Sequential Similarity Detection Research Articles

A novel method for multiple targets localization based on normalized cross-correlation adaptive variable step-size dynamic template matching

The template matching method has been widely utilized in the defect detection of wafer surfaces. However, the traditional matching approaches are limited by illumination, noise, and deformation, which cannot meet the requirements of accuracy and robustness. In this paper, a novel multiple targets localization method, named Normalized Cross-correlation Adaptive Variable Step-Size Dynamic Template (NCC-AVSSDT) matching, is proposed to improve the accuracy and efficiency of image localization, which combines the advantages of NCC and AVSSDT. The AVSSDT method is utilized to dynamically adjust the scanning step size based on the NCC matching coefficients. This approach optimizes the scanning process, accelerating convergence toward the optimal matching position. Experimental results verify the accuracy and robustness of the proposed method under different conditions, especially when dealing with rotational variations and variations in noise textures. Therefore, NCC-AVSSDT can be used to perform multiple targets localization of chip image in nearly real-time. Three experiment types were used for comprehensive evaluations, including multiple targets, noise, and rotation angles. Experimental results show that NCC-AVSSDT is much better than the sequential similarity detection algorithm and mean absolute deviation methods in terms of multiple targets (0.667 vs 0.811 s, 0.832 s) and success rate (100% vs 35%, 20%).

Image Processing Methods for Gesture-Based Robot Control

Abstract In this paper we discuss some image processing methods that can be used for motion recognition of human body parts such as hands or arms in order to interact with robots. This interaction is usually associated to gesture-based control. The considered image processing methods have been experienced for feature recognition in applications involving human robot interaction. They are namely: Sequential Similarity Detection Algorithm (SSDA), an appearance-based approach that uses image databases to model objects, and Kanade-Lucas-Tomasi (KLT) algorithm which is usually used for feature tracking. We illustrate the gesture-based interaction by using KLT algorithm. We discuss the adaptation of each of these methods to the context of gesture-based robot interaction and some of their related issues.

Research on Restoration Algorithm of Tomb Murals Based on Sequential Similarity Detection

Considering the problems of fuzzy repair and low pixel similarity matching in the repair of existing tomb murals, we propose a novel tomb mural repair algorithm based on sequential similarity detection in this paper. First, we determine the gradient value of tomb mural through second-order Gaussian Laplace operator in LOG edge detection and then reduce the noise in the edge of tomb mural to process a smooth edge of tomb mural. Further, we set the mathematical model to obtain the edge features of tomb murals. To calculate the average gray level of foreground and background under a specific threshold, we use the maximum interclass variance method, which considers the influence of small cracks on the edge of tomb murals and separates the cracks through a connected domain labelling algorithm and open and close operations to complete the edge threshold segmentation. In addition, we use the priority calculation function to determine the damaged tomb mural area, calculate the gradient factor of edge information, obtain the information entropy of different angles, determine the priority of tomb mural image repair, detect the similarity of tomb mural repair pixels with the help of sequential similarity, and complete the tomb mural repair. Experimental results show that our model can effectively repair the edges of the tomb murals and can achieve a high pixel similarity matching degree.

Real-time location estimation for indoor navigation using a visual-inertial sensor

PurposeThe purpose of this study is to use visual and inertial sensors to achieve real-time location. How to provide an accurate location has become a popular research topic in the field of indoor navigation. Although the complementarity of vision and inertia has been widely applied in indoor navigation, many problems remain, such as inertial sensor deviation calibration, unsynchronized visual and inertial data acquisition and large amount of stored data.Design/methodology/approachFirst, this study demonstrates that the vanishing point (VP) evaluation function improves the precision of extraction, and the nearest ground corner point (NGCP) of the adjacent frame is estimated by pre-integrating the inertial sensor. The Sequential Similarity Detection Algorithm (SSDA) and Random Sample Consensus (RANSAC) algorithms are adopted to accurately match the adjacent NGCP in the estimated region of interest. Second, the model of visual pose is established by using the parameters of the camera itself, VP and NGCP. The model of inertial pose is established by pre-integrating. Third, location is calculated by fusing the model of vision and inertia.FindingsIn this paper, a novel method is proposed to fuse visual and inertial sensor to locate indoor environment. The authors describe the building of an embedded hardware platform to the best of their knowledge and compare the result with a mature method and POSAV310.Originality/valueThis paper proposes a VP evaluation function that is used to extract the most advantages in the intersection of a plurality of parallel lines. To improve the extraction speed of adjacent frame, the authors first proposed fusing the NGCP of the current frame and the calibrated pre-integration to estimate the NGCP of the next frame. The visual pose model was established using extinction VP and NGCP, calibration of inertial sensor. This theory offers the linear processing equation of gyroscope and accelerometer by the model of visual and inertial pose.

Circuit Breaker Energy Storage Spring Deformation Characteristics Test Method Based on Identification Region Estimation and Optimization of SSD-P Algorithm

As a powerful component of a circuit breaker, the reliability of energy storage spring plays an important role in the drive and control the operation of a circuit breaker motion process. A non-contact testing method of spring deformation characteristics based on image matching tracking technology is proposed: the high-speed camera is utilized to capture the image sequence of energy storage spring extension-contraction process, and the first coil of the movable end of the spring is taken as the matching target. Then, the sequential similarity detection - pyramid (SSD-P) matching algorithm is utilized to search the target frame by frame to obtain the target coordinates of the key frame and parameters of spring deformation characteristic. A sequence similarity detection image pyramid matching based on recognition region estimation (SSD-P-E) algorithm is proposed. The subsequent frame target position is predicted according to the front and rear frame position correlation, the recognition area is dynamically adjusted according to the prediction to eliminate the interference of similar structures on the matching results and improve the matching speed and accuracy. Finally, the experimental results show that the method can effectively detect the extension-contraction deformation characteristics of the circuit breaker spring release energy process when the circuit breaker is working.

基于序贯相似性和布谷鸟寻优的敦煌壁画修复算法

基于序贯相似性和布谷鸟寻优的敦煌壁画修复算法

Online Inspection Method of Defect Dimension of Stainless Steel Precision Blanking Sheet Contour

In this study, a new method of online inspection of contour defects is proposed for stainless steel precision blanking sheet to address problems in the use of the current method to obtain detect information: the recognition system is complex, and the measurement error of defect dimension is large. The images of defect blanking sheet are obtained by the established image collection system. The results of image analysis show that the defect contour of blanking sheet has the correspondence and similarity characteristics. An improved sequential similarity detection algorithm and the measurement algorithm are developed. The measurement experiments show that the online inspection system is stable and reliable, and the maximum measurement error is 0.0362mm. The results of this study will lay a foundation for the online inspection of precision machining.

A novel image registration control system based on improved composite metric entropy function in color printing

The accuracy of overprint is one of the essential factors for the qualities of modern color printing technology. Using machine vision technology and image processing technology to detect overprint quality can steadily and accurately monitor overprint quality and avoid the disadvantages of human eyes detection. This paper firstly introduces the gradient entropy and direction constraint into sequential similarity detection algorithm (SSDA); then a novel joint function is proposed as similarity measure function; finally, Powell optimization algorithm is adopted to optimize the registration parameters. Simulation results, in both qualitative and quantitative, show that our proposed algorithm noticeably reduces the registration error compared with the traditional method. The obtained accurate registration parameter would make it possible for identifying the overprint qualities, sending signal when the misregister and deviation adjusting signal occur. In brief, our proposed algorithm can make the printing machine automatically adjust the plate location and correct the standard deviation in color printing system.

A novel quality test method of electricity meter LCD Screen based on image processing

In order to solve the problem of incorrect test on the LCD screen quality of smart electricity meter and to make its visual inspection item perfect, a novel quality test method based on image processing is put forward in this paper. First, a novel algorithm of self-learning fast template matching based on the sequential similarity detection algorithm is proposed. Then, how to synthesize characteristics of many templates into a standard template and how to establish a real-time and self-learning template library are described in detail. Finally, the sequential similarity detection algorithm is improved with adaptive threshold. The experiment results show that the proposed test method has higher efficiency and accuracy for smart electricity meter LCD screen quality testing. Therefore, it has great practical applications.

Application of image processing technology in the classroom energy-saving system

In this paper, image processing technology is applied to the field of classroom energy-saving. After the preprocessing of classroom images, we utilize SOPC based on the Nios II embedded soft-core processor, in order to acquire the number and position of students through illumination detection, image segmentation and template matching achieved by the sequential similarity detection algorithm (SSDA). Then the signal to control the switches of electrical appliances intelligently will be output through SOPC of FPGA. With the effective combination of hardware and software, the system achieves the intelligent control of electrical appliances such as lights in the classroom, which covers the shortage of the energy management of the classroom.

A study on fast SIFT image mosaic algorithm based on compressed sensing and wavelet transform

Considering the disadvantages of massive calculation and slow speed of traditional Scale Invariant Feature Transform (SIFT) algorithm, we propose an improved image mosaic method which combines Wavelet Transform (WT) and Compressed Sensing (CS) algorithm. The method works as follows. Firstly, images are transformed with wavelet and compressed using compressed sensing technology. Then, image feature points are extracted in combination with SIFT algorithm. Finally, Sequential Similarity Detection Algorithm (SSDA) with adaptive threshold is used to fast search of image matching to find out an optimal stitching line, and a panoramic image is obtained. Experimental results demonstrate that the method realizes fast image matching, efficiently overcomes the shortcomings of heavy computation and low efficiency in the process of extracting image features, and guarantees matching accuracy and stitching efficiency, which meets the real-time requestments in machine vision system. This algorithm can be applied to image matching and stitching in the field of digital image security.

Road edge detection based on dual-threshold SSDA template matching

Extracting road edge information from remote sensing image can simplify the conventional urban road mapping work. Based on the general road image features,this paper proposes a dual-threshold SSDA( sequential similarity detection algorithm) template matching method in an image processing model. And on the basis of the general SSDA,another algorithm is presented to reduce the excessive number of samples responsible for the error growth. Compared with other algorithms,this algorithm can more effectively access the road edge information extraction. As for some parts of the road which cannot be completely extracted through pretreatment process,the detection results can be corrected to reduce treatment,and hence the processing efficiency will be improved.

Sequential similarity detection algorithm based on image edge feature

This paper proposes a new sequential similarity detection algorithm (SSDA), which can overcome matching error caused by grayscale distortion; meanwhile, time consumption is much less than that of regular algorithms based on image feature. The algorithm adopts Sobel operator to deal with subgraph and template image, and regards the region which has maximum relevance as final result. In order to solve time-consuming problem existing in original algorithm, a coarse-to-fine matching method is put forward. Besides, the location correlation keeps updating and remains the minimum value in the whole scanning process, which can significantly decrease time consumption. Experiments show that the algorithm proposed in this article can not only overcome gray distortion, but also ensure accuracy. Time consumption is at least one time orders of magnitude shorter than that of primal algorithm.

Rapid Location of LED Die Array Based on Cross Correlation in Frequency Domain

A rapid template matching algorithm is used to locate l-emitting d (LED) die array on wafer planes in vision-based LED sorting or die-bonding system, the image of LED die array is first converted to binary image and is pre-processed through morphological operations such as dilation and erosion, and the cross correlation operation between LED die templatae and wafer image in frequency domain is implemented by using fast Fourier transform (FFT), and the pixel coordinates of all LED dies on the wafer plane can be determined at one time using the cross correlation in frequency domain (CCFD) instead of in spacial domain. Experimental results of LED die array measurement to a large-diameter LED wafer show that detection efficiency is far higher than conventional normalized cross-correlation (NCC) algorithm, and is only half of consumed time to compare with the sequential similarity detection algorithm (SSDA), the proposed CCFD algorithm can be used for rapid LED die array location in vision-baesd LED sorting or die-bonding machines.

Research of Picture Adaptive Processing for Packaging Printing Online Detection

In the process of printing machines increasing and reduction of speed, the image collected from online detection system for different speed of printing needs picture adaptive processing. In this paper, there are two methods put forward to realize above goal. One method is sequential similarity detection algorithms and the other is ratio value. Apply with VC++ programming to realize image matching on the premise of the unique CCD detection equipment. The experiment results show that: sequential similarity algorithm on the premise of printing machine running in low speed, by comparing with threshold to realize variable-speed imaging. The ratio value method can be used for a variety of printing speed and it has high speed, high detection efficiency and wide range of application.

Robot View Navigation Based on Level-Divided Strategy

In allusion to the colored image matching characteristic in the system of robot view navigation, SSDA (the sequential similarity detection algorithm) is improved and adaptive genetic algorithm is brought in; meanwhile, level-divided search strategy connective with rough and exact matching. The improved algorithm can enhance the image matching speed with no matching accuracy reduced, so that real-time requirements of robot view navigation can be met and robot view navigation will be of preferable robustness.

Motion detection in moving background using a novel algorithm based on image features guiding self-adaptive Sequential Similarity Detection Algorithm

A novel efficient algorithm for motion detection in dynamic background was proposed. In image registration step, a feature-based and self-adaptive Sequential Similarity Detection Algorithm (SSDA) algorithm was proposed, which searches for matching position under constraints induced by image features with variational threshold. Then perform change detection by calculating and classifying the Mean Absolute Difference (MAD) around detected features in the middle frames of three consecutive images. Moving objects position was determined according to the rule that the feature from moving regions shows a lager MAD. Experiments on data sets of four typical scenes show that the improved registration algorithm is accurate and costs less than 0.4s in computation, much faster compared with other four methods, and the proposed Dual Maximum Mean Absolute Difference Algorithm (DMMADA) can obtain a robust set of moving object features. Our algorithm can be used for fast detection of moving targets in dynamic background as well as change detection.

应用序贯相似检测的基本矩阵快速鲁棒估计

A fast and robust fundamental matrix estimation method based on Sequential Similarity Detection Algorithm(SSDA) is presented to estimate the fundamental matrix rapidly and accurately.The SSDA is introduced into the Maximum a Posteriori Sample Consensus(MAPSAC) to search the optimum model parameters and the accumulation times of computing a cost function are cut down by eliminating the false model as soon as possible,which not only keeps the better robustness of MAPSAC,but also reduces its computation effectively.Then,the initial inliers obtained by the improved MAPSAC are optimized with a M-estimator.Those inliers with larger residual errors are removed and the optimized inliers are used to compute the fundamental matrix to enhance the precision and improve the robustness of the algorithm.Experiment results demonstrate that the proposed algorithm performs better in accuracy and robustness,and its average speed has increased at least 30% as compared with that of the MAPSAC.The proposed algorithm can satisfy the requirements for real-time,precision and robustness in the fields such as three-dimensional reconstruction,image matching,image tracking and camera self-calibration.

Extracting road centrelines from high-resolution satellite images using active window line segment matching and improved SSDA

This paper presents a new semi-automatic approach to extracting main road centrelines from high-resolution satellite images. The approach is based on active window line segment matching and an improved sequential similarity detection algorithm (SSDA). First, a user-specified point on the road centreline is selected as a reference central point to define a template window, and a thresholding operation is performed within the window. Then a best matched target window along the road is searched to determine the next central point in the road. To avoid the influence of noise, only the line segment of ‘interest’ in the window is matched. An improved SSDA searching strategy is proposed to increase the matching speed. When the best matched target window is found, its centre is used as the next central point in the road, and a new template window is generated. By repeating the matching process, a series of central points can be obtained automatically and the corresponding final road centreline from them is extracted. Our approach also allows some kinds of user interventions in case automatic tracking fails. Experimental results confirm that the proposed approach is capable of rapidly and accurately extracting main road centrelines and has good robustness against noise.

S0302-2-1 パターンマッチングの精密化によるデジタル画像相関法の高精度化(実験力学における計測・解析法の新展開(2))

Until now, the comparison with a strain gauge or the finite element method has performed accuracy verification of the displacement analysis of the subpixel by the pattern-matching method using a digital image correlation method. The result proved that the digital image correlation method has sufficient high accuracy at the time of infinitesimal deformation. However, mismatching may arise depending on the texture of an image. Although accuracy improved more to enlarge subset size, the demerit of which the computation time increases existed. Therefore, when subset size was set small, improvement in the accuracy of the digital image correlation method was investigated by aiming to reduce mismatching. In the digital image correlation method using coarse-to-fine approach, the result checked that an accurate result was obtained, without mismatching occurring, even when subset size was set up small. Moreover, in the digital image correlation method using the SSDA (Sequential Similarity Detection Algorithm) method, it was possible to have analyzed with accuracy almost equivalent to the digital image correlation method by a correlation coefficient.