Orientation Filter Research Articles

Visual Feature-Guided Diamond Convolutional Network for Finger Vein Recognition.

Finger vein (FV) biometrics have garnered considerable attention due to their inherent non-contact nature and high security, exhibiting tremendous potential in identity authentication and beyond. Nevertheless, challenges pertaining to the scarcity of training data and inconsistent image quality continue to impede the effectiveness of finger vein recognition (FVR) systems. To tackle these challenges, we introduce the visual feature-guided diamond convolutional network (dubbed 'VF-DCN'), a uniquely configured multi-scale and multi-orientation convolutional neural network. The VF-DCN showcases three pivotal innovations: Firstly, it meticulously tunes the convolutional kernels through multi-scale Log-Gabor filters. Secondly, it implements a distinctive diamond-shaped convolutional kernel architecture inspired by human visual perception. This design intelligently allocates more orientational filters to medium scales, which inherently carry richer information. In contrast, at extreme scales, the use of orientational filters is minimized to simulate the natural blurring of objects at extreme focal lengths. Thirdly, the network boasts a deliberate three-layer configuration and fully unsupervised training process, prioritizing simplicity and optimal performance. Extensive experiments are conducted on four FV databases, including MMCBNU_6000, FV_USM, HKPU, and ZSC_FV. The experimental results reveal that VF-DCN achieves remarkable improvement with equal error rates (EERs) of 0.17%, 0.19%, 2.11%, and 0.65%, respectively, and Accuracy Rates (ACC) of 100%, 99.97%, 98.92%, and 99.36%, respectively. These results indicate that, compared with some existing FVR approaches, the proposed VF-DCN not only achieves notable recognition accuracy but also shows fewer number of parameters and lower model complexity. Moreover, VF-DCN exhibits superior robustness across diverse FV databases.

Indirect tuning of a complementary orientation filter using velocity data and a genetic algorithm

In this paper, the accuracy of inertial sensor orientation relative to the level frame is improved through optimal tuning of a complementary filter by a genetic algorithm. While constant filter gains have been used elsewhere, these may introduce errors under dynamic motions when gyroscopes should be trusted more than accelerometers. Optimal gains are prescribed by a Mamdani fuzzy rule base whose membership functions are found using a genetic algorithm and experimental data. Furthermore, model fitness is not based directly on orientation but the error between estimated and ground truth velocities. This paper has three interrelated novel elements. The main novelty is the indirect tuning method, which is simple, low-cost and requires a single camera and inertial sensor. The method is shown to increase tracking accuracy compared with popular baseline filters. Secondary novel elements are the bespoke genetic algorithm and the time agnostic velocity error metric. The contributions from this work can help improve the localization accuracy of assets and human personnel. This research has a direct impact in command and control by improving situational awareness and the ability to direct assets to safe locations using safer routes. This results in increasing safety in applications such as firefighting and battlespace.

IMU/UWB Fusion Method Using a Complementary Filter and a Kalman Filter for Hybrid Upper Limb Motion Estimation.

Motion capture systems have enormously benefited the research into human-computer interaction in the aerospace field. Given the high cost and susceptibility to lighting conditions of optical motion capture systems, as well as considering the drift in IMU sensors, this paper utilizes a fusion approach with low-cost wearable sensors for hybrid upper limb motion tracking. We propose a novel algorithm that combines the fourth-order Runge-Kutta (RK4) Madgwick complementary orientation filter and the Kalman filter for motion estimation through the data fusion of an inertial measurement unit (IMU) and an ultrawideband (UWB). The Madgwick RK4 orientation filter is used to compensate gyroscope drift through the optimal fusion of a magnetic, angular rate, and gravity (MARG) system, without requiring knowledge of noise distribution for implementation. Then, considering the error distribution provided by the UWB system, we employ a Kalman filter to estimate and fuse the UWB measurements to further reduce the drift error. Adopting the cube distribution of four anchors, the drift-free position obtained by the UWB localization Kalman filter is used to fuse the position calculated by IMU. The proposed algorithm has been tested by various movements and has demonstrated an average decrease in the RMSE of 1.2 cm from the IMU method to IMU/UWB fusion method. The experimental results represent the high feasibility and stability of our proposed algorithm for accurately tracking the movements of human upper limbs.

Device Attitude and Real-Time 3D Visualization: An Interface for Elderly Care

Objectivethis paper presents an innovative graphical user interface to visualize the attitude of a sensing device in a three-dimensional space, serving a wide-range of medical applications. Material and methodsbased on inertial measurement units (IMU) or on magnetic, angular rate and gravity (MARG) sensors, a processing unit provides Euler angles using a sensor fusion technique to display the orientation of the device relative to the Earth frame in real-time. The device is schematized by linking six polygonal regions, and is subject to sequential rotations by updating the graph each 350 ms. We conduct comparative studies between the two sensing devices, i.e. IMUs and MARGs, as well as two orientation filters, namely Madgwick's algorithm and Mahony's algorithm. Resultsthe accuracy of the system is reported as a function of (i) the sampling frequency, (ii) the sensing unit, and (iii) the orientation filter, following two elderly care applications, namely fall risk assessment and body posture monitoring. The experiments are conducted using public datasets. The corresponding results show that Madgwick's algorithm is best suited for low sampling rates, whereas MARG sensors are best suited for the detection of postural transitions. Conclusionthis paper addresses the different aspects and discusses the limitations of attitude estimation systems, which are important tools to help clinicians in their diagnosis.

Quantification of Error Sources with Inertial Measurement Units in Sports.

Inertial measurement units (IMUs) offer the possibility to capture the lower body motions of players of outdoor team sports. However, various sources of error are present when using IMUs: the definition of the body frames, the soft tissue artefact (STA) and the orientation filter. Methods to minimize these errors are currently being used without knowing their exact influence on the various sources of errors. The goal of this study was to present a method to quantify each of the sources of error of an IMU separately. An optoelectronic system was used as a gold standard. Rigid marker clusters (RMCs) were designed to construct a rigid connection between the IMU and four markers. This allowed for the separate quantification of each of the sources of error. Ten subjects performed nine different football-specific movements, varying both in the type of movement, and in movement intensity. The error of the definition of the body frames (11.3-18.7 deg RMSD), the STA (3.8-9.1 deg RMSD) and the error of the orientation filter (3.0-12.7 deg RMSD) were all quantified separately for each body segment. The error sources of IMU-based motion analysis were quantified separately. This allows future studies to quantify and optimize the effects of error reduction techniques.

A Fast Circle Detection Algorithm Based on Information Compression.

Circle detection is a fundamental problem in computer vision. However, conventional circle detection algorithms are usually time-consuming and sensitive to noise. In order to solve these shortcomings, we propose a fast circle detection algorithm based on information compression. First, we introduce the idea of information compression, which compresses the circular information on the image into a small number of points while removing some of the noise through sharpness estimation and orientation filtering. Then, the circle parameters stored in the information point are obtained by the average sampling algorithm with a time complexity of to obtain candidate circles. Finally, we set different constraints on the complete circle and the defective circle according to the sampling results and find the true circle from the candidate circles. The experimental results on the three datasets show that our method can compress the circular information in the image into 1% of the information points, and compared to RHT, RCD, Jiang, Wang and CACD, Precision, Recall, Time and F-measure are greatly improved.

A Segmentation Process to Isolate Various Cytological Components from Follicular Histology based on Texture Heterogeneity

Abstract: This research looks at an H&E-stained Follicular Lymphoma tissue sample in order to isolate different cytological components based on textural heterogeneity. The goal of this study is to determine the morphological behavior of various cytological components such as nuclei, cytoplasm, extracellular material, and red blood cells so that oncologists can make better decisions and provide appropriate treatment during the prognosis of histopathological images that are sometimes incorrectly concluded. To isolate these cytological components, a convolution process is applied to follicular histology and 8 different oriented masks produced from the gabor filter, yielding 8 separate representations for each of the 8 various orientation masks of H&E-stained FL histology. The information included in the 8 representations resulting from the application of the gaussian filter is summarized in twelve images that correspond to each of the filter's orientations. Second, the operation of concatenation is carried out over these 8 separate representations into a single 3-dimensional covariance image. The projected approach outperforms grey level-based texture analysis in FL histology, according to the results.

Scalable Growth of Organic Single‐Crystal Films via an Orientation Filter Funnel for High‐Performance Transistors with Excellent Uniformity

Organic single-crystal films (OSCFs) provide an unprecedented opportunity for the development of new-generation organic single-crystal electronics. However, crystallization of organic films is normally governed by stochastic nucleation and incoherent growth, posing a formidable challenge to grow large-sized OSCFs. Here, an "orientation filter funnel" concept is presented for the scalable growth of OSCFs with well-aligned, singly orientated crystals. By rationally designing solvent wetting/dewetting patterns on the substrate, this approach can produce seed crystals with the same crystallographic orientation and then maintain epitaxial growth of these crystals, enabling the formation of large-area OSCFs. As a result, this unique concept for crystal growth not only enhances the average mobility of organic film by 4.5-fold but also improves its uniformity of electrical properties, with a low mobility variable coefficient of 9.8%, the new lowest record among organic devices. The method offers a general and scalable route to produce OSCFs toward real-word electronic applications.

Inertial Measurement of Head Tilt in Rodents: Principles and Applications to Vestibular Research.

Inertial sensors are increasingly used in rodent research, in particular for estimating head orientation relative to gravity, or head tilt. Despite this growing interest, the accuracy of tilt estimates computed from rodent head inertial data has never been assessed. Using readily available inertial measurement units mounted onto the head of freely moving rats, we benchmarked a set of tilt estimation methods against concurrent 3D optical motion capture. We show that, while low-pass filtered head acceleration signals only provided reliable tilt estimates in static conditions, sensor calibration combined with an appropriate choice of orientation filter and parameters could yield average tilt estimation errors below during movement. We then illustrate an application of inertial head tilt measurements in a preclinical rat model of unilateral vestibular lesion and propose a set of metrics describing the severity of associated postural and motor symptoms and the time course of recovery. We conclude that headborne inertial sensors are an attractive tool for quantitative rodent behavioral analysis in general and for the study of vestibulo-postural functions in particular.

IMU-based knee flexion, abduction and internal rotation estimation during drop landing and cutting tasks

Anterior cruciate ligament (ACL) injury is a common and severe knee injury in sports. Knee flexion, abduction and internal rotation angles are considered crucial biomechanical indicators of the ACL injury risk but currently are computed in a laboratory with an optical motion capture. This paper introduces an inertial measurement unit (IMU) based algorithm for knee flexion, abduction and internal rotation estimation during ACL injury risk assessment tests, including drop landing and cutting tasks. This algorithm includes a special two-step complementary-based orientation filter and a special single-pose sensor-to-segment calibration procedure. Fourteen healthy subjects performed double-leg, single-leg drop landing and cutting tasks. Each subject wore four IMUs and reflective marker clusters on their thighs and shanks. For the presented knee angles algorithm with an empirical initial segment orientation, the root mean square errors (RMSEs) of the estimated continuous knee flexion, abduction and internal rotation cross all the movement tasks were 1.07°, 2.87° and 2.64°, and RMSEs of the peak knee flexion and peak knee abduction errors were 1.22° and 3.82°. The knee angles algorithm was capable of estimating knee abduction and internal rotation angles during drop landing and cutting tasks, and knee flexion estimation was substantially more accurate than previously reported approaches. Additionally, we found that for the presented algorithm, the accuracy of initial segment orientation was a critical factor for knee abduction and internal rotation estimations. The presented IMU-based knee angles algorithm could serve as a foundation to enable in-field biomechanical ACL injury risk assessment.

Efficient Attitude Estimators: A Tutorial and Survey

Inertial sensors based on micro-electro-mechanical systems (MEMS) technology, such as accelerometers and angular rate sensors, are cost-effective solutions used in inertial navigation systems in a broad spectrum of applications that estimate position, velocity and orientation of a system with respect to an inertial reference frame. Although they present several advantages in terms of cost and form factor, they are prone to various disturbances such as noise, biases, and random walk that degrade their orientation estimation. The task of an orientation filter is to compute an optimal solution for the attitude state, consisting of roll, pitch and yaw, through the fusion of angular rate, accelerometer, and magnetometer measurements, regardless of the underlying environmental constraints. The aim of this paper is threefold: first, it serves researchers and practitioners in the signal processing community seeking the most appropriate attitude estimators that fulfills their needs, shedding light on the drawbacks and the advantages of a wide variety of designs. Second, it serves as a survey and tutorial for existing estimator designs in the literature, assessing their design aspects and components, and dissecting their hidden details for the benefit of researchers. Third, a comprehensive list of algorithms is discussed for a fully functional inertial navigation system, starting from the navigation equations and ending with the filter equations, keeping in mind their suitability for power-limited embedded processors. The source code of all algorithms is published, with the aim of it being an out-of-box solution for researchers in the field. The reader will take away the following concepts from this article: understand the key concepts of an inertial navigation system; be able to implement and test a complete stand alone solution; be able to evaluate and understand different algorithms; understand the trade-offs between different filter architectures and techniques; and understand efficient embedded processing techniques, trends and opportunities.

Location-Based Saliency Maps from a Fully Connected Layer using Multi-Shapes

Recently, with the development of technology, computer vision research based on the human visual system has been actively conducted. Saliency maps have been used to highlight areas that are visually interesting within the image, but they can suffer from low performance due to external factors, such as an indistinct background or light source. In this study, existing color, brightness, and contrast feature maps are subjected to multiple shape and orientation filters and then connected to a fully connected layer to determine pixel intensities within the image based on location-based weights. The proposed method demonstrates better performance in separating the background from the area of interest in terms of color and brightness in the presence of external elements and noise. Location-based weight normalization is also effective in removing pixels with high intensity that are outside of the image or in non-interest regions. Our proposed method also demonstrates that multi-filter normalization can be processed faster using parallel processing.

A Sensor Fusion Approach to the Estimation of Instantaneous Velocity Using Single Wearable Sensor During Sprint.

Power-Force-Velocity profile obtained during a sprint test is crucial for designing personalized training and evaluating injury risks. Estimation of instantaneous velocity is requisite for developing these profiles and the predominant method for this estimation assumes it to have a first order exponential behavior. While this method remains appropriate for maximal sprints, the sprint velocity profile may not always show a first-order exponential behavior. Alternately, velocity profile has been estimated using inertial sensors, with a speed radar, or a smartphone application. Existing methods either relied on the exponential behavior or timing gates for drift removal, or estimated only the mean velocity. Thus, there is a need for a more flexible and appropriate approach, allowing for instantaneous velocity estimation during sprint tests. The proposed method aims to solve this problem using a sensor fusion approach, by combining the signals from wearable Global Navigation Satellite System (GNSS) and inertial measurement unit (IMU) sensors. We collected data from nine elite sprinters, equipped with a wearable GNSS-IMU sensor, who ran two trials each of 60 and 30/40 m sprints. We developed an algorithm using a gradient descent-based orientation filter, which simplified our model to a linear one-dimensional model, thus allowing us to use a simple Kalman filter (KF) for velocity estimation. We used two cascaded KFs, to segment the sprint data precisely, and to estimate the velocity and the sprint duration, respectively. We validated the estimated velocity and duration with speed radar and photocell data as reference. The median RMS error for the estimated velocity ranged from 6 to 8%, while that for the estimated sprint duration lied between 0.1 and −6.0%. The Bland–Altman plot showed close agreement between the estimated and the reference values of maximum velocity. Examination of fitting errors indicated a second order exponential behavior for the sprint velocity profile, unlike the first order behavior previously suggested in literature. The proposed sensor-fusion algorithm is valid to compute an accurate velocity profile with respect to the radar; it can compensate for and improve upon the accuracy of the individual IMU and GNSS velocities. This method thus enables the use of wearable sensors in the analysis of sprint test.

Improving EBSD precision by orientation refinement with full pattern matching.

We present a comparison of the precision of different approaches for orientation imaging using electron backscatter diffraction (EBSD) in the scanning electron microscope. We have used EBSD to image the internal structure of WC grains, which contain features due to dislocations and subgrains. We compare the conventional, Hough-transform based orientation results from the EBSD system software with results of a high-precision orientation refinement using simulated pattern matching at the full available detector resolution of 640 × 480 pixels. Electron channelling contrast imaging (ECCI) is used to verify the correspondence of qualitative ECCI features with the quantitative orientation data from pattern matching. For the investigated sample, this leads to an estimated pattern matching sensitivity of about 0.5 mrad (0.03°) and a spatial feature resolution of about 100 nm. In order to investigate the alternative approach of postprocessing noisy orientation data, we analyse the effects of two different types of orientation filters. Using reference features in the high-precision pattern matching results for comparison, we find that denoising of orientation data can reduce the spatial resolution, and can lead to the creation of orientation artefacts for crystallographic features near the spatial and orientational resolution limits of EBSD.

Image Transformation based Defense Against Adversarial Perturbation on Deep Learning Models

Deep learning algorithms provide state-of-the-art results on a multitude of applications. However, it is also well established that they are highly vulnerable to adversarial perturbations. It is often believed that the solution to this vulnerability of deep learning systems must come from deep networks only. Contrary to this common understanding, in this article, we propose a non-deep learning approach that searches over a set of well-known image transforms such as Discrete Wavelet Transform and Discrete Sine Transform, and classifying the features with a support vector machine-based classifier. Existing deep networks-based defense have been proven ineffective against sophisticated adversaries, whereas image transformation-based solution makes a strong defense because of the non-differential nature, multiscale, and orientation filtering. The proposed approach, which combines the outputs of two transforms, efficiently generalizes across databases as well as different unseen attacks and combinations of both (i.e., cross-database and unseen noise generation CNN model). The proposed algorithm is evaluated on large scale databases, including object database (validation set of ImageNet) and face recognition (MBGC) database. The proposed detection algorithm yields at-least 84.2% and 80.1% detection accuracy under seen and unseen database test settings, respectively. Besides, we also show how the impact of the adversarial perturbation can be neutralized using a wavelet decomposition-based filtering method of denoising. The mitigation results with different perturbation methods on several image databases demonstrate the effectiveness of the proposed method.

Fast and Efficient Facial Expression Recognition Using a Gabor Convolutional Network

Automatic facial expression recognition (FER) is a fundamental topic in computer vision. Many studies have indicated that facial emotion changes are strongly related to certain regions of interest (ROIs), such as the mouth, eyes, eyebrows, and nose; therefore, the features of these facial ROIs are very important for identifying expressions. Since Gabor filters are very efficient in extracting visual content, Gabor orientation filters (GoFs) modulated by Gabor kernels and traditional convolutional filters can capture such ROI information better than conventional convolutional filters. Consequently, this letter presents a light Gabor convolutional network (GCN) consisting of only four Gabor convolutional layers and two linear layers for FER tasks. Extensive experiments on the FER2013, FERPlus and Real-world Affective Faces (RAF) databases demonstrate that the proposed method achieves good recognition accuracy and requires very low computational costs. The source code can be found at https://github.com/general515/Facial_Expression_Recognition_Using _GCN.

Real-Time Infrastructureless Indoor Tracking for Pedestrian Using a Smartphone

Demands for accurate pedestrian indoor tracking on mobile platforms have been increasing rapidly these years, however, conventional tracking system based on dead reckoning suffers from inherent sensor drift, which leads to bad performance in long-term tracking. In this paper, an infrastructureless pedestrian dead reckoning system called iPDR is proposed and implemented on a ready-to-use smartphone, offering real-time indoor tracking for pedestrian without previous knowledge of the target area. The iPDR fuses the sensor data using a novel filter approach coined as hybrid orientation filter, which deploys a combination of the information filter and the complementary filter to achieve accurate heading estimation. A fast loop closure detection method called rapid loop detection is also presented in the iPDR to calibrate the tracking trajectory significantly whenever encountering a loop. Experiment results show that the iPDR system achieves typically sub-meter accuracy in localization and has an average orientation error of 2.89 degrees over a total turning of 1800 degrees.

Identification of fractured-basement reservoir based on integration of FMI Log and seismic attributes in hydrocarbon field “I”, Barito Basin, South Kalimantan

As basement has very small matrix porosity, secondary porosity is needed to store hydrocarbon within the basement. Fracture is a secondary porosity, yet not all fracture can be a good secondary porosity. Open fractures have capability to store hydrocabon, also have important roles in productivity and quality of the pre-tertiary basement reservoir. This study is aimed to identify open fractures using FMI log and seismic attributes in the Field “I”, Barito Basin. Interpreted image log (FMI) on two wells gives the azimuth and dip orientation of open fractures are ENE –WSW, NNW-SSE and WNW-ESE and also the horizontal stress orientation. The stress orientation from image log combined with leak-off test (LOT) data and density log used to identify stress fields. Azimuth and dip orientation of the open fracture from FMI log is the input of the stereonet, as an orientation filter for ant-tracking. Ant-track attribute is based on ant-colony optimization algorithm that captures only continuous features and used as edge enhancement methods for fracture-sensitive attributes. Variance is a fracture-sensitive attribute that applied as input data for ant-track algorithm. The results of ant-track map are well correlated and confirmed by image log analysis. Also, by applying ant-track attribute to the fracture-sensitive attributes succesfully able to identify faults and fractures with better resolution and visualization than only using the fracture-sensitive attribute itself, so it makes easier to interpret and get the information.

Orientation Information in Encoding Facial Expressions for People With Central Vision Loss.

PurposePatients with central vision loss face daily challenges on performing various visual tasks. Categorizing facial expressions is one of the essential daily activities. The knowledge of what visual information is crucial for facial expression categorization is important to the understanding of the functional performance of these patients. Here we asked how the performance for categorizing facial expressions depends on the spatial information along different orientations for patients with central vision loss.MethodsEight observers with central vision loss and five age-matched normally sighted observers categorized face images into four expressions: angry, fearful, happy, and sad. An orientation filter (bandwidth = 23°) was applied to restrict the spatial information within the face images, with the center of the filter ranged from horizontal (0°) to 150° in steps of 30°. Face images without filtering were also tested.ResultsWhen the stimulus visibility was matched, observers with central vision loss categorized facial expressions just as well as their normally sighted counterparts, and showed similar confusion and bias patterns. For all four expressions, performance (normalized d′), uncorrelated with any of the observers' visual characteristics, peaked between −30° and 30° filter orientations and declined systematically as the filter orientation approached vertical (90°). Like normally sighted observers, observers with central vision loss also relied mainly on mouth and eye regions to categorize facial expressions.ConclusionsSimilar to people with normal vision, people with central vision loss rely primarily on the spatial information around the horizontal orientation, in particular the regions around the mouth and eyes, for recognizing facial expressions.

Hybrid visual natural landmark–based localization for indoor mobile robots

Localization is a crucial part of autonomous moving for the indoor mobile robot. The natural features of the ceiling and surrounding environment can serve for position estimation. Based on these natural features, a hybrid visual natural landmarks–based localization method is proposed. We combine the landmarks-based positioning with ceiling-based visual odometry. During the visual odometry, the orientation is computed from the parallel features between the adjacent frames. The position is calculated from the corresponding point features in the two consecutive images using the perspective-n-point method. During the natural landmarks–based localization, the orientation filter is utilized to obtain the global orientation. Then, the feature points are determined by the Compute Unified Device Architecture–based scale-invariant feature transform algorithm. Finally, the position is estimated based on the computed orientation and point features. Various experiments have been conducted to evaluate the effectiveness of the proposed method. The experimental results show that the proposed localization method outperforms other methods in accuracy and efficiency.