Template Matching Technique Research Articles

DASH: Deep Learning for the Automated Spectral Classification of Supernovae and Their Hosts

Abstract We present DASH (Deep Automated Supernova and Host classifier), a novel software package that automates the classification of the type, age, redshift, and host galaxy of supernova spectra. DASH makes use of a new approach that does not rely on iterative template-matching techniques like all previous software, but instead classifies based on the learned features of each supernova’s type and age. It has achieved this by employing a deep convolutional neural network to train a matching algorithm. This approach has enabled DASH to be orders of magnitude faster than previous tools, being able to accurately classify hundreds or thousands of objects within seconds. We have tested its performance on 4 yr of data from the Australian Dark Energy Survey (OzDES). The deep learning models were developed using TensorFlow and were trained using over 4000 supernova spectra taken from the CfA Supernova Program and the Berkeley SN Ia Program as used in SNID (Supernova Identification software). Unlike template-matching methods, the trained models are independent of the number of spectra in the training data, which allows for DASH's unprecedented speed. We have developed both a graphical interface for easy visual classification and analysis of supernovae and a Python library for the autonomous and quick classification of several supernova spectra. The speed, accuracy, user-friendliness, and versatility of DASH present an advancement to existing spectral classification tools. We have made the code publicly available on GitHub and PyPI (pip install astrodash) to allow for further contributions and development. The package documentation is available at https://astrodash.readthedocs.io.

An Efficient and Fast Partial Template Matching Technique Enhancement in Normalized Cross Correlation

Template matching forms the basis of many image processing algorithms and hence the computer vision algorithms. There are many existing template matching algorithms like Sum of Absolute Difference (SAD), Normalized SAD (NSAD), Correlation methods (CORR), Normalized CORR(NCORR), Sum of Squared Difference (SSD), and Normalized SSD(NSSD). In general, as image requires more memory space for storage and much time for processing. The above said methods involves much computation. In any processing, efficiency constraints include many factors, especially accuracy of the results and speed of processing. An approach to reduce the execution time is always most appreciated. As a result of this, a novel method of partial NCC (PNCC) template matching technique is proposed in this paper. A block window approach is used to reduce the number of operations and hence to speed up the processing. A comparative study between existing NCC algorithm and the proposed partial NCC, PNCC algorithm is done. It is experimented and results proves that the execution time is reduced by 8 - 47 times approximately based on the various template images for different main images in PNCC. The accuracy of the result obtained is 100%. This proposed algorithm works for various types of images. The experiment is repeated for various sizes of templates and different sizes of main image. Further improvement in the speed of execution can be achieved by implementation of the proposed algorithm using parallel processors. It may find its importance in the real time image processing.

Interpretation of Ground Penetrating Radar Dataset using Normalised Cross-Correlation Technique

Ground Penetrating Radar (GPR) is one of the latest non-destructive geophysical technology and most widely used in detecting underground utilities. GPR can detect both metal and non-metal, however, it is unable to identify the type of underground utility object. Many researchers come out with their techniques to interpret the GPR image. The current method requires experience in interpretation. Thus, in this study, a new method to detect underground utility utilizing the Normalised Cross-Correlation (NCC) template matching technique is proposed. This technique will reduce the dependency on experts to interpret the radargram, less time consuming and eventually save cost. Upon detection, the accuracy of the system is assessed. From the accuracy assessment performed, it is shown that the system provides accurate detection results for both, depth and pipe size. The Root Mean Square Error (RMSE) for the buried pipe depth obtained by using the proposed system is 0.110 m, whereas the highest percentage match obtained is 91.34%, the remaining 8.66% mismatched might be due to the soil condition, velocity or processing parameter that affected the radargram. Based on the assessment, the developed system seems capable to detect the subsurface utility if the radar image and template image used is acquired using the same antenna frequency, point interval, and similar GPR instrument.

MoDTRAP: Improved heart rate tracking and preprocessing of motion-corrupted photoplethysmographic data for personalized healthcare

ObjectiveA new joint framework for heart rate (HR) tracking and preprocessing of motion artifact (MA) corrupted photoplethysmogram (PPG) data is presented. MethodsTwo popular signal decomposition techniques, viz., variational mode decomposition (VMD) to track HR, and ensemble empirical mode decomposition (EEMD) in conjunction with an artificial neural network (NN) model was utilized for preprocessing. The HR frequency was estimated from the signal strengths of VMD decomposed mode functions and tracked with an indigenous algorithm utilizing the fact that the PPG signal normally comprises base HR frequency along with its harmonics. For MA reduction, The HR synchronous signal component was extracted from the appropriate mode functions of VMD decomposition and reconstructed to minimize MA using a template matching technique utilizing an autoencoder and pre-trained multilayer feedforward neural network model. A combination of EEMD followed by a LSTM binary classifier was used to generate and update the reference PPG template beat for the above purpose. ResultsWith 2015 IEEE signal processing cup challenge database, an average absolute error and percent absolute error of 1.02 and 0.86 respectively compared to the ground truth HR were obtained for all 22 subjects. For MA reduction, we used wrist PPG data collected from 30 human subjects (normal and cardiovascular patients), achieving an average root mean squared error (RMSE) of 0.31 and SNR improvement of 21.23 dB. ConclusionProposed MoDTRAP technique provides noticeable improvements, separately, over existing methods on HR tracking and MA reduction. SignificanceThe proposed technique can be utilized for ambulatory healthcare monitoring.

Induced seismicity during the 2012 Newberry EGS stimulation: Assessment of two advanced earthquake detection techniques at an EGS site

To improve the microearthquake detection capability during the 2012 Newberry enhanced geothermal system (EGS) demonstration, we applied two advanced earthquake detection algorithms to the continuous seismic data. These techniques have the power to detect microearthquakes within the seismic noise that would otherwise be missed using traditional techniques. We compare the efficacy of a matched field processing algorithm with a multi-channel waveform correlation algorithm. Both methods identified between 60%–80% more events, with each slightly outperforming the other in different seismic noise contexts. Incorporating either template-matching technique into a seismic processing routine could therefore effectively increase the sensitivity of the seismic network without changes to the existing hardware. Additionally, lowering the magnitude of completeness would significantly add to the number of events that could subsequently inform future decision making at the reservoir level.

Fully automated method for glaucoma screening using robust optic nerve head detection and unsupervised segmentation based cup-to-disc ratio computation in retinal fundus images

Background and objectiveVisual impairment affects a significant part of the population worldwide. Glaucoma is one of these main causes, a chronic eye disease leading to progressive vision loss. Early glaucoma screening is an important task, allowing a slowing down of the pathology spreading and avoidance of irreversible vision damages. When manual assessment by experts suffers from disadvantages, exploiting the relevant Cup-to-Disc Ratio (CDR) feature as a structural indicator to assess the damage to the optic nerve head (ONH) is an efficient way for early glaucoma screening and diagnosis. MethodsIn this paper, we propose a new fully automated methodology for glaucoma screening and diagnosis from retinal fundus images. In order to allow eye examination in remote locations with limited access to clinical facilities, we focus in this work on the development of a computationally-efficient algorithm for further implementation on mobile devices. First, the method provides a robust optic disc (OD) detection method, combining a brightness criterion and a template matching technique, to effectively detect the optic disc (OD) even in the presence of bright lesions associated to pathological cases. Second, an efficient optic cup (OC) and optic disc (OD) segmentation is performed, using a texture-based and model-based approach. Finally, Cup-to-Disc Ratio (CDR) computation leads to glaucoma screening with a classification between healthy and glaucomatous patients. ResultsThe proposed approach for glaucoma screening and diagnosis have been tested on the publicly available DRISHTI-GS1 dataset. Fifty retinal images are provided and labeled healthy or glaucomatous by trained specialists. The method achieves 98% of accuracy on final glaucoma screening and diagnosis, and excellent performance rates on evaluation metrics, outperforming the state-of-the-art CDR feature-based approaches. ConclusionsWe proposed a fully automated method for glaucoma screening and diagnosis from retinal images. Excellent performance was obtained on final screening, classifying healthy and glaucomatous subjects. As it effectively detects the presence of glaucoma, in a low-computational manner, the approach can be part of a mobile help-diagnosis system, to improve the final diagnosis by the specialist and develop widespread visual health programs.

Defect detection method using deep convolutional neural network, support vector machine and template matching techniques

In this paper, a defect detection method using deep convolutional neural network (DCNN), support vector machine (SVM) and template matching techniques is introduced. First, a DCNN for visual inspection is designed and trained using a large number of images to inspect undesirable defects such as crack, burr, protrusion, chipping, spot and fracture phenomena which appear in the manufacturing process of resin molded articles. Then the trained DCNN named sssNet and well-known AlexNet are, respectively, incorporated with two SVMs to classify sample images with high recognition rate into accept as OK category or reject as NG one, in which compressed feature vectors obtained from the DCNNs are used as inputs for the SVMs. The performances of the two types of SVMs with the DCNNs are compared and evaluated through training and classification experiments. Finally, a template matching technique is further proposed to efficiently extract important target areas from original training and test images. This will be able to enhance the reliability and accuracy for defect detection.

Seismic Activity Preceding the 2011 Mw9.0 Tohoku Earthquake, Japan, Analyzed With Multidimensional Template Matching

AbstractThe observation of a transient slip 1 month before the rupture of the 2011 Tohoku earthquake is a conandrum since the area was supposedly fully coupled. A better understanding of the mechanisms at work during the preseismic phase is thus fundamental. However, the configuration of the Pacific plate and the location of the Tohoku rupture zone 200 km from the coast make it difficult to detect microseismic events. In this study, we use a multidimensional template matching (MDTM) technique to detect earthquakes that are hidden in the noise. The temporal distribution of these 395 newly detected earthquakes provides new insights on the slip history of the megathrust earthquake epicentral zone. The detected events can be separated into two groups: 187 low‐frequency detections (below 5 Hz) that well recorded the episodes of earthquake migration prior to the Tohoku earthquake and 208 high‐frequency detections (above 10 Hz) that occurred close to the rupture zones of the M ≥ 4.8–6 earthquakes that struck between the 9 March 2011 M7.3 foreshock and the 30 November 2010 Tohoku‐Oki earthquake. The seismic rate of these high frequency detection events starts to increase on 30 November 2010 until the Tohoku earthquake.

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.

Integrity Checking of Physical Currency with Pattern Matching: Coping with Few Data and the Training Sample Order

Nowadays, technology utilization increases rapidly in our daily life. Detection of original things from fake make difficult due to misusers of this technology. Currently, world is moving toward digitalization even though physical currency is playing an important role in some of the rural areas. Counterfeit detection and maintain is a major issue. In this paper, an approach has proposed that would be useful to recognize the identity of the currencies and decreases the processing time of verification by pattern recognition techniques. This method can improves accuracy in the process of fake notes detection. In order to recognize currency features, this system uses preprocessing, color detection, segmentation, edge detection and template matching techniques. The result of this application notifies that whether the currency is original or fake to the end user. Here, we have been considering Indian currency dataset for testing the proposed system. The main strengths of this paper are performance analysis which has done by various approaches like quantitative method histogram and quality metrics comparison with test case study reports.

Clinical application of biological fingerprints extracted from averaged chest radiographs and template-matching technique for preventing left-right flipping mistakes in chest radiography.

We aimed to evaluate the identification performance achieved using biological fingerprints extracted from averaged chest radiographs and template-matching techniques for the prevention of left-right flipping mistakes. We produced averaged chest radiographs for each sex by averaging 100 posteroanterior chest radiographs. Further, 400 and 566 chest radiographs were used in consistency and validation tests, respectively, and they were flipped horizontally to produce flipped chest radiographs under the assumption that the left-right flipping mistake occurred. The correlation values obtained with chest radiographs and those obtained with flipped chest radiographs were calculated. When we used correlation indices calculated from the correlation values from four biological fingerprints except for the lung apex, 96.5% (386/400) and 95.8% (542/566) of the left or right sides were identified correctly in the consistency and validation tests, respectively. This result indicates that our proposed method would be promising for the prevention of left-right flipping mistakes.

Robust speaker verification in band-localized noise conditions

This research paper presents a robust method for speaker verification in noisy environments. The noise is assumed to contaminate certain parts of the voice’s frequency spectrum. Therefore, the verification method is based on splitting the noisy speech into subsidiary bands then using a threshold to sense the existence of noise in a specific part of the spectrum, hence activating an adaptive filter in that part to track changes in noise’s characteristics and remove it. The decomposition is achieved using low complexity quadrature mirror filters QMF in three levels thus achieving four bands in a non-uniform that resembles human hearing perceptual. Speaker recognition is based on vector quantization VQ or template matching technique. Features are extracted from speaker’s voice using the normalized power in a similar way to the Mel-frequency cepstral coefficients. The performance of the proposed system is evaluated using 60 speakers subjected to five levels of signal to noise ratio SNR using total success rate TSR, false acceptance rate FAR, false rejection rate FRR and equal error rate. The proposed method showed higher recognition accuracy than existing methods in severe noise conditions.

Real-Time Vehicle Detection Using Cross-Correlation and 2D-DWT for Feature Extraction

Nowadays, real-time vehicle detection is one of the biggest challenges in driver-assistance systems due to the complex environment and the diverse types of vehicles. Vehicle detection can be exploited to accomplish several tasks such as computing the distances to other vehicles, which can help the driver by warning to slow down the vehicle to avoid collisions. In this paper, we propose an efficient real-time vehicle detection method following two steps: hypothesis generation and hypothesis verification. In the first step, potential vehicles locations are detected based on template matching technique using cross-correlation which is one of the fast algorithms. In the second step, two-dimensional discrete wavelet transform (2D-DWT) is used to extract features from the hypotheses generated in the first step and then to classify them as vehicles and nonvehicles. The choice of the classifier is very important due to the pivotal role that plays in the quality of the final results. Therefore, SVMs and AdaBoost are two classifiers chosen to be used in this paper and their results are compared thereafter. The results of the experiments are compared with some existing system, and it showed that our proposed system has good performance in terms of robustness and accuracy and that our system can meet the requirements in real time.

Constraining Spatiotemporal Characteristics of Magma Migration at Piton De La Fournaise Volcano From Pre-eruptive Seismicity.

Volcano‐tectonic seismicity has been recorded for decades on various volcanoes and is linked with the magma transport and reservoir pressurization. Yet earthquakes often appear broadly distributed such that magma movement is difficult to infer from its analysis. We explore the seismicity that occurred before eruptions at Piton de la Fournaise in the last 5 years. Using template matching and relocation techniques, we produce a refined image of the summit seismicity, demonstrating that most earthquakes are located on a ring structure. However, only a portion of this structure is activated before each eruption, which provides an indication as to the direction of the future eruptive site. Furthermore, we show that the delay between the pre‐eruptive swarm and the eruption onset is proportional to the distance of the eruptive fissures relative to the summit cone. This reveals that the beginning of the intrusion already bears information regarding the future eruption location.

Defect Detection in Electronic Surfaces Using Template-Based Fourier Image Reconstruction

For defect detection in nonperiodical pattern images, such as printed circuit boards or integrated circuit dies found in the electronic industry, template matching could be the only applicable method to tackle the problem. The traditional template matching techniques work in the spatial domain and rely on the local pixel information. They are sensitive to geometric and lighting changes, and random product variations. The currently available Fourier-based methods mainly work for plain and periodical texture surfaces. In this paper, we propose a global Fourier image reconstruction method to detect and localize small defects in nonperiodical pattern images. It is based on the comparison of the whole Fourier spectra between the template and the inspection image. It retains only the frequency components associated with the local spatial anomaly. The inverse Fourier transform is then applied to reconstruct the test image, where the local anomaly will be restored and the common pattern will be removed as a uniform surface. The proposed method is invariant to translation and illumination, and can detect subtle defects as small as 1-pixel wide in a wide variety of nonperiodical patterns found in the electronic industry.

Nightside Winds at the Lower Clouds of Venus with Akatsuki/IR2: Longitudinal, Local Time, and Decadal Variations from Comparison with Previous Measurements

Abstract We present measurements of the wind speeds at the nightside lower clouds of Venus from observations by JAXA’s mission Akatsuki during 2016, complemented by new wind measurements from ground-based observations acquired with the TNG/Near Infrared Camera Spectrometer (NICS) in 2012 and IRTF/SpeX in 2015 and 2017. The zonal and meridional components of the winds were measured via cloud tracking on a total of 466 Akatsuki images of Venus acquired by the camera IR2 using the 2.26 μm filter, with spatial resolutions ranging from 10 to 80 km per pixel and covering 2016 March 22 to October 31. More than 149,000 wind vectors were obtained using an automatic template-matching technique, and 2947 wind vectors were inferred using a manual procedure. The meridional profiles for both components of the winds are found to be consistent with results from the Venus Express mission during 2006–2008, although stronger wind variability is found for the zonal component at equatorial latitudes where Akatsuki observations have better viewing geometry than Venus Express. The zonal winds at low latitudes also suggest a zonal variability that could be associated with solar tides or vertically propagating orographic waves. Finally, the combination of our wind measurements from TNG/NICS, IRTF/SpeX, and Akatsuki images with previously published data from 1978 to 2017 suggests variations of up to 30 m s−1 in the winds at the nightside lower clouds of Venus.

A new approach for profile interpretation of a tray-type distillation column using gamma-ray scan and template matching techniques

Gamma-ray scanning is a well-known technique for inspection of distillation columns. A fast and accurate identification of the malfunctions or defects strongly depends on the profile interpretation procedure. By using this technique, interpretation of scan profiles is not always easy and often needs experienced staffs as well as a long enough time for efficient construing after doing scan work. In the present work, a method has been proposed and implemented to develop the interpretation procedure of the scan profile without involving technical staffs. The proposed approach includes gamma-ray scanning in combination with template matching technique. The method has been validated through the several experiments carried out to obtain different scan profiles for a typical laboratory scale distillation column. In this regard, an appropriate mechanical system along with associated electronics was developed to perform the experiments. A software was also implemented based on the method which provide some controls on scanning procedure in addition to displaying the defects types and locations on the screen. The results revealed that the commonly occurred malfunctions such as foaming, flooding, and damaged tray etc. in the column have been accurately interpreted and automatically reported in a short time using this method. Overall results also showed that the proposed method works almost independent of the scanning speed in the range of 5 to 30 mm/sec.

Evaluation of the depiction ability of similar subtraction images using digital chest radiographs of different patients.

The temporal subtraction (TS) technique requires the same patient's chest radiographs (CXRs) acquired on different dates, whereas the similar subtraction (SS) technique can be used in patients who have no previous CXR, using similar CXRs from different patients. This study aimed to examine the depiction ability of SS images with simulated nodules in comparison with that of TS images with 2- and 7-year acquisition intervals. One hundred patients were randomly selected from our image database. The most recently acquired images of the patients were used as target images for subtraction. The simulated nodule was superimposed on each target image to examine the usefulness of the SS technique. The most (Top 1) and ten most (Top 10) similar images for each target image were identified in the 24,254-image database using a template-matching technique, and used for the SS technique. SS and TS images were obtained using a previously developed nonlinear image-warping technique. The depiction ability of SS and TS images was evaluated using the contrast-to-noise ratio (CNR). The proportion of Top 1 SS images showing higher CNR than that of the TS images with 2- and 7-year acquisition intervals was 28% (28/100) and 33% (33/100), respectively. Moreover, the proportion of cases that had any of the Top 10 SS images with higher CNRs than those of TS images with 2- and 7-year acquisition intervals was 56% (56/100) and 72% (72/100), respectively. Our study indicates that the SS technique can potentially be used to detect lung nodules on CXRs.

Efficient Spectroscopy of Exoplanets at Small Angular Separations with Vortex Fiber Nulling

Abstract Instrumentation designed to characterize potentially habitable planets may combine adaptive optics and high-resolution spectroscopy techniques to achieve the highest possible sensitivity to spectral signs of life. Detecting the weak signal from a planet containing biomarkers will require exquisite control of the optical wavefront to maximize the planet signal and significantly reduce unwanted starlight. We present an optical technique, known as vortex fiber nulling (VFN), that allows polychromatic light from faint planets at extremely small separations from their host stars (≲λ/D) to be efficiently routed to a diffraction-limited spectrograph via a single-mode optical fiber, while light from the star is prevented from entering the spectrograph. VFN takes advantage of the spatial selectivity of a single-mode fiber to isolate the light from close-in companions in a small field of view around the star. We provide theoretical performance predictions of a conceptual design and show that VFN may be utilized to characterize planets detected by radial velocity (RV) instruments in the infrared without knowledge of the azimuthal orientation of their orbits. Using a spectral template-matching technique, we calculate an integration time of ∼400, ∼100, and ∼30 hr for Ross 128 b with Keck, the Thirty Meter Telescope, and the Large Ultraviolet/Optical/Infrared Surveyor, respectively.

Selective capture based high-speed optical vehicular signaling system

The present article introduces a high-speed optical vehicular signaling system using a distinct and unique capturing strategy called selective capture (SC). The proposed scheme performs the SC within the frame while capturing, not after the frames are captured, thereby reducing the capturing area and thus increasing the camera capture speed. One of the major challenges in optical camera communication (OCC) based vehicular signaling system is low data transmission rate, due to a low sampling rate of a camera receiver, compared with very high-speed modulation of light emitting diodes (LEDs) used as the transmitter. We propose this SC-based technique for a high-speed optical vehicular signaling system. Experiments are conducted to verify the proposed scheme while analyzing various parameters such as margin setting to calculate a total SC area, considering the movement of a vehicle along the roadside, inter-vehicle distance measurement and LED detection from a Raspberry Pi camera (RaspiCam) module. The SC is performed using template matching technique on the RaspiCam module and then the margin is added with the SC to obtain the total SC area. This total SC area is utilized for capturing the taillights of the leading vehicle (LV). The optical vehicle-to-vehicle (V2V) signaling system utilizes two 4 × 4 red LED arrays mounted on LV as the taillights and a RaspiCam mounted on the following vehicle (FV). It is found that the use of RaspiCam set with the total SC area to capture the taillights significantly increases the capture speed of RaspiCam from 120 frames per second (fps) to 435 fps, yielding an efficient and high-speed V2V signaling with flicker-free taillights. Experiment results demonstrate that the proposed optical V2V provides a data rate of up to 6.912 kbps and achieves acceptable bit error rate performance at a distance of up to 175 cm.