Template Matching Algorithm Research Articles

Detection of Vehicles Number Plate Using Image Processing with Template matching Method

To design a system in order to identify an object number plate for the Indonesian format, an initial system is designed, in the form of a vehicle licence plate recognition application using template matching method. The goal of this application is to be implemented to the parking system by identifying the number plate. This system uses the camera for the image capture process, by utilizing image processing technology with the matching correlation template method for recognition to produce a string value from the image. Before doing recognition process, First, the pre processing stage is performed on the input image which includes grayscale, binary, until the segmentation stage before the correlation / comparison process is carried out on the image of Template. The process that occure in the pre-processing unit done for some reason including to make the image lighter and less complex. This process will make the image easer to be processed and also to increase the proses speed of the system. Before aply template matching algorithm to the image output from segmentation process, the image has to be resized first to match the size of the template image stored in data base. This has to done so that the target image and the template image can be match directly with template matching algorithm. The output of this system is a string value which is refer to the value of the license plate capture by camera used by the system. The problem that arises in the introduction process is how to identify various types of characters with various sizes and shapes so that the string value is the same as the text image. The average success rate of this application is 70% so that further research must be carried out so this system can be implemented into the parking system.
 Keyword : Image Processing, Template matching, Camera, Number Plate, Matlab

MRI artifact simulation for clinically relevant MRI sequences for guidance of prostate HDR brachytherapy

For the purpose of magnetic resonance imaging (MRI) guidance of prostate high-dose-rate (HDR) brachytherapy, this paper presents a study on the potential of clinically relevant MRI sequences to facilitate tracking or localization of brachytherapy devices (HDR source/titanium needle), and which could simultaneously be used to visualize the anatomy. The tracking or localization involves simulation of the MRI artifact in combination with a template matching algorithm. Simulations of the MRI artifacts induced by an HDR brachytherapy source and a titanium needle were implemented for four types of sequences: spoiled gradient echo, spin echo, balanced steady-state free precession (bSSFP) and bSSFP with spectral attenuated inversion recovery (SPAIR) fat suppression. A phantom study was conducted in which mentioned sequences (in 2D) as well as the volumetric MRI sequences of the current clinical scan protocol were applied to obtain the induced MRI artifacts for an HDR source and a titanium needle. Localization of the objects was performed by a phase correlation based template matching algorithm. The simulated images demonstrated high correspondences with the acquired MR images, and allowed localization of the objects. A comparison between the object positions obtained for all applied MRI sequences showed deviations (from the average position) of 0.2–0.3 mm, proving that all MRI sequences were suitable for localization of the objects, irrespective of their 2D or volumetric nature. This study demonstrated that the MRI artifact induced by an HDR source or a titanium needle could be simulated for the four investigated types of MRI sequences (spoiled gradient echo, spin echo, bSSFP and bSSFP-SPAIR), valuable for real-time object localization in clinical practice. This leads to more flexibility in the choice of MRI sequences for guidance of HDR brachytherapy, as they are suitable for both object localization and anatomy visualization.

Searching for hidden earthquakes in Southern California.

Earthquakes follow a well-known power-law size relation, with smaller events occurring much more often than larger events. Earthquake catalogs are thus dominated by small earthquakes yet are still missing a much larger number of even smaller events because of signal fidelity issues. To overcome these limitations, we applied a template-matching detection technique to the entire waveform archive of the regional seismic network in Southern California. This effort resulted in a catalog with 1.81 million earthquakes, a 10-fold increase, which provides important insights into the geometry of fault zones at depth, foreshock behavior and nucleation processes, and earthquake-triggering mechanisms. The rich detail resolved in this type of catalog will facilitate the next generation of analyses of earthquakes and faults.

Video-Based Driver’s Hand Tracking using Fast Normalized Cross Coefficient with Improved Computational Efficiency

Driver distraction is one of the major causes for fatal car accidents. In a distracting activity, manual distraction is a triggered response of other types of distraction, such as cognitive and visual distraction. Therefore, recognition of manual distraction can contribute to the monitoring of overall drivers’ distraction. In this study, a computer vision-based method to track hand movement from the recorded driving behavior is proposed. This method integrates a low computational cost template matching algorithm using fast normalized cross coefficient (NCC) and a novel searching strategy. The proposed method was evaluated by the VIVA hand tracking data set. It achieves 50.83% of marginal accuracy percentage (mAP), 42.18% of multiple object tracking accuracy (MOTA), 31.56% of mostly tracked (MT), and 19.29% of mostly lost (ML), and it outperformed a state of the art algorithm in MOTA and MT. Additionally, the computational cost of the proposed method is greatly improved, and it can run at around 11.1 frames per second. The outcome of this research will further assist driving distraction recognition and mitigation, and improve driving safety.

Kernel Hilbert space template-matching techniques for simultaneous determination of neutron source location and identity with a volumetrically-sensitive moderating-type neutron spectrometer

Hand-held instrumentation that can provide real-time information regarding the location and identity (i.e., type/radioisotope and local surrounding/shielding) of neutron radiation sources, via free neutron measurements alone, are of interest to non-proliferation, water/oil-exploration and related neutron scattering applications. In a previous report, template-matching techniques in two- and three-spatial dimensions were introduced as methods for simultaneously determining the horizontal-planar location and the identity of neutron radiation sources with a new class of volumetrically-sensitive moderating-type neutron spectrometer . Although these methods were shown to be quite promising for this new class of instrumentation, there are three significant factors that negatively affect their performance in practice: (1) there are a large number of templates of interest for most practical applications; (2) many of these templates are very similar (i.e., highly correlated or strongly degenerate); and, (3) the measurement data is superposed with environmental neutron scattering effects. In this work, kernel Hilbert space transformations, that have been proposed to solve analogous problems in digital image processing applications, are employed to overcome the aforementioned difficulties encountered when analyzing spectroscopic neutron radiation measurements via template-matching techniques, and a novel kernel Hilbert space template-matching algorithm is introduced. Four variants of this improved technique are tested and compared via MCNP6 simulation for efficacy of localization and identification of neutron radiation sources with this new class of neutron spectrometer.

Ranging Method of Binocular Stereo Vision Based on Random Ferns and NCC Template Matching

As an important research direction in the field of computer vision, binocular stereo vision has important application value for the reconstruction of scene 3D geometric information. A fast and accurate binocular vision target ranging method is proposed. Firstly, the random fern algorithm is used to accurately and quickly detect the left image target area to obtain the target center point. Then the NCC template matching algorithm is used to find the matching point in the right image. Finally, the two-dimensional coordinates of the matching point pairs of center point is used to calculate the distance between the target and the camera. The simulation results show that the ranging scheme can accurately measure the target distance within a certain distance range, and can achieve fast and effective target ranging.

Face detection and tracking using hybrid margin-based ROI techniques

This study is to solve the problem of low accuracy and slow processing speed for real-time face detection and tracking systems. A margin-based region of interest approach with fixed and dynamic margin concepts is proposed to speed up the processing time. In addition, a hybrid system is developed to boost the accuracy and overcome the deficiency of the main detection algorithm. This approach consists of two routines, i.e., main and escape routines. Three algorithms are used independently as the main routine to evaluate the effectiveness of the proposed hybrid approach. These algorithms are Haar cascade, Joint cascade, and multitask convolutional neural networks. The escape routine based on template matching algorithm is designed to evaluate the effectiveness of the proposed hybrid approach and improve detection accuracy. Two RGB video datasets with diversity and variations in face poses, video backgrounds, illuminations, video resolutions, expressions, over exposed faces, and occlusions of people within various unseen environments have been used for experiments and evaluation. The experiment results confirm that the hybrid approach is capable of detecting and tracking faces in non-frontal orientation with better accuracy and faster processing speed, i.e., four times faster than the conventional full frame scanning techniques.

Detection of fallen logs from high-resolution UAV images

Background: High-resolution images from unmanned aerial vehicles (UAVs) can be used to describe the state of forests at regular time periods in a cost-effective manner. The purpose of this study was to assess the performance of a line template matching algorithm, the Hough transformation, for detecting fallen logs from UAV-based high-resolution RGB images. The suggested methodology does not aim to replace any known aerial method for log detection, rather it is more oriented to the detection of fallen logs in open forest stands with a high percentage of log visibility and straightness.
 Methods: This study describes a line template matching algorithm that can be used for the detection of fallen logs in an automated process. The detection technique was based on object-based image analysis, using both pixel-based and shape descriptors. To determine the actual number of fallen logs, and to compare with the ones predicted by the algorithm, manual visual assessment was used based on six high-resolution orthorectified images. To evaluate if a line matched, we used a voting scheme. The total number of detected fallen logs compared with the actual number of fallen logs based on several accuracy metrics. To evaluate predictive models we tested the cross-validation mean error. Finally, to test how close our results were to chance, we used the Cohen`s Kappa coefficient.
 Results: The detection algorithm found 136 linear objects, of which 92 of them were detected as fallen logs. From the 92 detected fallen logs, 86 were correctly predicted by the algorithm and 24 were falsely detected as fallen logs. The calculated amount of observed agreement was equal to 0.78, whereas the expected agreement by chance was 0.61. Finally, the kappa statistic was 0.44.
 Conclusions: Our methodology had high reliability for detecting fallen logs based on total user‘s accuracy (94.9%), whereas a Kappa of 0.44 indicated there was good agreement between the observed and predicted values. Also, the cross-validation analysis denoted the efficiency of the proposed method with an average error of 16%.

Comparative Study of Tiger Identification Using Template Matching Approach based on Edge Patterns

The presence of tigers in residential areas as predators was a threat to humans and their livestock. Through digital image processing, these animals could be identified by matching line patterns on the skin as a characteristic of the tiger using the template matching method, namely comparing the similarities between the lines pattern in the reference image with the main image. However, the presence of plant leaves and shrubs with various shapes could disguise tiger skin line patterns so that it could affect the accuracy of identification results. In this paper, we conducted a comparative study to identify tigers based on edge lines which were then processed using three edge detection method namely Canny, Laplacian and Sobel. The results of each operator were further processed using template matching algorithm to get the accuracy of object identification (tiger).

Fully Automated R-peak Detection Algorithm (FLORA) for fetal magnetoencephalographic data

Background and Objective: Fetal magnetoencephalography (fMEG) is a method for recording fetal brain signals, fetal and maternal heart activity simultaneously. The identification of the R-peaks of the heartbeats forms the basis for later heart rate (HR) and heart rate variability (HRV) analysis. The current procedure for the evaluation of fetal magnetocardiograms (fMCG) is either semi-automated evaluation using template matching (SATM) or Hilbert transformation algorithm (HTA). However, none of the methods available at present works reliable for all datasets.Methods: Our aim was to develop a unitary, responsive and fully automated R-peak detection algorithm (FLORA) that combines and enhances both of the methods used up to now.Results: The evaluation of all methods on 55 datasets verifies that FLORA outperforms both of these methods as well as a combination of the two, which applies in particular to data of fetuses at earlier gestational age.Conclusion: The combined analysis shows that FLORA is capable of providing good, stable and reproducible results without manual intervention.

Visualization of spatial distribution of the droplet size and velocity in flash boiling spray with extended glare-point imaging technique

Flash boiling is an effective way to improve the atomization quality. Droplet diameter and velocity distribution of the flash boiling spray extremely impact the mixture formation of direct injection engines. We visualize and measure the spatial distribution of the droplet size and velocity of flash boiling spray with extended glare-point imaging technique in this paper. An improved correlation-based processing algorithm for droplet identification is proposed. The algorithm is capable of identifying the droplet positions and sizes as well as tracking and matching of the droplet displacement vectors. The employed template matching algorithm using serial particle mask and the centroid method provide higher accuracy for estimating the droplet displacement, and the cross-correlation matching algorithm and the two-frame particle tracking algorithm further ensure higher matching rates for the droplet pairs. The performance of the algorithm is well validated by simulations. Furthermore, the method is applied for the experimental study of flash boiling spray with extended glare-point imaging technique in combination with particle tracking velocimetry for measuring the particle size and velocity with higher accuracy, the results of which provides improved understanding of the flash boiling spray formation mechanism.

ELPHA: Dynamically deformable liver phantom for real-time motion-adaptive radiotherapy treatments.

Real-time motion-adaptive radiotherapy of intrahepatic tumors needs to account for motion and deformations of the liver and the target location within. Phantoms representative of anatomical deformations are required to investigate and improve dynamic treatments. A deformable phantom capable of testing motion detection and motion mitigation techniques is presented here. The dynamically dEformable Liver PHAntom (ELPHA) was designed to fulfill three main constraints: First, a reproducibly deformable anatomy is required. Second, the phantom should provide multimodality imaging contrast for motion detection. Third, a time-resolved dosimetry system to measure temporal effects should be provided. An artificial liver with vasculature was casted from soft silicone mixtures. The silicones allow for deformation and radiographic image contrast, while added cellulose provides ultrasonic contrast. An actuator was used for compressing the liver in the inferior direction according to a prescribed respiratory motion trace. Electromagnetic (EM) transponders integrated in ELPHA help provide ground truth motion traces. They were used to quantify the motion reproducibility of the phantom and to validate motion detection based on ultrasound imaging. A two-dimensional ultrasound probe was used to follow the position of the vessels with a template-matching algorithm. This detected vessel motion was compared to the EM transponder signal by calculating the root-mean-square error (RMSE). ELPHA was then used to investigate the dose deposition of dynamic treatment deliveries. Two dosimetry systems, radio-chromic film and plastic scintillation dosimeters (PSD), were integrated in ELPHA. The PSD allow for time-resolved measurement of the delivered dose, which was compared to a time-resolved dose of the treatment planning system. Film and PSD were used to investigate dose delivery to the deforming phantom without motion compensation and with treatment-couch tracking for motion compensation. ELPHA showed densities of 66 and 45HU in the liver and the surrounding tissues. A high motion reproducibility with a submillimeter RMSE (<0.32mm) was measured. The motion of the vasculature detected with ultrasound agreed well with the EM transponder position (RMSE<1mm). A time-resolved dosimetry system with a 1Hz time resolution was achieved with the PSD. The agreement of the planned and measured dose to the PSD decreased with increasing motion amplitude: A dosimetric RMSE of 1.2, 2.1, and 2.7cGy/s was measured for motion amplitudes of 8, 16, and 24mm, respectively. With couch tracking as motion compensation, these values decreased to 1.1, 1.4, and 1.4cGy/s. This is closer to the static situation with 0.7cGy/s. Film measurements showed that couch tracking was able to compensate for motion with a mean target dose within 5% of the static situation (-5% to +1%), which was higher than in the uncompensated cases (-41% to -1%). ELPHA is a deformable liver phantom with high motion reproducibility. It was demonstrated to be suitable for the verification of motion detection and motion mitigation modalities. Based on the multimodality image contrast, a high accuracy of ultrasound based motion detection was shown. With the time-resolved dosimetry system, ELPHA is suitable for performance assessment of real-time motion-adaptive radiotherapy, as was shown exemplary with couch tracking.

Detection of Fetal ECG R Wave From Single-Lead Abdominal ECG Using a Combination of RR Time-Series Smoothing and Template-Matching Approach

Fetal electrocardiograph (fECG) R-wave detection from maternal abdominal ECGs (aECGs) is challenging as it is easily distorted and often overwhelmed by a variety of unavoidable interference signals. In this study, we combined RR time-series smoothing with a template-matching (TM) approach to detect fECG R waves from a single-lead aECG. According to the quasi-periodicity of the R wave, we analyzed the cases of misaligned and missed R wave detection in the RR time series and developed an amendment algorithm to distinguish and correct them. The fECG R wave detection consists of two stages. First, an fECG R wave, which did not overlap with the maternal ECG QRS complex (mQRS), was detected. Subsequently, the amendment algorithm corrected the misaligned and missed R waves and predicted the approximate region of the fECG R wave that overlapped with the mQRS. A TM algorithm was implemented to detect the fECG R wave that overlapped with the mQRS in the approximate region. The fECG QRS complex (fQRS) and mQRS templates were built from the detected fQRS and mQRS that did not overlap with the fQRS, respectively, using singular value decomposition. The TM algorithm then determined the accurate location when the most optimal correlation occurred between the actual mQRS and the superposition of the mQRS and fQRS templates in the approximate region. The performance of the proposed method was assessed using F1 measure and Bland-Altman analysis. High accuracy values were obtained corresponding to 95% and -0.04±9.00 ms, respectively. The proposed method was therefore considered to enhance accurate extraction of the fECG R wave in both the clinical and commercial applications.

Organic Multi-Channel Optoelectronic Sensors for Wearable Health Monitoring

Recent progress in printed optoelectronics and their integration in wearable sensors have created new avenues for research in reflectance photoplethysmography (PPG) and oximetry. The reflection-mode sensor, which consists of light emitters and detectors, is a vital component of reflectance oximeters. Here, we report a systematic study of the reflectance oximeter sensor design in terms of component geometry, light emitter and detector spacing, and the use of an optical barrier between the emitter and the detector to maximize sensor performance. Printed red and near-infrared (NIR) organic light-emitting diodes (OLEDs) and organic photodiodes (OPDs) are used to design three sensor geometries: (1) Rectangular geometry, where square OLEDs are placed at each side of the OPD; (2) Bracket geometry, where the OLEDs are shaped as brackets and placed around the square OPD; (3) Circular geometry, where the OLEDs are shaped as block arcs and placed around the circular OPD. Utilizing the bracket geometry, we observe 39.7% and 18.2% improvement in PPG signal magnitude in the red and NIR channels compared to the rectangular geometry, respectively. Using the circular geometry, we observe 48.6% and 9.2% improvements in the red and NIR channels compared to the rectangular geometry. Furthermore, a wearable two-channel PPG sensor is utilized to add redundancy to the measurement. Finally, inverse-variance weighting and template matching algorithms are implemented to improve the detection of heart rate from the multi-channel PPG signals.

Identification of Tropical Cyclone Centers in SAR Imagery Based on Template Matching and Particle Swarm Optimization Algorithms

Synthetic aperture radar (SAR) has emerged as a new tool for tropical cyclone (TC) monitoring by providing information on the location of TC centers. However, SAR does not usually cover the entire TC domain due to its limited swath width. In this paper, we develop a procedure to identify the location of the center of a TC when an SAR image only covers the rain band portion of the TC but not the eye. The algorithm is based on both an image processing procedure and the available knowledge of the inherent rain-band structure of a TC. The three-step algorithm includes: 1) applying a Canny edge detector to find the curves associated with rain bands; 2) defining two filter criteria to select the spiral curves that resemble the estimation based on a TC rain-band model; 3) searching for the optimal matching solution using the particle swarm optimization algorithm. Numerical experiments with images without TC eye information show that the proposed method can effectively locate the centers of TCs. We compare the experimental results with the best track data to indicate the accuracy. Then, we compare the inflow angle model and the logarithmic spiral model and find that the inflow angle model is more accurate for TC center identification.

A Novel Multi-Sensor Image Matching Algorithm Based on Adaptive Multiscale Structure Orientation

Automatic and reliable multi-sensor image matching is a very challenging task due to the significant nonlinear radiometric differences between multi-sensor images. In this paper, a novel dense descriptor based on adaptive multiscale structure orientation is proposed for capturing the geometrical structure information of an image. The dense descriptor of the proposed matching algorithm is not only illumination and contrast invariant but also robust against the image noise. Further, an improved similarity measurement is introduced for adapting the orientation reversal caused by the intensity inversion between multi-sensor images. Based on the robust dense descriptor and the improved similarity measurement, we developed a novel and practical template matching algorithm to match multi-sensor images reliably. We evaluate the proposed matching algorithm by comparing it with other state-of-the-art algorithms. The experimental results show the proposed algorithm has a significant advantage on matching accuracy.

Maneuver identification using elastic template matching: multi-case study

Advanced driver assistance systems (ADAS), which can either help to prevent accidents or reduce their negative consequences by intervening in a wide variety of ways, are the solution of choice for considerably greater safety in traffic and comfortable driving. Further, they can be used to perform various improvements such as optimizing fuel consumption or emissions. In conjunction with the driver, they form human machine systems (HMS) with varying degrees of complexity and automation. In order to pass the numerous checks and meet certain standards, ADAS must recognize the surrounding traffic as quickly and accurately as possible in order to act upon it. As a result, rapid and accurate identification methods are required to ensure this. Available approaches still have a lot of potential for optimization in terms of speed and accuracy and in the present work we are aiming to improve the elastic template matching algorithm developed by the authors in a previous study. We extend the approach with a training-free continuous and simultaneous detection of several maneuvers by means of the so-called Nearest Neighbour Algorithm, which in our case transforms into Nearest Centroid Classifier. Moreover, the approach can be easily used for multi-vehicle scenarios; though by treating each vehicle as a separate object without taking into account their interactions.

Fault Diagnosis of Reciprocating Compressor Using Component Estimating Empirical Mode Decomposition and De-Dimension Template With Double-Loop Correction Algorithm

This paper presents an approach to implement multi-parameter (i.e., pressure, temperature, vibration, current, and liquid level) signals for fault diagnosis of the reciprocating compressor (RC). Due to the complexity of structure and motion of such compressor, the acquired signals involve transient impacts and noises. This causes the useful information to be corrupted and makes it difficult to diagnose the fault patterns accurately. A component estimating empirical mode decomposition (CEEMD) method is proposed to remove the random noise and improve data quality. Furthermore, a new template matching algorithm called de-dimension template with double-loop correction (DDT-DLC) is applied to diagnose the fault pattern contained in the time series signals. The DDT employs a judging criterion for key characterization parameters extraction and a multicellular parameter fusion method to reduce the dimension of the matching template, and then, the DLC supplies a double-loop correction algorithm to build a parameter state array computing model of the time series data by adjusting the dynamic factors. The proposed approach is validated with three fault patterns and the healthy pattern in a two-stage reciprocating air compressor. To confirm the superiority of the proposed method, its performance is compared with that of the traditional methods. The results have indicated that the proposed approach is of highly diagnostic accuracy and shortly computing time in the fault diagnosis.

A Study on IR Target Recognition Approach in Aerial Jamming Environment Based on Bayesian Probabilistic Model

The use of infrared (IR) decoys as a countermeasure has become a significant and important factor that influences the performance of heat-seeking missiles. The system employed by such missiles utilizes a template matching algorithm that relies on the infrared characteristics of the target. This target feature vector is compared against the features of nearby objects using minimum distance classification criterion. One of the problems is that it is very difficult to efficiently consider every possible jamming condition. This paper confronts the issue using Bayesian methods to build a probabilistic recognition model that performs well in an aerial jamming environment. Our approach is based on simulating the partial reasoning functions of human visual cognition, where the Bayesian component is used to handle uncertainty. Dealing with ambiguity, such as distinguishing between target and decoy, requires a properly trained model. Our solution, in part, is to conduct a feature histogram analysis on a large set of data that are generated by using a simulated method. This produces a feature probability model with a mixed Gaussian distribution. The maximum likelihood estimation is performed to determine the class of the object, and as such distinguish between genuine targets and decoys. We extend this to construct a new aerial IR target recognition algorithm that relies on both prior information and our probabilistic recognition model. Our empirical analysis includes simulated aerial combat images that are generated for the purpose of testing our method. The experimental results indicate that our approach shows an improvement in performance when compared to the feature template matching approach.

Force-Sensing Robotic Microinjection System for Automated Multi-Cell Injection With Consistent Quality

This paper presents the design and development of a new microinjection system with force sensing for automated multi-cell injection in genome editing of zebrafish using the CRISPR/Cas9 system. In comparison with the traditional approach, it achieves a high injection speed and high precision of operation, which leads to consistent quality and high survival rate of the injected cells. One unique feature is that force sensing is employed to determine the exact moment when the cell membrane is pierced, which contributes to the protection of the cell from damage. Moreover, a new cell holding device is designed to immobilize the cells, which speeds up the multi-cell microinjection process by eliminating the use of conventional vacuum holding pipette. The system implements the object detection by machine vision algorithm along with position/force regulation. The machine vision is realized by combining the pyramid template matching algorithm with Kalman filter, which reduces the computation time and facilitates real-time control. The experimental studies are conducted to verify the performance of the developed system. Results demonstrate the reliability of the robotic microinjection system, which offers a more consistent injection quality and higher viability of cells over the skilled human operator.