Image Processing & Applications

Structural S355 steel is widely applied in various sectors. Fatigue properties are of fundamental importance and extremely time consuming to be assessed. The aim of this research activity is to apply the Static Thermographic Method during tensile tests and correlate the temperature trend to the fatigue properties of the same steel. The Digital Image Correlation (DIC) and Infrared Thermography (IR) techniques have been used during all static tests. The Digital Image Correlation technique allowed the detection of displacements and strain, and so the evaluation of the mechanical properties of the material. Traditional fatigue tests were also performed in order to evaluate the stress-number of cycles to failure curve of the same steel. The value of the fatigue limit, obtained by the traditional procedure, was compared with the values predicted by means of the Static Thermographic Method (STM) obtained from tensile tests. The predicted values are in good agreement with the experimental values of fatigue life.

Keywords: Digital image correlation , Fatigue , Infrared thermography , Marine structures , Tensile tests

Background Preclinical training in perforator flap harvesting is typically conducted on living animal models; however, repeated training is not possible with these models because of ethical and/or economical constraints. We describe an anterolateral thigh flap (ALT flap) training model using chicken thigh that seems to be an appropriate training model prior, for example, to raise a perforator flap in a living rat or swine model. Methods A total of 10 chicken legs were used in this study. Six chicken legs were anatomically dissected to confirm the presence of the perforator and to identify the main vascular tree. In four chicken legs, a skin flap was planned based on the perforator and intramuscular dissection was performed under magnification. Results The perforator was identified in all dissections and was consistently found 3 cm above the line extending from the patella to the head of the femur in its third proximal. Proximally, the mean diameter of the artery and vein was 0.56 (σ = 0.04) and 0.84 (σ = 0.06) mm, respectively. The mean dissection time to raise the flap was 88 (σ = 7) min. Conclusion This is the first description of a nonliving biological simulation model for training in perforator flap dissection that mimics an ALT flap. As an ex vivo chicken model, it is a cost effective and readily accessible model suitable for repeated practice.

Keywords: ALT , chicken , perforator flap , training

In the fashion field, the use of electroplated small metal parts such as studs, clips and buckles is widespread. The plate is often made of precious metal, such as gold or platinum. Due to the high cost of these materials, it is strategically relevant and of primary importance for manufacturers to avoid any waste by depositing only the strictly necessary amount of material. To this aim, companies need to be aware of the overall number of items to be electroplated so that it is possible to properly set the parameters driving the galvanic process. Accordingly, the present paper describes a simple, yet effective machine vision-based method able to automatically count small metal parts arranged on a galvanic frame. The devised method, which relies on the definition of a rear projection-based acquisition system and on the development of image processing-based routines, is able to properly count the number of items on the galvanic frame. The system is implemented on a counting machine, which is meant to be adopted in the galvanic industrial practice to properly define a suitable set or working parameters (such as the current, voltage, and deposition time) for the electroplating machine and, thereby, assure the desired plate thickness from one side and avoid material waste on the other.

Keywords: Electro-deposition industry , Image analysis , Item counting device , Machine vision

This paper presents a software based on an innovative Convolutional Neural Network model to recognize the six Ekman's universal emotions from the photos of human faces captured in the wild. The CNN was trained using three different datasets already labeled and merged after making them homogeneous. A comparison among different types of CNN architectures using the Keras framework for Python language is proposed and the evaluation results are presented.

Keywords: convolutional neural network , deep learning , emotion recognition

This paper introduces a new system capable of adaptively managing multimedia contents (e.g. music, video clips, etc.) and lighting scenarios based on the detected user's emotional state. The system captures the emotion from the user's face expression mapping it into a 2D valence-arousal space where the multimedia content is mapped and matches them with lighting color. Results of preliminary tests suggest that the proposed system is able to detect the user's emotional state and manage proper music and light colors in a symbiotic way.

The study of human factors is fundamental for the human-centered design of Smart Workplaces. IIoT (Industrial Internet of Things) technologies, mainly wearable devices, are becoming necessary to acquire data, whose analysis will be used to make decision in a smart way. For industrial applications, motion-tracking systems are strongly developing, being not invasive and able to acquire high amounts of data related to human motion in order to evaluate the ergonomic indexes in an objective way, as well as suggested by standards. For these reasons, a modular inertial motion capture system has been developed at the Department of Engineering of the University of Campania Luigi Vanvitelli. By using low cost Inertial Measurement Units – IMU and sensor fusion algorithms based on Extended Kalman filtering, the system is able to estimate the orientation of each body segment, the posture angles trends and the gait recognition during a working activity in industrial environment. From acquired data it is possible to develop further algorithms to online asses ergonomic indexes according to methods suggested by international standards (i.e. EAWS, OCRA, OWAS). In this paper, the overall ergonomic assessment tool is presented, with an extensive result campaign in automotive assembly lines of Fiat Chrysler Automobiles to prove the effectiveness of the system in an industrial scenario.

Keywords: IMU , Industrial environment , Industrial ergonomics , Motion capture , Wearable device

Nowadays, facial mimicry studies have acquired a great importance in the clinical domain and 3D motion capture systems are becoming valid tools for analysing facial muscles movements, thanks to the remarkable developments achieved in the 1990s. However, the face analysis domain suffers from a lack of valid motion capture protocol, due to the complexity of the human face. Indeed, a framework for defining the optimal marker set layout does not exist yet and, up to date, researchers still use their traditional facial point sets with manually allocated markers. Therefore, the study proposes an automatic approach to compute a minimum optimized marker layout to be exploited in facial motion capture, able to simplify the marker allocation without decreasing the significance level. Specifically, the algorithm identifies the optimal facial marker layouts selecting the subsets of linear distances among markers that allow to automatically recognizing with the highest performances, through a k-nearest neighbours classification technique, the acted facial movements. The marker layouts are extracted from them. Various validation and testing phases have demonstrated the accuracy, robustness and usefulness of the custom approach.

Keywords: 3D face , Face analysis , Feature extraction , Marker optimization , Motion capture

This work proposes a method for recognizing the main 13 Facial Action Units and the 6 basic emotions. The methodologies rely on Differential Geometry to extract relevant discriminant features from the query faces, and on some linear quantities used as measures: Euclidean, geodesic, and angles between 17 automatically extracted soft-tissue landmarks. A thresholding system which evaluates local properties of connected regions, selected through tailored geometrical descriptors, supports the identification of the AUs. Then, a technique based on crisp logic allows the identification of the global expression. The three-dimensional context has been preferred due to its invariance to different lightening/make-up/camouflage conditions.

Keywords: Emotional design , Face expression recognition , Intelligent drive

This paper proposes a methodology to assess the discriminative capabilities of geometrical descriptors referring to the public Bosphorus 3D facial database as testing dataset. The investigated descriptors include histogram versions of Shape Index and Curvedness, Euclidean and geodesic distances between facial soft-tissue landmarks. The discriminability of these features is evaluated through the analysis of single block of features and their meanings with different techniques. Multilayer perceptron neural network methodology is adopted to evaluate the relevance of the features, examined in different test combinations. Principle component analysis (PCA) is applied for dimensionality reduction.

Keywords: 3D face recognition , Dimensionality reduction , Geometrical descriptors , Neural network , Principal component analysis

This paper proposes a methodology to assess the discriminative capabilities of geometrical descriptors referring to the public Bosphorus 3D facial database as testing dataset. The investigated descriptors include histogram versions of Shape Index and Curvedness, Euclidean and geodesic distances between facial soft-tissue landmarks. The discriminability of these features is evaluated through the analysis of single block of features and their meanings with different techniques. Multilayer perceptron neural network methodology is adopted to evaluate the relevance of the features, examined in different test combinations. Principle Component Analysis (PCA) is applied for dimensionality reduction.

Keywords: 3D face recognition , Dimensionality reduction , Geometrical descriptors , Neural network , Principal component analysis

This paper describes the conceptual model and the implementation of an emotion aware system able to manage multimedia contents (i.e., music tracks) and lightning scenarios, based on the user's emotion, detected from facial expressions. The system captures the emotions from the user's face expressions, mapping them into a 2D valence-arousal space where the multimedia content is mapped and matches them with lighting color. A preliminary experimentation involved a total of 26 subjects has been carried out with the purpose of assess the system emotion recognition effectiveness and its ability to manage the environment appropriately. Results evidenced several limits of emotion recognition through face expressions detection and opens to several research challenges.

Keywords: Affective computing , Ambient intelligence , Emotion detection , Emotion recognition , Emotion-aware system , Face expression recognition , Smart environment

Aboveground biomass (AGB) is a parameter commonly used for assessing and monitoring primary productivity of grassland communities. Destructive AGB measurements, although accurate, are time-consuming and do not allow for repeated measurements as required by monitoring protocols. Structure-from-motion (SfM) photogrammetry has been proved to be a reliable tool for rapid and not destructive AGB estimations in grass systems. Three-dimensional (3D) models of fourteen 1 × 1 m2 pasture plots were reconstructed and AGB volume measured under several measurement settings. Volume-based AGB measures were regressed to AGB values resulting from destructive methods to identify the measurement settings that show the best fit. Furthermore, 3D models of four mountain pasture plots were reconstructed in May, July, and August. Models relative to the same plot were aligned and their relative difference measured to produce a diachronic canopy variation model (DCVM). On the measured volume (Vd), the coefficient of density (cρ) was applied to adjust the volume values (Vadj) in relation to variation due to different DCVM point densities. The measurement setting for AGB volume estimations strongly influenced their correlation with traditional AGB scores. The best fit was obtained selecting 1 mm grid cell size and minimum point height distance. Such options were then selected to measure the DCVM. Adjusted volumes were fully correlated with the average point distance. Three plots revealed higher rates of AGB in the spring compared to summer season, as justified by the summer aridity constraints affecting vegetation productivity in Mediterranean areas. In one plot, we found an anomalous seasonal pattern, showing an AGB reduction in spring, which can be correlated with grazing, that promoted a subsequent increment in summer. Our study indicates that image-based photogrammetric techniques allow for reliable non-destructive measurements of surface biomass in diachronic analyses, offering a valuable tool for evaluating occurrence, magnitude, and spatial patterns of variations of community primary productivity over time. Diachronic canopy variation model produced congruent patterns of inter-seasonal canopy variations proving to be a useful tool for analyzing local disturbance to vegetation canopy caused by grazing.

Keywords: biomass , coefficient of density , diachronic variation , local disturbance , non-destructive measurements , pasture community , photogrammetry , structure-from-motion

In this paper, we present a solution for the photorealistic ambient light render of holograms into dynamic real scenes, in augmented reality applications. Based on Microsoft HoloLens, we achieved this result with an Image Base Lighting (IBL) approach. The real-time image capturing that has been designed is able to automatically locate and position directional lights providing the right illumination to the holograms. We also implemented a negative "shadow drawing" shader that contributes to the final photorealistic and immersive effect of holograms in real life. The main focus of this research was to achieve a superior photorealism through the combination of real-time lights placement and negative "shadow drawing" shader. The solution was evaluated in various Augmented Reality case studies, from classical ones (using Vuforia Toolkit) to innovative applications (using HoloLens).

Keywords: Augmented reality , Holographic shadow , Image processing , Light mapping , Rendering techniques

The preservation status of an underwater cultural site can be determined as the combination of two primary factors, namely the site physical integrity, which results from the past and present interaction of the site itself with the biological/chemical agents located in the surrounding environment, and the exposure of the site to human-related threats. Methods to survey underwater archaeological sites have evolved considerably in the last years in order to face the challenges and problems in archaeological prospection, documentation, monitoring, and data collection.This paper presents a case-study of an archaeological documentation campaign addressed to study and monitor the preservation status of an underwater archaeological site by combining the quantitative measurements coming from optical and acoustic surveys with the study of biological colonization and bioerosion phenomena affecting ancient artefacts. In particular, we present the first results obtained in the survey and documentation campaign carried out during the spring - summer 2018 in the "Nymphaeum of Punta Epitaffio" located in the Marine Protected Area - Underwater Park of Baiae (Naples).

Keywords: 3D Imaging , 3D Mapping , Baiae Archaeological Park , Photogrammetry , Underwater Archaeology

Objectives: To assess conceptual designs of dental posts consisting of polyetherimide (PEI) reinforced with carbon (C) and glass (G) glass fibers in endodontically treated anterior teeth. Methods: 3D tessellated CAD and geometric models of endodontically treated anterior teeth were generated from Micro-CT scan images. Model C-G/PEI composite posts with different Young's moduli were analyzed by Finite Element (FE) methods post A (57.7 GPa), post B (31.6 GPa), post C (from 57.7 to 9.0 GPa in the coronal–apical direction). A load of 50 N was applied at 45° to the longitudinal axis of the tooth, acting on the palatal surface of the crown. The maximum principal stress distribution was determined along the post and at the interface between the post and the surrounding structure. Results: Post C, with Young's modulus decreasing from 57.7 to 9.0 GPa in the coronal–apical direction, reduced the maximum principal stress distribution in the restored tooth. Post C gave reduced stress and the most uniform stress distribution with no stress concentration, compared to the other C-G/PEI composite posts. Significance: The FE analysis confirmed the ability of the functionally graded post to dissipate stress from the coronal to the apical end. Hence actual (physical) C-G/PEI posts could permit optimization of stress distributions in endodontically treated anterior teeth.

Keywords: CAD , Dental materials , Design , Endodontic treatment , Finite Element analysis , Image analysis

In this work is exploited the possibility to use Electronic Speckle Pattern Interferometry (ESPI) for the characterization of different tyres with particular attention to the tyres shoulder section. Tyres characterization is of fundamental importance for vehicle dynamics modelling, since they are the main responsible of vehicles dynamical behaviour and thanks to their ability to deform, they allow to drive a vehicle generating the appropriate interaction forces at the interface with the road. Their behaviour is a consequence to their very complex structure. Two different racing tyres, one for car and other for motorcycle, have been considered. The investigation has been focused at the aim to evaluate and measure the section's components in order to get accurate information about the different layers along through the tyres shoulder section. Here we demonstrate that the different layers (rubber, nylon, steel) can be easily highlighted and identified by mean of the ESPI that, thanks to its high sensitivity, is capable to estimate the different out of plane displacement of the different layers that respond in a different way (i.e. with a different deformation) to a thermal stimulus highlighting the layers themselves. Moreover, we introduce a de-noising step in the reconstruction process: In particular we enhance the wrapped phase information by using a suitable algorithm called SPADEDH. It is important to note that the assessment about the different layers along the section is a very difficult task to obtain by visual inspection or classical microscopy. In fact, the condition of the cutted surface, or rather the strong inhomogeneity and the roughness make impossible to obtain good images especially in the shoulder area.

Keywords: Holography , Non-destructive testing , Speckle , Tyre characterization

Over recent years, various virtual prototyping technologies have been developed to innovate apparel industry. For each step of the garment design process one can find dedicated tools (from body acquisition to garment modelling and simulation) with the aim of making the process easier and faster. However, most of them are based on expensive solutions both for hardware and software systems. In this paper, we focus the attention on the first step of the made-to-measure garment design, i.e. customer's measures acquisition. We present a plug-in, named Tailor Tracking, which permits to get the measurements by interacting with the customer's avatar using hands as in the traditional way. Tailor Tracking has been developed using low cost devices, such as Microsoft Kinect sensor, Leap motion device and Oculus Rift, and open source libraries, such as Visualisation Toolkit (VTK) and Qt. The proposed approach is based on the use of multiple Kinect v2 to simultaneously acquire both customer's body and motion. This permits to emulate the customer's postures required to take the correct measurements. In addition, a virtual measuring tape is made available to replicate the one commonly used by the tailor. A men shirt has been considered as case study and a tailor and 14 people with no skills in garment design and different levels of experience in virtual reality technology have been involved to preliminary test Tailor tracking. Finally, tests as well as results reached so far are presented and discussed. Results have been considered quite good; however, some critical measures have been identified as well as future developments. Anyway, Tailor Tracking can represent an alternative solution to the existing approaches that automatically extract anthropometric measures from the customer's avatar.

Keywords: Clothing design , garment measurements , hand-tracking device , head mounted display , Kinect sensors , motion capture , virtual reality

Using a wheelchair can be a challenging task for people with reduced force and control of muscles of abdomen or lower back. Spinal cord injured (SCI) people are the majority of those who are spending most of the day on a wheelchair and a proper training and chair setup is mandatory to reach a good level of functionality and to avoid harms and side effects. In order to assess the complex motion of a person self-pushing a wheelchair, a motion capture (Mocap) system has been arranged and a group of SCI patients has been acquired in a hospital gym. The Mocap system uses three Microsoft Kinect RGB-D sensors and iPisoft to perform the recording of the 3D motion. The main goal of the research is to provide therapists with a quantitative method to define a preliminary configuration in an objective way once is given the user's medical conditions and his/her way of using the wheelchair. Working side by side with physiotherapists, the main parameters to be evaluated (e.g. pushing angles) have been identified and algorithms have been identified to automatically extract them from the 3D digital avatar model data coming from the Mocap system. The performance of the patients is then analyzed taking into account the wheelchair setup (e.g. position and inclination of the seat and of the back). The influence of geometric parameters on patients' motion is analyzed so that design guidelines for configuration can be found. The overall outcome is to maximize performance and minimize side effects and fatigue, providing users with a better experience on the wheelchair.

A number of pathologies impact on the way a patient can either move or control the movements of the body. Traumas, articulation arthritis or generic orthopedic disease affect the way a person can walk or perform everyday movements; brain or spine issues can lead to a complete or partial impairment, affecting both muscular response and sensitivity. Each of these disorder shares the need of assessing patient's condition while doing specific tests and exercises or accomplishing everyday life tasks. Moreover, also high-level sport activity may be worth using digital tools to acquire physical performances to be improved. The assessment can be done for several purpose, such as creating a custom physical rehabilitation plan, monitoring improvements or worsening over time, correcting wrong postures or bad habits and, in the sportive domain to optimize effectiveness of gestures or related energy consumption. The paper shows the use of low-cost motion capture techniques to acquire human motion, the transfer of motion data to a digital human model and the extraction of desired information according to each specific medical or sportive purpose. We adopted the well-known and widespread Mocap technology implemented by Microsoft Kinect devices and we used iPisoft tools to perform acquisition and the preliminary data elaboration on the virtual skeleton of the patient. The focus of the paper is on the working method that can be generalized to be adopted in any medical, rehabilitative or sportive condition in which the analysis of the motion is crucial. The acquisition scene can be optimized in terms of size and shape of the working volume and in the number and positioning of sensors. However, the most important and decisive phase consist in the knowledge acquisition and management. For each application and even for each single exercise or tasks a set of evaluation rules and thresholds must be extracted from literature or, more often, directly form experienced personnel. This operation is generally time consuming and require further iterations to be refined, but it is the core to generate an effective metric and to correctly assess patients and athletes performances. Once rules are defined, proper algorithms are defined and implemented to automatically extract only the relevant data in specific time frames to calculate performance indexes. At last, a report is generated according to final user requests and skills.