Search

Purpose Electrocardiogram (ECG) is one of the most essential tools for detecting heart problems. Till today most of the ECG records are available in paper form. It can be challenging and time-consuming to manually assess the ECG paper records. Hence, automated diagnosis and analysis are possible if we digitize such paper ECG records. Methods The proposed work aims to convert ECG paper records into a 1-D signal and generate an accurate diagnosis of heart-related problems using deep learning. Camera-captured ECG images or scanned ECG paper records are used for the proposed work. Effective pre-processing techniques are used for the removal of shadow from the images. A deep learning model is used to get a threshold value that separates ECG signal from its background and after applying various image processing techniques threshold ECG image gets converted into digital ECG. These digitized 1-D ECG signals are then passed to another deep learning model for the automated diagnosis of heart diseases into different classes such as ST-segment elevation myocardial infarction (STEMI), Left Bundle Branch Block (LBBB), Right Bundle Branch Block (RBBB), and T-wave abnormality. Results The accuracy of deep learning-based binarization is 97%. Further deep learning-based diagnosis approach of such digitized paper ECG records was having an accuracy of 94.4%. Conclusions The digitized ECG signals can be useful to various research organizations because the trends in heart problems can be determined and diagnosed from preserved paper ECG records. This approach can be easily implemented in areas where such expertise is not available. Supplementary Information The online version contains supplementary material available at 10.1007/s40846-021-00632-0.

In production, poor ergonomic environments not only lead to increased workloads and health hazards for employees but also tend to reduce efficiency and quality. Recently, the human-cyber-physical (HCP) system has been proposed and widely studies to meet human capabilities and limitations. However, most existing frameworks are still not adaptive enough to integrate humans into a smart production environment due to a lack of real-time individual human factors digitalization. This research proposes an HCP workstation model for comprehensive assembly resources digitalization and autonomous interaction by CPS enabling technologies. Based on this, an adaptive control system has been developed for proactive ergonomic risk mitigation. Computer vision is deployed for real-time individual ergonomic evaluation and a prototype has been set up for functional validation.

In this study, the effects of ambient illuminance and light source on participants’ reading performance and visual fatigue during a long reading task were investigated using three electronic paper displays. Reading on electronic paper displays was also compared with reading on paper. In Experiment 1, 100 participants performed a reading task where the display area for the text was equated for the displays. The results indicated that participants’ visual performance and visual fatigue did not differ significantly among different electronic paper displays, ambient illuminance conditions, or light sources. In Experiment 2, another 60 participants performed the same reading task where the full screen of each electronic paper display was used to present the text. The results showed that reading speed differed significantly across different electronic paper displays and ambient illuminance levels. The reading speed was slower for displays with smaller screens and increased as the ambient illuminance increased. Changes in the critical flicker fusion frequency significantly differed across ambient illuminance levels. Implications of the results for the use of electronic paper displays are discussed.

Creatinine is a clinically significant analyte used to diagnose kidney condition. However, the literature still lacks in creatinine sensors fulfilling point-of-care testing requirements. In this paper, we have developed colorimetric paper-based creatinine sensors adhering to point-of-care testing principles. The signal readout is accomplished with a smartphone modified with 3D-printed elements and processed with a self-written application compromising computer vision algorithm for automatic detection of the colored zone. Two colorimetric methods – routinely used Jaffe method and an alternative one with 3,5-dinitrobenzoic acid were both tested and compared. Hue channel intensity from HSV color space and green channel from RGB color space was used as the analytical signal in Jaffe and 3,5-dinitrobenzoate method, respectively. For both kinds of sensors the linear range of the response covered the range significant for urinary analysis, with precision, expressed as RSD, below 5%. Limit of quantification for Jaffe method was 1.05 mmol·L−1 whereas it was 0.82 mmol·L−1 for 3,5-dinitrobenzoate method. The utility of the developed sensors to selectively quantify creatinine in undiluted urine was proved using artificial urine samples and the obtained recoveries were in the range from 70 to 129 %.

This study investigated the effects of bending curvature of simulated e-paper displays (−10 cm, plane and 10 cm) and ambient illuminance (50, 500, 6000 and 12,000 lx) on the visual performance of young and elderly users for simulated electronic-paper displays. In total, 24 people comprising 12 young and 12 elderly users participated in this study. Young users demonstrated significantly enhanced visual performance using the simulated electrophoretic ink (E ink) e-paper display with ambient illuminance set at 50 and 500 lx; however, participants did not demonstrate significantly different visual performance using the 2 simulated e-paper displays with ambient illuminance set at 6000 and 12,000 lx. The bending curvature did not exhibit significant effects on the visual performance of young participants under various ambient illuminances. The elderly participants exhibited significantly enhanced visual performance using the simulated E ink e-paper display only when ambient illuminance was set at 50 lx; however, participants did not exhibit significantly different visual performance using the two simulated e-paper displays with ambient illuminance set at other levels. Elderly users exhibited significantly enhanced visual performance when the bending curvature was set at 10 cm, with ambient illuminance set at 50 lx. Elderly users also demonstrated significantly enhanced visual performance under bending curvature settings of 10 cm and plane, with ambient illuminance set at 500 lx. However, the bending curvature of the simulated e-paper did not exhibit significant effects on the visual performance of elderly participants under ambient illuminance settings of 6000 and 12,000 lx.

Visual performance and visual fatigue of electronic paper displays (electrophoretic display and cholesteric liquid crystal display) under ambient illuminances and light sources were studied and compared with paper. Forty-eight participants participated in a character-search task in the experiment. The results showed that search speed depends on the illuminance but not light source. Search speed increased as illumination increased from 300 lx (45.6 sec), 700 lx (44.18 sec) to 1500 lx (43.24 sec). The effect of medium display and polarity on accuracy was also significant. Accuracy was greater for electrophoretic display and positive polarity. However, the effect of illuminance and light source on visual fatigue was not statistically significant. Based on the results of this study, it seems that E-paper displays may need greater illumination (700 lx or higher).

Paper formation (the distribution and intermixing of fibres in a paper sheet), plays a central role in paper products, and is usually evaluated off-line, with a significant delay relative to the high production rates achieved in modern paper machines. In this paper, we address an approach for evaluating and monitor paper formation using images acquired with an especially designed sensor, in-line, in-situ and in real time. The methodology essentially consists of applying wavelet texture analysis to raw images, in order to compute a wavelet signature for each image, based on which their discrimination, according to the formation quality level, can be made. A PCA analysis of such features confirms the different formation quality levels defined a priori after visual inspection, and, furthermore, suggests a new subclass for abnormal samples, related to the bulkiness of fibre flocks. A multivariate statistical process control framework, based on such PCA description (PCA-MSPC), is proposed to monitor formation quality, which provides quite good results when applied to the available images, as analyzed with the ROC curve for the method and confirmed with a Monte Carlo simulation study using subimages with 1/4 of the size of the original ones.

Effects of character size under ambient illuminances and light sources on legibility of electronic paper displays (electrophoretic display and cholesteric liquid crystal display) were studied and compared with paper. Sixty subjects participated in a letter-search task in the experiment. The results showed that search speed depends on the illuminance but not light source. Search speed increased as the illuminance increase from 300, 700 to 1500 lx. Search speed also increased with the increase of character size, from character height of 1.4 mm (9.6 min visual angle), 2.2 mm (15.1 min visual angle) to 3.3 mm (22.7 min visual angle), and the increase leveled off at 4.3 mm (29.6 min visual angle). The effect of character size on accuracy was also significant. Accuracy increased with the increase of character size. However, the effect of illuminance and light source on accuracy was not statistically significant. Based on the results of this study, it seems that E-paper displays may need greater illumination (700 lx or higher), greater character size (3.3 mm or 22 min of visual angle).

Multi-sensor object detection and tracking on a highway scene with radar measurements is presented. The estimation algorithm is the random finite set based Bernoulli filter, working in the Bayesian framework. The recursion for calculating the Bayes estimation is implemented as a particle filter. A method is presented for calculating the likelihoods, suitable for particle filtering performed with moving sensors, assuming additive Gaussian measurement noise. In our approach, for calculating the posterior estimate of the object state, the measurement likelihoods are computed in the state space, instead of the measurement space, by mapping each measurement to the global coordinate system. The map consists of a nonlinear and an affine part. While the affine transformation trivially preserves the Gaussian nature, the nonlinear is well-proven to be approximated as affine too. This approach allows the particles to be drawn directly from the state space, hence the evaluation of the measurement model is not needed, which saves computational power.

In this paper, we describe the development of a system for evaluating an specific quality characteristic of recycled paper sheets using techniques of image analysis and pattern recognition. We call Bumpiness the phenomenon of interest, which is new in the literature on paper quality. This phenomenon is characterized by the appearance of macroscopic undulations on the paper sheet surface that may emerge shortly or some time after its production. We explore the detection and measurement of this defect by means of computer vision and statistical pattern recognition techniques that may allow early detection at the production site. Our goal is to give an scalar continuous measure of Bumpiness. We propose features computed from Gabor filter banks (GFB) and discrete wavelet transforms (DWT) for the characterization of paper sheet surface Bumpiness in recycled paper images. The starting point is to state the problem as a classification of the paper sheet images into two classes: low and high Bumpiness. In this setting we obtain, with both proposed texture modelling approaches (GFB and DWT), classification accuracies comparable to the agreement between human observers. The best performance is obtained using DWT features. Finally, we propose as the scalar index of Bumpines the fisher discriminant analysis (FDA) function defined on the space of the best features for the classification task. We perform an innovative validation process of this Bumpiness index, based on the ordering of random pairs of images, obtaining a very high agreement with the human observers.

The study used the simulated e-paper to investigate how the bending radius of curvature (−10 cm, plane, and 10 cm) and 12 text/background color-combinations of e-paper affect subjects’ visual performance and subjective preference under various ambient illuminance conditions (200 and 500 lx). Analysis results indicated that the bending curvature and ambient illuminance did not significantly affect subjects’ visual performance. However, subjects visual performance differed significantly for different text/background color combinations of the simulated e-paper. When the background color of the simulated e-paper was set to yellow-like condition and the luminance of the text was low (2.2 and 4.6 cd/m 2 ), subjects’ visual performance was best. Regarding the subjective preferences of subjects, the results of this research also demonstrated that the bending curvature, text/background color combinations and ambient illuminance all significantly affected the subjective preferences of subjects. Subjects exhibited the best preference under the following settings: bending curvature of the simulated e-paper set to plane; background color of the simulated e-paper set to yellow-like condition and low text luminance (2.2 or 4.6 cd/m 2 ); high ambient illuminance (500 lx).

The main objective of this paper is to elaborate how defective fabric parts can be processed using Matlab with image processing techniques. In developing countries like India especially in Tamilnadu, Tirupur the Knitwear capital of the country in three decades yields a major income for the country. The city also employs either directly or indirectly more than 3 lakhs of people and earns almost an income of 12, 000 crores per annum for the country in past three decades [2]. To upgrade this process the fabrics when processed in textiles the fault present on the fabrics can be identified using Matlab with Image processing techniques. This image processing technique is done using Matlab 7.3 and for the taken image, Noise Filtering, Histogram and Thresholding techniques are applied for the image and the output is obtained in this paper. This research thus implements a textile defect detector with system vision methodology in image processing.

QT dispersion from the 12 lead ECG has been extensively evaluated as a risk parameter in pts prone to arrhythmias. Usually, this parameter is assessed directly from the ECG tracing by means of a magnifying glass and a digitizing pad with reproducibility and accuracy not being optimal. We therefore developed a software program with a graphical interface permitting conversion of a scanned image of the ECG on paper to a digital ECG function (sampling rate 500 or 1000 Hz) which can then be analyzed by a second interactive computer program for standard ECG intervals, QT dispersion and other repolarization parameters (JTpeak, T areas, T peak to T end interval). Digitally available ECGs can also be converted to a format analyzable by the program. The respective signals are processed channel-by-channel with enlarged high resolution display on a 20″ computer screen. The computer program uses customized algorithms to detect important features of the ECG waveforms (Q onset, J point, T peak, and T end for ECG signals) and then displays colored vertical spikes superimposed on the signal marking these points with high resolution for confirmation or manual correction by the observer. The processed data are automatically written to a spreadsheet for further processing. With this methodology accuracy and reproducibility of QT intervals and ECG parameters of dispersion of repolarization can be increased and parameters not easily measurable on paper can be determined (T wave areas).

Vision is one of the most important sources of information for supporting intelligent human behaviour, as well as a key competence for designing new types of intelligent computers and machines. Over the period of the past 40 years or so, computer vision has evolved into a mature subject including many topics and applications which range from the automatic interpretation of documents to the image recognition for the automatic guidance of vehicles. In reality, however, current computer vision systems are vastly di-erent from, and in most ways inferior to, biological vision systems. Software agents are computer programs capable of 3exible, autonomous action and may support a wide range of di-erent behaviours, de5ned as rules, or based on machine learning algorithms such as neural networks. Agents also, generally, monitor their operating environment and respond to events in a timely fashion, utilising internal scheduling and planning engines to formulate a response. Perhaps the most signi5cant advantage that an agent-based approach provides is the ability to design systems based on decoupled units–based on the particular role that such a unit is likely to play within a multi-agent system. Authors are encouraged to submit papers which cover some of the following issues (although this list is not exhaustive)

Identifying a forged printed document with scanned evidence can be a challenge. Microscopic printing is showing random shape which depends on the printing source as well as printing material. This paper presents a statistical analysis of the printing patterns under a microscopic scale, analyses the effect of printing direction, printing substrate (uncoated and coated paper), and printing technology (conventional offset, waterless offset, and electrophotography). The analysis shows a negligible effect of printing direction, yet, using the shape descriptor indexes, the printing materials and technologies are distinguishable under a microscopic scale. As a result, the algorithms based on Support Vectors Machine and Random Forest are developed, with shape descriptor indexes as features, for printing source identification. Both proposed algorithms, equally, achieve a high classification accuracy rate, over 92% accuracy with complex geometric-shape patterns. Thanks to the lightweight and efficiency of the Support Vectors Machine, the study shows promising applications for real-world and potential implementation in the Internet of Things devices.

Observers rank partly visible postures on video frames differently than fully visible postures, but it's not clear if this is due to differences in observer perception. This study investigated the effect of posture visibility on between-observer variability in assessments of trunk and arm posture. Trained observers assessed trunk and arm postures from video recordings of 84 pulp mill shifts using a work sampling approach; postures were also categorized as ‘fully’ or ‘partly’ visible. Between-worker, between-day, and between-observer variance components and corresponding confidence intervals were calculated. Although no consistent gradient was seen for the trunk, right upper arm posture showed smaller between-observer variance when all observers rated a posture as fully visible. This suggests that, partly-visible data, especially when observers disagree as to the level of visibility, introduces more between-observer variability when compared to fully visible data. Some previously-identified differences in daily posture summaries may be related to this phenomenon.

An automatic visual inspection system designed for dirt inspection in the pulp and paper industry is presented. A new hierarchical region oriented segmentation algorithm is introduced. The algorithm is tuned according to the singular characteristics of the pulp samples. A criterion based on the maximisation of the local contrast is defined in order to perform a defect region segmentation of the pulp and paper images. Some optimisations are introduced to avoid an excessive computational load. http://www.sciencedirect.com/science/article/B6V27-3XR260K-2T/1/aa6b716fc7193b3d447bff73516ce10d

This paper proposes a novel technique for converting a given animated mesh into a series of displaced subdivision surfaces. Instead of independently converting each mesh frame in the animated mesh, our technique produces displaced subdivision surfaces that share the same topology of the control mesh and a single displacement map. We first propose a conversion framework that enables sharing the same control mesh topology and a single displacement map among frames, and then present the details of the components in the framework. Each component is specifically designed to minimize the shape conversion errors that can be caused by enforcing a single displacement map. The resulting displaced subdivision surfaces have a compact representation, while reproducing the details of the original animated mesh. The representation can also be used for efficient rendering on modern graphics hardware that supports accelerated rendering of subdivision surfaces.

Wood quality assessment is an important issue in the pulp and paper industry. In this paper an automatic visual inspection system for wood structural quality measurement is described. To improve statistical image segmentation a new logarithm based global contrast enhancement technique is described. Region identification and reconstruction is performed based on local morphological operators with constrained merge operations. A measurement technique, build-up upon a constrained optimisation problem, is described for fibber wall width computation. The method proves computational efficiency. The described inspection system uses only two control parameters. http://www.sciencedirect.com/science/article/B6V27-3XR260K-2X/1/ec9883418b48742462509747b052093f

The systems and concepts described in this paper document the evolution of the geometric invariance approach to object recognition over the last five years. Invariance overcomes one of the fundamental difficulties in recognising objects from images: that the appearance of an object depends on viewpoint. This problem is entirely avoided if the geometric description is unaffected by the imaging transformation. Such invariant descriptions can be measured from images without any prior knowledge of the position, orientation and calibration of the camera. These invariant measurements can be used to index a library of object models for recognition and provide a principled basis for the other stages of the recognition process such as feature grouping and hypothesis verification. Object models can be acquired directly from images, allowing efficient construction of model libraries without manual intervention. A significant part of the paper is a summary of recent results on the construction of invariants for 3D objects from a single perspective view. A proposed recognition architecture is described which enables the integration of multiple general object classes and provides a means for enforcing global scene consistency. Various criticisms of the invariant approach are articulated and addressed.

Latent lip print test results produced by permanent lipsticks are presented in this work. This cosmetic product, contrary to conventional lipsticks, does not leave visible prints and can thus be overlooked at the crime scene. As print vehicles the study used ceramics, glass, cotton fabric and paper. Lip prints were left to dwell for different periods and were later developed using aluminum powder, cobalt oxide powder and magnetic powder. The results show that identifiable lip prints can be obtained up to 30 days after being produced.

We present an approach to compute the perceived complexity of a given 3D shape using the similarity between its views. Previous studies on 3D shape complexity relied on geometric and/or topological properties of the shape and are not appropriate for incorporating results from human shape perception which claim that humans perceive 3D shapes as organizations of 2D views. Therefore, we base our approach to computing 3D shape complexity on the (dis)similarity matrix of the shape's 2D views. To illustrate the application of our approach, we note that simple shapes lead to similar views whereas complex ones result in different, dissimilar views. This reflected in the View Similarity Graph (VSG) of a shape as tight clusters of points if the shape is simple and increasingly dispersed points as it gets more complex. To get a visual intuition of the VSG, we project it to 2D using Multi-Dimensional Scaling (MDS) and introduce measures to compute shape complexity through point dispersion in the resulting MDS plot. Experiments show that results obtained using our measures alleviate some of the drawbacks present in previous approaches.

A common variant of caricature relies on exaggerating characteristics of a shape that differs from a reference template, usually the distinctive traits of a human portrait. This work introduces a caricature tool that interactively emphasizes the differences between two three-dimensional meshes. They are represented in the manifold harmonic basis of the shape to be caricatured, providing intrinsic controls on the deformation and its scales. It further provides a smooth localization scheme for the deformation. This lets the user edit the caricature part by part, combining different settings and models of exaggeration, all expressed in terms of harmonic filter. This formulation also allows for interactivity, rendering the resulting 3d shape in real time.

Simultaneous Localization and Mapping (SLAM) is the foundation of autonomous navigation for unmanned systems. The existing SLAM solutions are mainly divided into the visual SLAM(vSLAM) equipped with camera and the lidar SLAM equipped with lidar. However, pure visual SLAM have shortcomings such as low positioning accuracy, the paper proposes a visual-inertial information fusion SLAM based on Runge-Kutta improved pre-integration. First, the Inertial Measurement Unit (IMU) information between two adjacent keyframes is pre-integrated at the front-end to provide IMU constraints for visual-inertial information fusion. In particular, to improve the accuracy in pre-integration, the paper uses the Runge-Kutta algorithm instead of Euler integral to calculate the pre-integration value at the next moment. Then, the IMU pre-integration value is used as the initial value of the system state at the current frame time. We combine the visual reprojection error and imu pre-integration error to optimize the state variables such as speed and pose, and restore map points' three-dimensional coordinates. Finally, we set a sliding window to optimize map points' coordinates and state variables. The experimental part is divided into dataset experiment and complex indoor-environment experiment. The results show that compared with pure visual SLAM and the existing visual-inertial fusion SLAM, our method has higher positioning accuracy.

Localization forms the heart of various autonomous mobile robots. For efficient navigation, these robots need to adopt effective localization strategy. This paper, presents a comprehensive review on localization system, problems, principle and approaches for mobile robots. First, we classify the localization problems in to three categories based on the information of initial position of the robot. Next, we discuss on robot position update principles. Then, we discuss key techniques to localize the mobile robot such as: probabilistic approach, autonomous map building and radio frequency identification (RFID) based scheme. In the probabilistic localization section, we discuss the Markov localization and Kalman filter along with its extended versions. Autonomous map building focuses on the widely used simultaneous localization and mapping (SLAM) approach. This section also discusses on applying SLAM to localize brain-controlled mobile robots. Next, we discuss on applying evolutionary approaches to estimate optimal position. The RFID scheme addresses on effective utilization of RFID tags to track objects and position the robot. We then analyze on position and orientation errors occurred by different localization strategies. We conclude this paper by highlighting future research possibilities.

Periocular region is the feature rich region around the eye which may include features like eyelids, eyelashes, eyebrows, tear duct, eye shape, skin texture and many more. Periocular region based authentication system is a good trade-off between face and iris based biometric authentication systems as they need high user cooperation. This paper provides a comprehensive survey of periocular biometrics and a deep insight of various aspects such as utility of periocular region as a stand-alone modality, periocular region and its fusion with iris, application of periocular region in smart phone authentication and the role of periocular region in soft biometric classification etc. The paper also provides an outlook over possible future research in the area of periocular biometrics.

In this paper, we use artificial intelligence image recognition to obtain Digestive endoscopy image, and process the image based on 5G Deep learning edge algorithm to judge the disease type of the patient, and then consider the treatment plan. The combination of body area network and edge computing technology can meet the demand of low delay in body area network. In this case, the resource constrained body area network gateway node can process the physiological data collected by it into an offloadable task, and then unload the task and data to the edge computing node according to a certain strategy. The edge computing node completes the corresponding task processing and data storage, and finally provides the results to the relevant medical institutions and body area network users for reading auxiliary diagnosis and treatment of diseases. Studies have shown that 25% of patients with colon polyps have CD4 cells in peripheral blood based on 5G deep learning edge algorithm under artificial intelligence image recognition of Digestive endoscopy. The number of lymphocyte in group of differentiation was less than 200/μL, and the blood RNA in 92.3% patients was lower than 100 IU/ml, while fam CTP (A-cyclic peptide) was lower than 100 IU/ml. Opportunistic infections of the intestine and viruses can directly cause enteropathy because the fluorescence intensity of the probe is essentially unchanged and cannot form a triple helix structure. In terms of feature recognition accuracy, the 5G deep learning edge algorithm in this paper improves accuracy by 68% compared to the simple Yolo algorithm, and is similar in speed. Compared with RCNN algorithm, the accuracy and speed are improved by 21% and 85% respectively. Therefore, the 5G deep learning edge algorithm based on artificial intelligence image recognition has the advantages of accuracy and speed in digestive endoscopy of intelligent medical.

Agricultural disease image recognition has an important role to play in the field of intelligent agriculture. Some advanced machine learning methods associated with the development of artificial intelligence technology in recent years, such as deep learning and transfer learning, have begun to be used for the recognition of agricultural diseases. However, the adoption of these methods continues to face a number of important challenges. This paper looks specifically at deep learning and transfer learning and discusses the recent progress in the use of these advanced technologies for agricultural disease image recognition. Analysis and comparison of these two methods reveals that current agricultural disease data resources make transfer learning the better option. The paper then examines the core issues that require further study for research in this domain to continue to progress, such as the construction of image datasets, the selection of big data auxiliary domains and the optimization of the transfer learning method. Creating image datasets obtained under actual cultivation conditions is found to be especially important for the development of practically viable agricultural disease image recognition systems.

With the rapid development of intelligent control technology, computer technology, bionics, artificial intelligence and other disciplines, more and more attention has been paid to the research of intelligent mobile robot technology, and autonomous positioning is the basis for mobile robots to conduct autonomous navigation and exploration research. Sensors assist each other to provide a wealth of perception information about the internal state of the robot and the external surrounding environment. This paper proposes a method for optimizing the Support Vector Machine (SVM) multi-classifier with a binary tree structure, which improves the accuracy of multi-modal tactile signal recognition. The improved particle swarm clustering algorithm is used to optimize the binary tree structure, reduce the error accumulation of the binary tree structure SVM multi-classifier, and further improve the accuracy of multi-modal tactile signal recognition. The effect of the method in this paper is verified by robot grasping experiments. The results show that the use of multi-modal information of two-dimensional images and three-dimensional point cloud images can effectively identify and locate target objects of different shapes. Compared with the processing method of two-dimensional or point cloud monomodal image information, the positioning error can be reduced by 54.8%, and the direction error can be reduced by 50.8%, which has better robustness and accuracy. The simulation results show that the improved PSOBT-SVM model has the best classification effect for artificial features, PCA features and spatio-temporal correlation features. The improved PSOBT-SVM optimizes the classification accuracy without changing the number of SVM classifiers, and proves its accuracy in classifying multimodal tactile signals.

In this paper, we tackle the task of improving biometric verification in the context of Human-Robot Interaction (HRI). A robot that wants to identify a specific person to provide a service can do so by either image verification or, if light conditions are not favourable, through voice verification. In our approach, we will take advantage of the possibility a robot has of recovering further data until it is sure of the identity of the person. The key contribution is that we select from both image and audio signals the parts that are of higher confidence. For images we use a system that looks at the face of each person and selects frames in which the confidence is high while keeping those frames separate in time to avoid using very similar facial appearance. For audio our approach tries to find the parts of the signal that contain a person talking, avoiding those in which noise is present by segmenting the signal. Once the parts of interest are found, each input is described with an independent deep learning architecture that obtains a descriptor for each kind of input (face/voice). We also present in this paper fusion methods that improve performance by combining the features from both face and voice, results to validate this are shown for each independent input and for the fusion methods.

This paper synchronizes control theory with computer vision by formalizing object tracking as a sequential decision-making process. A reinforcement learning (RL) agent successfully tracks an interface between two liquids, which is often a critical variable to track in many chemical, petrochemical, metallurgical, and oil industries. This method utilizes less than 100 images for creating an environment, from which the agent generates its own data without the need for expert knowledge. Unlike supervised learning (SL) methods that rely on a huge number of parameters, this approach requires far fewer parameters, which naturally reduces its maintenance cost. Besides its frugal nature, the agent is robust to environmental uncertainties such as occlusion, intensity changes, and excessive noise. From a closed-loop control context, an interface location-based deviation is chosen as the optimization goal during training. The methodology showcases RL for real-time object-tracking applications in the oil sands industry. Along with a presentation of the interface tracking problem, this paper provides a detailed review of one of the most effective RL methodologies: actor–critic policy.

In recent years, with the improvement of artificial intelligence technology, it has become possible to reconstruct high-precision 3D human body models based on ordinary RGB images. The current 3D human body reconstruction technology requires complex external equipment to scan all angles of the human body, which is complicated to be implemented and cannot be popularized. In order to solve this problem, this paper applies deep learning models on reconstructing 3D human body based on monocular images. First of all, this paper uses Stacked Hourglass network to perform convolution operations on monocular images collected from different views. Then Multi-Layer Perceptrons (MLPs) are used to decode the encoded high-level images. The feature codes in the two views(main and side) are fused, and the interior and exterior points are classified by the fusion features, so as to obtain the corresponding 3D occupancy field. At last, the Marching Cube algorithm is used for 3D reconstruction with a specific threshold and then we use Laplace smoothing algorithm to remove artifacts. This paper proposes a dense sampling strategy based on the important joint points of the human body, which has a certain optimization effect on the realization of high-precision 3D reconstruction. The performance of the proposed scheme has been validated on the open source datasets, MGN dataset and the THuman dataset, provided by Tsinghua University. The proposed scheme can reconstruct features such as clothing folds, color textures, and facial details,and has great potential to be applied in different applications.

This paper presents an approach to determine optimal grasping poses for dual-arm space robot cooperatively grasping an uncooperative satellite. Aiming at better manipulating the satellite after capture, it is necessary to plan properly grasping poses on the satellite for dual-arm end-effectors to maximize the manipulability of space robot. In this paper, global manipulability based on capability map is applied as the quality index to seek optimal grasping poses. First, the technique to generate cooperative workspace for a closed chain system is introduced fusing the workspace of each single-arm with self-collision avoidance. Second, several general manipulability indices, such as dexterity, manipulability measure and task compatibility, are extended to the entire cooperative workspace to construct capability maps. Next, global manipulability is evaluated for dual-arm space robot cooperative manipulation based on the capability maps. Following this, the optimal grasping poses among all feasible grasping poses on the satellite are obtained by the global manipulability. Finally, a simulation study is carried out to verify the feasibility of the proposed approach based on a redundant dual-arm space robotic system.

This paper presents a modified Neutron Computerized Tomography reconstruction method for solving three main problems facing the Inverse Radon Transform based reconstruction method. The three problems are poor contrast of the reconstructed slice, the duplication of slice and the error in the center of rotation position in the images. The paper aims to solve all of these problems automatically without user intervention and during the acquisition phase in order to obtain immediate clear noise free high-quality reconstruction. The proposed method did not use any special filters in all its phases except the two basic filters, the median filter in normalization phase and one kind from the five filters that used in filtered back-projection step. Six samples have been studied taken in different rotations 180° and 36b° with different equiangular steps, different exposure times and different reactor power to prove high quality of reconstructed slice under these parameters. The practical work has been carried out in the Neutron Computerized Tomography facility at the Egyptian Second Research Reactor. The resulted reconstructed images showed that a high-quality image has been obtained comparable to the existing classical reconstruction method without losing any information.

Divers perform demanding tasks in a complex and hazardous underwater environment, which prevents them from carrying special devices that may allow them to communicate with their robotic diving buddies. In this world of natural human-robot interaction in the underwater environment, envisioned by the FP7 Cognitive Robotics project CADDY, hand detection and gesture interpretation is a prerequisite. While hand gesture recognition is most often performed with cameras (mono and stereo), their use in the underwater environment is compromised due to water turbidity and lack of sunlight at greater depths. This paper deals with this lack of performance by introducing the concept of using high resolution multibeam sonars (often referred to as acoustic cameras) for diver hand gesture recognition. In order to ensure reliable communication between the diver and the robot, it is of great importance that the classification precision is as high as possible. This paper presents results of hand gesture recognition which is performed by using two approaches: convex hull method and the support vector machine (SVM). A novel approach that fuses the two methods is introduced as a way of increasing the precision of classification. The results obtained on more than 1000 real sonar samples show that the precision using the convex hull method is around 92%, and using the SVM around 94%, while fusing the two approaches provides around 99% classification precision.

One of the visually noticeable compression artifacts in block-based image/video compression platforms is called blocking artifact. Several post-processing methods were presented to reduce such kind of artifacts. However, most methods in the literature often induce visibly blurring artifacts. The paper presents a deep network to eliminate image compression artifacts (usually denoted by image deblocking) based on image fusion in multi-scale manner. Recent deep learning-based related methods usually learn deep models using a loss function in per-pixel manner based on explicit image priors in order to directly produce clean images. In place of existing deep learning-guided approaches, the problem is reformulated in this paper to the learning of the residuals (or artifacts) between the received images and their corresponding clean images (ground truths). In the presented deep framework, an input image is first down-sampled while naturally reducing the blocking artifacts. Then, our multi-scale image fusion model is used for fusing the different down-scaled versions (of less artifacts) with the input image (with severer artifacts) to estimate the blocking artifacts. Then, by deducting the estimated artifacts from the input image, the blocking artifacts can be significantly eliminated and most original image details are preserved simultaneously. The presented method is well applicable to any vision-based computer systems with digital visual codec embedded.

In agriculture science, automation increases the quality, economic growth and productivity of the country. The export market and quality evaluation are affected by assorting of fruits and vegetables. The crucial sensory characteristic of fruits and vegetables is appearance that impacts their market value, the consumer’s preference and choice. Although, the sorting and grading can be done by human but it is inconsistent, time consuming, variable, subjective, onerous, expensive and easily influenced by surrounding. Hence, an astute fruit grading system is needed. In recent years, various algorithms for sorting and grading are done by various researchers using computer vision. This paper presents a detailed overview of various methods i.e. preprocessing, segmentation, feature extraction, classification which addressed fruits and vegetables quality based on color, texture, size, shape and defects. In this paper, a critical comparison of different algorithm proposed by researchers for quality inspection of fruits and vegetables has been carried out.

Stair region detection and recognition from a stair candidate image is a challenging work in the computer vision research area. In the last few decades, researchers use many recognition systems to recognize and verify the stair region from other analogous objects. However, all the verification systems such as vanishing point (VP) do not achieve the desired result for various reasons. In this regard, a method is proposed in this paper to investigate the vanishing point’s problem arising in the case of stair region verification based on the three basic criteria, i.e. focal angle of the camera, height of the camera from the ground, and distance of the camera from the stair image. For that, primarily, the stair region is extracted by utilizing the geometrical features of a stair. The detected stair candidate region is verified through the y coordinate value of the vertical VP, i.e. y y coordinate value of VP does not verify the stair region from all the scenarios. This paper investigates and justifies this problem utilizing the experimental analysis and introduces a mathematical model to estimate the location of the VP of the stair region. Finally, support vector machine (SVM) classifier is utilized instead of VP to recognize the stair candidate region and the performance of SVM is compared with respect to the VP. For that, rotational invariant uniform local binary pattern (LBP) is used for feature extraction. Stair images captured under different orientation and illumination conditions have been used to test the proposed method to evaluate the resultant accuracy.

Brain-computer interface (BCI) based on electroencephalogram (EEG) signals can provide a way for human to communicate with the outside world. This approach is independent of the body's peripheral nerves and muscle tissue. The brain-controlled robot is a new technology based on the brain-computer interface technology and the robot control technology. This technology allows the human brain to control a robot to perform a series of actions. The processing of EEG signals plays a vital role in the technology of brain-controlled robots. In this paper, the methods of EEG signal processing in recent years are summarized. In order to better develop the EEG signal processing methods in brain-controlled robots, this paper elaborate on three parts: EEG signal pre-processing, feature extraction and feature classification. At the same time, the correlation analysis methods and research contents are introduced. The advantages and disadvantages of these methods are analyzed and compared in this paper. Finally, this article looks forward to the EEG signal processing methods in the process of brain-controlled robots.

Recently, two types of common sensors, LiDAR and Camera, show significant performance on all tasks in 3D vision. LiDAR provides accurate 3D geometry structure, while camera captures more scene context and semantic information. The fusion of two different sensor becomes a fundamental and common idea to achieve better performance. To give a thorough cognition of the complementary and boosting about two kind of sensors. This paper briefly reviews the fusion and enhancement systems between both two sensors in the field of depth completion, 3D object detection, 2D\3D semantic segmentation and 3D object tracking. Meanwhile, the state of art fusion algorithms is quantitatively demonstrated, in this paper, based on the in KITTI widely-used public dataset. Furthermore, the technical challenge and the future potential of LiDAR and camera fusion are also discussed.

This paper deals with the estimation of the lateral motion of steel strips during the hot strip rolling process in a tandem finishing mill. The method presented in this paper uses an image sequence captured by a 2D-CMOS camera. In the considered application, just a small segment of the strip is inside the camera field of view and thus an image sequence has to be used for online estimation. An optimization-based algorithm uses the image data and the knowledge about the constraints of the strip movement in the rolling gap for robust estimation of the lateral position and width of the strip. Measurement data from a tandem finishing mill show the performance of the designed algorithm.

Paper discusses modern methods for localization of mobile ground robot in outdoor environment. Special attention is payed to lidar-based methods which allow to do precise simultaneous localization and mapping (SLAM) independently to lighting conditions. Modular approach to lidar-based localization is proposed. It consists of three modules: map reconstructor, map merger and corrector, localization module. As map reconstructor we use 3D Lidar-based Graph SLAM, state-of-the-art method LOAM and its modification with point cloud segmentation techniques A-LeGO-LOAM. As map merger and corrector we apply the technique of interactive map correction for 3D Graph SLAM. For localization module we compare different real-time approaches: NDT scan matching and Localization with scan batch processing. They do not allow to localize the robot with an unknown initial position. To overcome this problem, a stage of global Monte Carlo localization is proposed, which allows to generate a switching condition and a rough initial pose. Matrix of localization convergence speed is introduced to study influence of possible inaccuracies of initial pose estimation to the convergence of real-time localization approach. An important emphasis in the paper is made to the evaluation of the localization quality with relative and absolute metrics. Experimental results are obtained for own data from mobile ground robot ClearPath Husky equipped with Velodyne HDL-32E lidar. Proposed approach to robot localization achieves real-time performance for different hardware platforms in particular single-board computer Nvidia Jetson Xavier. It demonstrates possibility for integration of studied modular localization approach to onboard control systems of autonomous vehicles.

Background Augmented assembly guidance aims to help users complete assembly operations more efficiently and quickly through augmented reality technology, breaking the limitations of traditional assembly guidance technology which is single in content and boring in way. Object registration is one of the key technologies in augmented assembly guidance process, which can affect the location and direction of virtual assembly guidance information in real assembly environment. Methods This paper presents an object registration method based on RGB-D camera, which combines Lucas-Kanade (LK) optical flow algorithm and Iterative Closet Point (ICP) algorithm. An augmented assembly guidance system for complex products through this method is built. Meanwhile, in order to compare the effectiveness of the proposed method, we also implemented object registration based on an open source augmented reality SDK Vuforia. Results An engine model and a complex weapon cabin equipment are taken as an case to verify this work. The result shows that the registration method proposed in this paper is more accurate and stable compared with that based on Vuforia and the augmented assembly guidance system through this method greatly improves the user's time compared with the traditional assembly. Conclusions Therefore, we can conclude that the object registration method mentioned in this paper can be well applied in the augmented assembly guidance system, which can do enhance the efficiency of assembly considerably.

Image information may be distorted during acquisition, propagation, compression, and storage. Distortion is common in real life, but it affects the subjective experience after acquiring an image. In order to improve the subjective experience, it is necessary to properly evaluate the image quality. This paper discusses image quality assessment without reference. This paper proposes a new method for image quality assessment. In complex scenarios, we deploy multiple critical sensors. We use sensors to get the necessary factors in the environment. After acquiring the feature values, we fuse the acquired information. We propose a multi-feature fusion method based on the Internet of Things to evaluate images. After the information is merged, we get a fused image and use it as a reference image. We converted the no-reference image assessment into a full reference image assessment, and applied the corresponding image assessment method to obtain the corresponding assessment results. In the process of experimental verification, we compare the prediction results with the subjective assessment of the human eye. It can be seen that our method is close to subjective judgment.

Computer vision is a consistent and advanced technique for image processing, with the propitious outcome, and enormous potential. A computer vision has been strongly adopted in the heterogeneous domain including agriculture. During the study of existing research on the role of computer vision in fruits and vegetables among various horticulture products of agriculture fields it is noticed that, the existing survey paper has not focused properly on mathematical framework, feature descriptor, defect detection on multiple datasets of fruits and vegetables elaborately. This has motivated us to undertake an extensive survey. In this paper, we examine the paper broadly related to fruits and vegetables among various horticulture products of agriculture fields, specific model, data pre-processing, data analysis method and overall value of performance accuracy by using a particular performance metric. Moreover, we study the different type of disease present in various fruit and vegetable. We have also focused on the comparison of different machine learning approach with respect to different performance metrics on the same dataset. Thus, we have found that among all existing machine learning techniques SVM give better classification accuracy. A generalized framework to grade the quality and defect detection of multiple fruits and vegetables is also proposed in this survey. This paper covers the survey of ninety-eight papers closely related to computer vision in the agricultural field. By the survey, we have found that computer vision plays an important role and has a large potential to address the challenges related to the agricultural fields.

Hand gestures are quite suitable for space human-robot interaction (SHRI) because of their natural and convenient features. While the detection and localization of hands are the premise and foundation for SHRI based on hand gestures. But hand gestures are very complicated and hand sizes are very small in some images. These problems make the robust real-time hand detection and local- ization very difficult. In this paper, a feature-map-fused single shot multibox detector (FF-SSD) which is a deep learning network is designed to deal with the problems of hand detection and localization in SHRI. First, the background of the method is introduced in this paper, including an astronaut assistant robot platform, the difficulties of hand detection and localization, and introduction of the state-of-the-art deep learning networks for object detection and localiza- tion. Then, the FF-SSD is proposed for detecting and localizing hands especially pony-size hands. This network magentatakes into consideration both accuracy and speed with balanced performance. And in the experiment part, the FF-SSD is trained and tested on hand databases which include a homemade database and two public databases. At last, the superiority of the proposed method is demonstrated compared with the state-of-the-art methods.

In this paper, we address a challenging task in real-word applications, i.e., automatic reading recognition for pointer meters, called PRM. 1 This application is valuable in the fields of military, industry, and aerospace. However, the accuracy of recognizing the readings of pointer meters by machine vision is, oftentimes, affected by several factors, such as uneven illumination in each image, large range variation of illumination in different images, complex backgrounds, tilting of pointer meters, image blur, and scale change, resulting in the recognized readings with unacceptable accuracy. In this paper, a new robust approach to reading recognition of pointer meters is proposed. The proposed method consists of three main contributions: (1) constructing a novel deep learning algorithm in which the PrRoIPooling is used in lieu of the RoiAlign in the existing Mask-RCNN, (2) classifying the type of pointer meters while fitting the pointer binary mask, and (3) calculating the readings of pointer meters by the proposed angle method. In addition, we also report and release a new dataset for the community. Experiments show that the new algorithm can significantly improve the accuracy of the recognized readings of pointer meters, meanwhile, the proposed approach is also robust to the natural environments and computationally efficient.

Iris and face are two most popular biometric traits. Unfortunately, their performance can be degraded when these systems encountered with non-ideal images. The primary motivation of this paper is to analyze the usability of a new feature rich biometric trait known as periocular region (nearby region around the eye) for two different non-ideal scenarios 1) Matching of images with different pose variation and 2) Matching of different side of periocular images (Left eye to Right eye & Right eye to Left eye). In this paper, seven different off-the-shelf deep learning based Convolutional Neural Networks (CNN) using transfer learning approach are implemented on UBIPr database. Experimental results demonstrated that for images with pose variation VGG 19 obtained maximum recognition accuracy while for matching of two different side of periocular region Res Net 18 outperform others. As an additional contribution, a novel approach for the use of mirror images to improve the matching accuracy of two different side of periocular region is also presented.

With the rapid development of Unmanned Aerial Vehicle (UAV), stealth warship and stealth tank, the mission of radar has become more difficult. The modern radar system must detect and track target through strong clutter from many aspect, such as ground and sea. Radar detection for low slow small （LSS）targets has gradually become a new focus. LSS target has a small Radar Cross Section (RCS) because of its small size, making the SNR of the echo signal very low. At the same time, the Doppler frequency of slow target is very low, making it difficult for conventional signal processing methods to separate the Doppler information from the clutter spectrum. Thus, it does make sense to study how to detect the LSS target in strong clutter efficiently. In this paper, the distribution characteristics of radar clutter and coherent accumulation algorithm for LSS target detection in complex electromagnetic environment are studied. On the base of that, a double-threshold target detection method based on coherent accumulation is proposed. To check out the efficiency of the detection method, an experiment has been conducted, and the data collected was used to test the detection algorithm, and the result has been shown in this paper.