concentration of Chemical Elements -- 1 Introduction and Previous Work -- 2 Data Collection -- 3 Statistical Analysis -- 4 Learning Scheme -- 5 Experiments and Results -- 6 Conclusions and Future Work -- References -- Blind Deblurring of Hyperspectral Document Images -- 1 Introduction -- 2 Proposed Method -- 3 Experiments -- 4 Results and Discussion -- 5 Conclusion -- References -- MyBottega: An Environment for the Innovative Production and Distribution of Digital Art -- 1 Introduction -- 1.1 Structure of the Paper -- 2 Web 3.0 and Generative AI: Two Converging Evolutions -- 2.1 Non-fungible Tokens and the New Course in Art Distribution -- 2.2 Generative Artificial Intelligence to Boost Art Production -- 3 Technological Background -- 4 MyBottega: Design Principles -- 5 The MyBottega Architecture -- 6 Conclusion -- References -- A Case Study for the Design and Implementation of Immersive Experiences in Support of Sicilian Cultural Heritage -- 1 Introduction -- 2 Related Works -- 3 The Pipeline -- 4 The Sense of Detail -- 5 Digital Acquisition and Data ; Processing -- 6 Point Cloud Processing -- 7 Use Case Development -- 8 Conclusions -- References -- Automatic Indexing of Virtual Camera Features from Japanese Anime -- 1 Introduction -- 2 Related Work -- 3 Animated Movie Dataset -- 3.1 A Taxonomy for Virtual Camera Features -- 3.2 Dataset Annotation and Split -- 3.3 Data Augmentation -- 4 Methods -- 4.1 Model Architecture -- 4.2 Hyperparameters and Cross-validation -- 5 Results.; 5.1 Error Analysis -- 6 Conclusion -- References -- Imageability-Based Multi-modal Analysis of Urban Environments for Architects and Artists -- 1 Introduction -- 1.1 The City Image and Imageability -- 1.2 Case Study -- 2 Related Work -- 2.1 Related Visual Analysis Techniques -- 2.2 Related Textual Analysis Techniques -- 3 The Proposed Multi-modal System - Method -- 3.1 Visual Analysis Algorithms -- 4 Experiments and Results -- 4.1 Workshop -- 4.2 Results -- 5 Conclusions -- References -- Challenges in Image Matching for Cultural Heritage: An Overview and Perspective -- 1 Overview -- 1.1 Introduction -- 1.2 Traditional Image Matching -- 1.3 Learning-Based Image Matching -- 2 Analysis and Evaluation -- 2.1 Rationale -- 2.2 Results and Discussion -- 3 Conclusions and Perspective -- References -- Workshop on Intelligent Systems in Human and Artificial Perception - ISHAPE 2022 -- Virtual and Augmented Reality for Quality Control of Aircraft Interiors -- 1 Introduction -- 2 Related Works -- 3 A Brief Introduction to Geometrical and Surface Defects -- 4 Reporting Sub-system -- 5 Results -- 6 Conclusions and Future Work -- References -- Automatic Scoring of Synchronization from Fingers Motion Capture and Music Beats -- 1 Introduction -- 2 Related Works -- 2.1 Musical Rhythmic Features Extraction -- 2.2 Human Movement and MoCap -- 2.3 Audiomotor Synchronization -- 3 Methodology -- 3.1 Motion Parameters -- 3.2 Music Parameters -- 3.3 Similarity and Score of Synchronization -- 4 Experiments -- 4.1 Set-up -- 4.2 Results -- 5 Conclusion -- References -- Performance of Recent Tiny/Small YOLO Versions in the Context of Top-View Fisheye Images -- 1 Introduction and Motivations -- 2 Detection Method -- 2.1 YOLO: An Architecture for Human Detection -- 2.2 Dataset -- 3 Experiments and Evaluations -- 3.1 Evaluation Metrics -- 3.2 Training of the Models.; 3.3 Performance of the Models on Images in a Familiar Context -- 3.4 Performance of the Models on Images in an Unfamiliar Context -- 4 Conclusion -- References -- Cloud-Based Visually Aided Mobile Manipulator Kinematic Parameters Calibration -- 1 Introduction -- 1.1 Contribution -- 2 Problem Formulation -- 3 Background -- 3.1 Unscented Kalman Filter -- 3.2 Probabilistic Pose Composition -- 4 System Architecture and Model Design -- 4.1 System Architecture -- 4.2 Model Design -- 4.3 Methodology -- 5 Experiment -- 5.1 Mobile Manipulator Experiment -- 6 Conclusion and Future Works -- References -- Deep Learning Approaches for Image-Based Detection and Classification of Structural Defects in Bridges -- 1 Introduction -- 2 Related Works -- 3 Methodology -- 3.1 Building the Dataset -- 3.2 Damage Classification -- 3.3 Discussion -- 4 Conclusions and Future Works -- References -- MONstEr: A Deep Learning-Based System for the Automatic Generation of Gaming Assets -- 1 Introduction -- 2 Related Works -- 3 Materials And Methods -- 3.1 GameAssetDataset -- 3.2 Deep Learning Pipeline -- 3.3 3D Asset Generation -- 4 Results and Discussions -- 5 Conclusions and Future Works -- References -- Surface Oxide Detection and Characterization Using Sparse Unmixing on Hyperspectral Images -- 1 Introduction -- 2 Optical Model -- 2.1 Optical Modelization for Oxides -- 3 Sparse Unmixing Approach -- 3.1 Algorithm -- 4 Results and Discussion -- 4.1 Single Oxide Characterization -- 4.2 Multiple Oxides Characterization -- 5 ; Conclusion -- References -- FakeNED: A Deep Learning Based-System for Fake News Detection from Social Media -- 1 Introduction -- 2 State of Art -- 3 Materials and Methods -- 3.1 FakeNED Multimodal Deep Learning Phase -- 3.2 Fakeddit Dataset -- 4 Results and Discussions -- 4.1 User Service Interaction -- 5 Conclusions and Future Works -- References.; Artificial Intelligence and Radiomics in Computer-Aided Diagnosis - AIRCAD.