Template Matching Algorithm Research Articles

Vision-based patient identification recognition based on image content analysis and support vector machine for medical information system

In this paper, a vision-based patient identification recognition system based on image content analysis and support vector machine is proposed for medical information system, especially in dermatology. This proposed system is composed of three parts: pre-processing, candidate region detection, and digit recognition. To consider the efficiency of the proposed scheme, image normalization is performed. The color information is used to identify camera-captured screen images. In the pre-processing part, the effect of noise in captured screen images is reduced by a bilateral filter. The color and spatial information is used to initially and roughly locate the candidate region. To reduce the skew effect, a skew correction algorithm based on the Hough transform is developed. A template matching algorithm is used to find special symbols for locating the region of interest (ROI). For digit segmentation, digits are segmented in the ROI based on the vertical projection and adaptive thresholding. For the digit recognition, some features are measured from each digit segment and a classifier based on the support vector machine is applied to recognize digits.The experiment’s results show that the proposed system could effectively not only use color information to distinguish the captured screen images from the skin images but also detect the ROIs. After the digit segmentation, the accuracy rates of digit recognition are 98.4% and 94.2% for the proposed system and the Tesseract Optical Character Recognition (OCR) software, respectively. These results demonstrate that the proposed system outperforms the Tesseract OCR software in terms of the accuracy rate of digit recognition.

A fast template matching method based on improved ring projection transformation and local dynamic time warping

Aiming at the difficulty with which conventional template matching algorithms can simultaneously solve the problems of rotation, scaling, and illumination changes, this paper proposed a two-stage fast template matching method with lower complexity. In the first stage, according to the improved ring projection transformation feature vectors, that was, 1-D profiles, a local dynamic time warping algorithm was used to calculate the similarities and the scaling factors by locally aligning the 1-D profiles. In the second stage, the orientation codes method was applied to calculate the rotation angle based on the scaling factor. Compared with conventional template matching methods, the proposed algorithm does not need numerous template images with different scaling factors to enrich the template feature library. Only one template image is required to calculate the scaling factor and the rotation angle. Experimental results showed that by virtue of the proposed algorithm, a very attractive matching accuracy was obtained in the range of 0.8–1.2 scaling factor and arbitrary rotation angle, which was robust to noise and illumination changes.

Chaos-Based Random Sampling for Photometric Invariant Shoe Detection With Vision Sensor in Human–Robot Coexisting Environments

People-following in a leader-follower scheme is considered as a major contemporary research problem in the domain of human-robot coexistence. The problem essentially requires human detection and tracking, and, in recent times, vision sensing based shoe detection has evolved as an effective mechanism for human detection. The problem gets more challenging when the environment becomes affected by photometric conditions like varying illumination, shadows, specularities, etc. Recently, a state-of-the-art fast image template matching algorithm, called photometric-invariant CFAsT-match (PICFAsT-match), has been specifically proposed for shoe detection based people-following in those challenging environments. In this approach, for determining the best shoe matching result corresponding to a frame, each single transformation included in a number of specified grids of general affine transformations is evaluated. However, in order to achieve a high speed real-life implementation of PICFAsT-match, every transformation is assessed by considering a handful number of pixels sampled randomly from the images. Research beyond PICFAsT-match reveals that the matching accuracy significantly relies on the quality of the random sampling. In this paper, we propose an improved variant of PICFAsT-match, called chaos based PICFAsT-match (CBPICFAsT-match), where a novel approach for this process of random sampling of pixels has been developed. This strategy is based on the state-time histories of multiple fractional order chaotic systems. Experimental results aptly demonstrate the superiority of the proposed algorithm, when compared to competing state-of-the-art algorithms, successfully employed for the said shoe detection purpose in human-robot coexisting environments.

A PCB Alignment System Using RST Template Matching with CUDA on Embedded GPU Board.

The fiducial-marks-based alignment process is one of the most critical steps in printed circuit board (PCB) manufacturing. In the alignment process, a machine vision technique is used to detect the fiducial marks and then adjust the position of the vision system in such a way that it is aligned with the PCB. The present study proposed an embedded PCB alignment system, in which a rotation, scale and translation (RST) template-matching algorithm was employed to locate the marks on the PCB surface. The coordinates and angles of the detected marks were then compared with the reference values which were set by users, and the difference between them was used to adjust the position of the vision system accordingly. To improve the positioning accuracy, the angle and location matching process was performed in refinement processes. To overcome the matching time, in the present study we accelerated the rotation matching by eliminating the weak features in the scanning process and converting the normalized cross correlation (NCC) formula to a sum of products. Moreover, the scanning time was reduced by implementing the entire RST process in parallel on threads of a graphics processing unit (GPU) by applying hash functions to find refined positions in the refinement matching process. The experimental results showed that the resulting matching time was around 32× faster than that achieved on a conventional central processing unit (CPU) for a test image size of 1280 × 960 pixels. Furthermore, the precision of the alignment process achieved a considerable result with a tolerance of 36.4 μm.

Random residual neural network-based nanoscale positioning measurement.

In the field of positioning measurement, a combination of complex components, a stringent environment, and time-consuming calibration are the main limitations. To address these issues, this paper presents a deep learning-based positioning methodology, which integrates image processing with nanomanufacturing technology. Non-periodic microstructure with nanoscale resolution is fabricated to provide the surface pattern. The main advantage of the proposed microstructure is its unlimited measurement range. A residual neural network is used for surface pattern recognition to reduce the search area, a survival probability mechanism is proposed to improve the transmission efficiency of the network layers, and template matching and sub-pixel interpolation algorithms are combined for pattern matching. The proposed methodology defines a comprehensive framework for the development of precision positioning measurement, the effectiveness of which was collectively validated by pattern recognition accuracy and positioning measurement performance. The trained network exhibits a recognition accuracy of 97.6%, and the measurement speed is close to real time. Experimental results also demonstrate the advantages and competitiveness of the proposed approach compared to the laser interferometer method.

Application Of A Template Matching Algorithm In The Detection Of The Railroad Track

As the most important part of urban public transportation system, railway and subway are undertaking extremely important tasks. Manual inspection is sometimes difficult to detect track damage in time. Based on the impulse excitation of the rail, the undamaged rail and the damaged rail are distinguished according to the characteristics of its vibration signal. In the process of feature extraction, the pulse signal is intercepted, and the threshold is taken after gaussian smoothing filter. After multiple processing, the feature template is formed. Through the template matching algorithm proposed in this paper, the rail excitation pulse signal can be identified and the rail damage state can be determined. And the simulation display and control platform based on real object is made. After many tests, the method is proved to be effective.

Template Matching Based Sign Language Recognition System for Android Devices

An android based sign language recognition system for selected English vocabularies was developed with the explicit objective to examine the specific characteristics that are responsible for gestures recognition. Also, a recognition model for the process was designed, implemented, and evaluated on 230 samples of hand gestures. The collected samples were pre-processed and rescaled from 3024 ×4032 pixels to 245 ×350 pixels. The samples were examined for the specific characteristics using Oriented FAST and Rotated BRIEF, and the Principal Component Analysis used for feature extraction. The model was implemented in Android Studio using the template matching algorithm as its classifier. The performance of the system was evaluated using precision, recall, and accuracy as metrics. It was observed that the system obtained an average classification rate of 87%, an average precision value of 88% and 91% for the average recall rate on the test data of hand gestures. The study, therefore, has successfully classified hand gestures for selected English vocabularies. The developed system will enhance the communication skills between hearing and hearing-impaired people, and also aid their teaching and learning processes. Future work include exploring state-of-the-art machining learning techniques such Generative Adversarial Networks (GANs) for large dataset to improve the accuracy of results. Keywords— Feature extraction; Gestures Recognition; Sign Language; Vocabulary, Android device.

GPU-Accelerated Automatic Microseismic Monitoring Algorithm (GAMMA) and Its Application to the 2019 Ridgecrest Earthquake Sequence

Abstract Foreshocks and/or aftershocks play critical roles in improving our understanding of the processes of faulting, such as nucleation of earthquakes, earthquake triggering, and postseismic deformation. A rapid and accurate earthquake detection and location algorithm can provide timely information of seismic activities, thereby benefitting our understanding of physical mechanisms of faulting and seismic hazard assessment. We have developed a graphic processing unit (GPU)-accelerated automatic microseismic monitoring algorithm (GAMMA) for accurate and near real-time detection and location of earthquakes. GAMMA utilizes methods based on backprojection to automatically detect potential earthquakes, and then the waveforms of qualified earthquakes are selected as templates when searching for small earthquakes in continuous recordings using the template-matching algorithm. The use of GPUs has substantially accelerated the calculations and has made GAMMA capable of (near-)real-time earthquake monitoring. We have successfully applied GAMMA to the 2019 Ridgecrest earthquake sequence in southern California. The number of earthquakes detected by GAMMA is more than 21 times that documented in the regional catalog. The more complete catalog determined by GAMMA may provide crucial information for improving our understanding of the physical mechanisms of faulting and also supply useful constraints for a variety of types of studies, including dynamic rupture simulations and crustal deformation modeling.

Development of video analytics with template matching methods for using camera as sensor and application to highway bridge structural health monitoring

Structural health monitoring (SHM) has been conducted by placing sensors on structures, so-called contact sensors, to measure displacements, strains, and accelerations of engineering structures. Contact sensing is accurate and effective, but suffers from some critical shortcomings, such as high cost, intensive labor, and traffic interruption. With the advancement and wide availability of digital video cameras, compounded with the development and enhancement of computer vision algorithms, vision-based sensing using a video camera as a sensor for SHM has become a viable alternative and a complementary method to remotely capture structural responses. Several computer vision algorithms are proposed, together with specific type of video camera, for capturing and processing the SHM video for the dynamic structural responses, e.g. displacements of selected targets. Up to date, there is a limited number of successful applications using video camera as a sensor in SHM practice. To facilitate the real-world applications of vision-based SHM, this paper presents the integrated methods, and a software tool for analyzing SHM videos using template matching algorithms along with a subpixel method that enhances the accuracy of the vision-based structural responses. The integrated approach is flexible and versatile for not only extracting displacements, strains, velocities, and accelerations, but also detecting damage of the desired multiple points or areas (templates) from videos. The methods and the software tool have been applied to a comprehensive analysis of the lab structural test, which was video-recorded by a third party without any involvement of the authors or any intension in using video camera as sensor. Good agreement for the lab test has been achieved for the structural responses (e.g. displacement and strain) and the damage detection recorded by the conventional sensors and extracted from the video by applying the integrated tool. The approach has been further validated on a highway bridge in the field, where a contact-based SHM system is permanently installed on the bridge and serves a good baseline reference for validating the proposed approach. The vision-based SHM results obtained for the highway bridge application show good correlation with the structural responses captured by conventional sensors and indicate that the developed analysis methods and software tool perform well for highway bridge test and structural health monitoring.

A novel dense descriptor based on structure tensor voting for multi-modal image matching

Automatic and robust matching of multi-modal images can be challenging owing to the nonlinear intensity differences caused by radiometric variations among these images. To address this problem, a novel dense feature descriptor and improved similarity measure are proposed for enhancing the matching performance. The proposed descriptor is built on a voting scheme of structure tensor that can effectively capture the geometric structural properties of images. It is not only illumination and contrast invariant but also robust against the degradation caused by significant noise. Further, the similarity measure is improved to adapt to the reversal of orientation caused by the intensity inversion between multi-modal images. The proposed dense feature descriptor and improved similarity measure enable the development of a robust and practical template-matching algorithm for multi-modal images. We verify the proposed algorithm with a broad range of multi-modal images including optical, infrared, Synthetic Aperture Radar (SAR), digital surface model, and map data. The experimental results confirm its superiority to the state-of-the-art methods.

A Rail Fastener Tightness Detection Approach Using Multi-source Visual Sensor.

At present, the method of two-dimensional image recognition is mainly used to detect the abnormal fastener in the rail-track inspection system. However, the too-tight-or-too-loose fastener condition may cause the clip of the fastener to break or loose due to the high frequency vibration shock, which is difficult to detect from the two-dimensional image. In this practical application background, 3D visual detection technology provides a feasible solution. In this paper, we propose a fundamental multi-source visual data detection method, as well as an accurate and robust fastener location and nut or bolt segmentation algorithm. By combining two-dimensional intensity information and three-dimensional depth information generated by the projection of line structural light, the locating of nut or bolt position and accurate perception of height information can be realized in the dynamic running environment of railway. The experimental results show that the static measurement accuracy in the vertical direction using the structural light vision sensor is 0.1 mm under the laboratory condition, and the dynamic measurement accuracy is 0.5 mm under the dynamic train running environment. We use dynamic template matching algorithm to locate fasteners from 2D intensity map, which achieves 99.4% accuracy, then use the watershed algorithm to segment the nut and bolt from the corresponding depth image of located fastener. Finally, the 3D shape of the nut and bolt is analyzed to determine whether the nut or bolt height meets the local statistical threshold requirements, so as to detect the hidden danger of railway transportation caused by too loose or too tight fasteners.

Control System for Wheeled Humanoid Following Robot

Aiming at application and development prospects of following robot, a control system for humanoid 18-DOF robot supported by four wheels is designed. The system adopts the double-controller structure composed of master controller Raspberry Pi and slave controller STM32 for servo control of robot based on multi-sensor information fusion. In this control system, USB camera and two-axis pan-tilt are used for capturing images with wide viewing angles. Multi-scale template matching and Median-Flow algorithm are used for target recognition. Kalman Filter is used to fuse acceleration and angular velocity given by attitude sensor to obtain the reliable upright angle. PID algorithms are applied to the control system to realize robot’s upright angle control, speed control and turning angle control. Robot’s action adjustment is achieved by controlling its joint steering gears. The experimental results show that this low-cost wheeled humanoid robot has good self-balancing stability, anti-interference and following stability.

Individual Tree Position Extraction and Structural Parameter Retrieval Based on Airborne LiDAR Data: Performance Evaluation and Comparison of Four Algorithms

Information for individual trees (e.g., position, treetop, height, crown width, and crown edge) is beneficial for forest monitoring and management. Light Detection and Ranging (LiDAR) data have been widely used to retrieve these individual tree parameters from different algorithms, with varying successes. In this study, we used an iterative Triangulated Irregular Network (TIN) algorithm to separate ground and canopy points in airborne LiDAR data, and generated Digital Elevation Models (DEM) by Inverse Distance Weighted (IDW) interpolation, thin spline interpolation, and trend surface interpolation, as well as by using the Kriging algorithm. The height of the point cloud was assigned to a Digital Surface Model (DSM), and a Canopy Height Model (CHM) was acquired. Then, four algorithms (point-cloud-based local maximum algorithm, CHM-based local maximum algorithm, watershed algorithm, and template-matching algorithm) were comparatively used to extract the structural parameters of individual trees. The results indicated that the two local maximum algorithms can effectively detect the treetop; the watershed algorithm can accurately extract individual tree height and determine the tree crown edge; and the template-matching algorithm works well to extract accurate crown width. This study provides a reference for the selection of algorithms in individual tree parameter inversion based on airborne LiDAR data and is of great significance for LiDAR-based forest monitoring and management.

Automated detection of premature ventricular contraction in ECG signals using enhanced template matching algorithm

Nowadays, with the increasing number of people who suffer from cardiovascular diseases such as irregular heartbeats (arrhythmia), there is a vital need to pay more attention to healthcare conditions. Therefore, the production of smart biomedical garments becomes of great necessity. The first step of manufacturing such smart garments is to build an electrocardiogram (ECG) analysis system. In this paper, the premature ventricular contraction (PVC), which is a serious life-threatening cardiovascular condition, is recognised. In addition, an improved template matching technique is developed, implemented, and evaluated to identify the irregularity of PVC beats in the QRS complex and T wave. The improvement in this technique is that a PVC recogniser is established by analysing the maximum and minimum correlation coefficient values instead of the maximum values only. Moreover, a sufficient number of features are relied upon for the accurate detection of PVC beats. The template matching algorithm is evaluated on the MIT-BIH arrhythmia, St. Petersburg Institute of Cardiological Technics (INCART), QT, MIT-BIH Supraventricular Arrhythmia, and Fantasia databases. The results show a valuable accuracy enhancement when compared with those of other recent approaches.

Image recognition in online monitoring of power equipment

The application of remote digital video surveillance and image recognition technology in online monitoring of power equipment is conducive to timely equipment maintenance and troubleshooting. In order to solve the problem of slow speed and large amount of computation of traditional template matching algorithm for power image recognition, a second template matching algorithm for fast recognition of target image is proposed in this article. Firstly, a quarter of the template data is taken and matched within a quarter of the source image, and a reasonable error threshold is given in the matching process. Then, the neighborhood of the minimum error point in rough matching is matched to get the final result. Finally, the algorithm is applied to identify the power equipment and detect the abnormal state of the power equipment. The experimental results show that the matching algorithm can not only accurately locate and identify power equipment and detect equipment faults, but also greatly improve the matching speed compared with other commonly used template matching algorithms.

A closed-loop electrical stimulation system triggered by EOG for acupuncture therapy

Acupuncture therapy is an often-used traditional Chinese medicine intervention of autism spectrum disorder. Acupuncture is usually delivered by therapists; thus, its effectiveness highly relies on their experience. This paper designed a closed-loop electrical stimulation treatment system triggered by neurophysiological signals, in order to improve the conventional acupuncture in clinical trials. Electrooculogram (EOG) signals are collected and analyzed synchronously while autistic children are watching the specifically designed visual evocation system. The electrical stimulation is triggered once the attention state is determined, delivering stimulation to the Changqiang acupoint (between the tailbone and the anus). Three healthy volunteers and four autistic children participated in this proof-of-concept study. Prior to the online test, the subject-special EOG template was determined offline. We obtained the mean recognition rate of 95.45% for healthy participants and 89.43% for autistic children, and the mean false recognition rate of 2.51% for healthy participants and 7.23% for autistic children by template matching algorithm. The system was able to recognize the EOG pattern of attention to the state and successfully trigger the electrical stimulation. This study is the first time to combine acupuncture and bioelectrical signal to provide an automatic closed-loop electrical stimulation system for acupuncture therapy.

Catenary insulator defect detection based on contour features and gray similarity matching

Insulators are the key components of high speed railway catenaries. Insulator failures can cause outages and affect the safe operation of high speed railways. It is important to perform insulator defect detection. Due to the collection of insulator images by moving catenary inspection vehicles, the consistency of the images is poor, and the number of insulator defect samples is very small. An algorithm of deep learning and conventional template matching cannot meet the requirements of insulator defect detection. This paper proposes a fusion algorithm based on the shed contour features and gray similarity matching. High accuracy and consistency of contour extraction and precise separation of each insulator shed were realized. An insulator defect detection model based on the spacing distance of the sheds and the gray similarity was constructed. Experiments show that the method based on the contour features and gray similarity matching can effectively classify normal insulators and defective insulators. Recall of 99.50% and high precision of 91.71% were achieved in the test of the image data set, and this can meet the requirements for the reliability and high precision of a detection algorithm for catenary insulators.

Sub-pixel displacement measurement based on Taylor expansion theory

Traditional vision measurement algorithms have many shortcomings, such as complex process, multi-parameter adjustment and the integer pixel accuracy. To solve these problems, a sub-pixel displacement measurement algorithm based on Taylor expansion is proposed. The displacement vector between adjacent frames is modeled in the first step, and then shift equation of the template image is constructed based on assumptions of constant brightness and spatial consistency. After performing a first-order Taylor series approximation, the displacement vector is obtained by least squares estimation. Finally, through iteratively updating the position of template image, displacement is rapidly extracted. In order to verify the accuracy and effectiveness of the Taylor expansion algorithm, the accuracy test of the grating ruler platform in the presence of the target and the vibration measurement experiment on vibration motor in the absence of the target are designed. Experimental results show that, compared with template matching algorithm based on normalized cross correlation, for the experiments mentioned in this paper, the proposed algorithm can control the calculation time for one frame in less than 1 ms, and achieve higher sub-pixel computation accuracy. Compared with the actual set frequency of 10.78 Hz, the measured frequency of the motor is very consistent with a relative error of 1.1%. It also verifies that the Taylor expansion algorithm proposed in this paper is a reliable and effective non-contact measurement method with important practical application value for vibration measurement.

Road Extraction From High-Resolution Satellite Images Based on Multiple Descriptors

Geometry and texture noise make it difficult to accurately describe road image rules, which leads to the low degree of automation of traditional template matching algorithms based on internal texture homogenization. We propose a semi-automatic road extraction method based on multiple descriptors to improve the degree of automation while ensuring the accuracy of road extraction. This method aims to address the problems of incomplete road image geometric information and poor homogeneity of internal road texture. The multiscale line segment orientation histogram model and sector descriptor are established. Road points are tracked by interpolation and extension, and postprocessing is used to fit the tracking points and extract the road routes. In this article, high-resolution remote sensing images of different types, different resolutions, and different scenes are selected, and the roads exhibit curvatures, vehicle and shadow occlusions, roundabouts, and variational features. Experiments show that for roads with a certain width, completeness, and correctness of the method are more than 98%. Additionally, as compared with other algorithms, the interactive human intervention of this method is reduced by more than 2/3.

Tracking and recognition algorithm for a robot harvesting oscillating apples

Apple fruits on trees tend to swing because of wind or other natural causes, therefore reducing the accuracy of apple picking by robots. To increase the accuracy and to speed up the apple tracking and identifying process, tracking and recognition method combined with an affine transformation was proposed. The method can be divided into three steps. First, the initial image was segmented by Otsu’s thresholding method based on the two times Red minus Green minus Blue (2R-G-B) color feature; after improving the binary image, the apples were recognized with a local parameter adaptive Hough circle transformation method, thus improving the accuracy of recognition and avoiding the long, time-consuming process and excessive fitted circles in traditional Hough circle transformation. The process and results were verified experimentally. Second, the Shi-Tomasi corners detected and extracted from the first frame image were tracked, and the corners with large positive and negative optical flow errors were removed. The affine transformation matrix between the two frames was calculated based on the Random Sampling Consistency algorithm (RANSAC) to correct the scale of the template image and predict the apple positions. Third, the best positions of the target apples within 1.2 times of the prediction area were searched with a de-mean normalized cross-correlation template matching algorithm. The test results showed that the running time of each frame was 25 ms and 130 ms and the tracking error was more than 8% and 20% in the absence of template correction and apple position prediction, respectively. In comparison, the running time of our algorithm was 25 ms, and the tracking error was less than 4%. Therefore, test results indicate that speed and efficiency can be greatly improved by using our method, and this strategy can also provide a reference for tracking and recognizing other oscillatory fruits. Keywords: apple picking robot, tracking and recognition algorithm, oscillating apple, Hough transform, pyramid LK optical flow algorithm, affine transform, template matching DOI: 10.25165/j.ijabe.20201305.5520 Citation: Yang Q H, Chen C, Dai J Y, Xun Y, Bao G J. Tracking and recognition algorithm for a robot harvesting oscillating apples. Int J Agric & Biol Eng, 2020; 13(5): 163–170.