Approximating Boundary of Bitmap Characters Using Genetic Algorithm

Uncalibrated stereo vision with deep learning for 6-DOF pose estimation for a robot arm system

To better achieve image correction effect, an image correction method based on corner point detection is proposed. In image preprocessing, firstly, image equalization is achieved based on the contrast limited adaptive histgram equalization to avoid the problems caused by illumination and suppress noise while maintaining details, and then adaptive threshold segmentation is performed using the OTSU to obtain the binarized image. In the corner point detection stage, the contours of the binarized image are extracted firstly and the closed contours are filled to avoid the independent contours from affecting the accuracy of region growth, then the center point of the image is used as the seed pixel for region growth, and finally the four corner points are calculated based on the linear contours of the growth region and Hough theory, where the accurate region growth result can avoid the influence of the background on the corner point detection. In the correction stage, the perspective matrix is calculated by the four corner points, and the image is corrected by the perspective transformation. The experiments show that the proposed method can accurately find the corner points of document images and achieve efficient correction.

A method based on rotate-angle accumulation is presented to detect the corner points on digital curve. By constructing a rotate-angle accumulation curve and its curvature waves, the intersections points are detected firstly, then the rotate-angle accumulation curve which doesn't include intersection point is segmented to fit in straight line through the curvature waves, lastly the tangent points are determined according to the intersection point of every two adjacent fitted straight line. The method does not need in advance to give a threshold value and the detection accuracy was less affected by noise. Experiments show that the method is efficient for detection and localization.

An optimization technique is proposed for the outline capture of planar images. The overall technique has various phases including extracting outlines of images, detecting corner points from the detected outline, and curve fitting. Linear and conic interpolation methods have been used for vectorization. The idea of multilevel coordinate search has been used to optimize the shape parameters in the description of the generalized conic spline. The two methods ultimately produce optimal results for the approximate vectorization of the digital contours obtained from the generic shapes.

Two approaches, based on linear and conic splines, are proposed here for vectorizing image outlines.Both of the approaches have various phases including extracting outlines of images, detecting corner points from the detected outlines, and curve fitting.Interpolation splines are the bases of the two approached.Linear spline approach is straight forward as it does not have a degree of freedom.interms of some shape controller in its description.However, the idea of the soft computing approach, namely simulated annealing, has been utilized for conic splines.This idea has been incorporated to optimize the shape parameters in the description of the generalized conic spline.Both of the linear and conic approaches ultimately produce optimal results for the approximate vectorization of the digital contours obtained from the generic shapes.Demonstrations and a comparative study also make the essential parts of the paper.

Aiming at the problem of screen size detection in mobile phone production, a method of screen size detection based on homography matrix camera calibration is adopted. For the problem of inconsistent image coordinate system origin and direction between different calibrated images in corner point detection during calibration, the corner detection strategy of manual plus automatic is adopted, which solves the problem of inconsistent image coordinate system origin and direction between images in automatic corner point detection. The experimental results show that the homography-based camera calibration method has an average reprojection error of about 0.12 pixels, high calibration accuracy and small error. And the detection accuracy is better than the requirements of industrial production, which can meet the needs of practical applications.

Reverse Transcription Polymerase Chain Reaction (RT-PCR) using new designed primers pair for Heat Shock Protein70 homologue (HSP70h) of Olive leaf yellowing-associated virus revealed 667 amplified product of 10 olive accessions collected from various olive-growing regions in Tunisia. Amplicons were cloned and sequenced. The sequences were deposited in the international databases. Pairwise sequence comparisons among 10 Tunisian isolates along with a reference sequence (AJ440010) extracted from GenBank revealed a nucleotide identity of 86.06-99.40 and an amino acid similarity of 91.89-99.55. Sequence multiple alignments were searched for evidence of recombination using three methods, ie. Differences of Sums of Squares (DSS) implemented in TOPALi v2.5 software and Single Breakpoint (SBP) along with GARD, a genetic algorithm, both incorporated in HyPhy package. All used methods pointed out the presence of putative breaking points in partially sequenced HSP70h-coding gene. Since failing to account for recombination can mislead the phylogeny inference and can elevate the false positive error rate in positive selection assessment, the use of GARD resulted in the reconstruction of different phylogenies on the left as well as on the right sides of putative recombination breaking points, and the 11 accessions were distributed into at least three clusters compared to MEGA6 software which delineated only two clades. Nonetheless, by dividing the aligned sequences at breakpoints into separate sequence sets, MEGA6 delineated a clustering pattern different from the former two. As a result, recombination reshuffled the affiliation of the different accessions to the clusters. Analysis of selection pressures exerted on HSP70h encoded protein using different models (SLAC, IFEL, FEL, REL, PARRIS, FUBAR, MEME, GA Branch, and PRIME) taking into account recombination, and implemented in HyPhy package, revealed that it underwent predominantly purifying selection as confirmed by Tajima’s D, Fu and Li’s D and F tests, and SNAP algorithm. However, a few sites were also under positive selection as assessed by various models such as FEL, IFEL, REL, MEME, and PRIME.

Sustainability encompasses the interaction between environmental, economic, and social systems at various levels. In transportation systems, vehicles rely on different fuels to meet energy demands. However, these fuels contribute to environmental pollution by releasing greenhouse gases. Considering this context, the present study investigates a sustainable fixed-charge multi-objective multi-driver multi-route multi-conveyance shortest path problem (FCMOMDMRMCSPP). The primary intent is to identify the most efficient route that minimizes cost, time, risk, carbon emissions, and distance while traveling between sources and destinations. Real-world scenarios often involve uncertainties, making it difficult to precisely define the parameters of FCMOMDMRMCSPP. Triangular fuzzy numbers are introduced in the proposed model to address this ambiguity. The possibilistic programming approach is employed to transform the fuzzy problem into a deterministic one. The resulting deterministic model is then solved using two multi-objective genetic algorithms (MOGAs): aspiration level (AL)-based non-dominated sorting genetic algorithm (NSGA)-II and NSGA-III. An aquatic fish haul system problem has been examined as an application within the framework of the proposed model. For α = 0 and 0.1, the AL-based NSGA-II and III generate 6, 11, and 4 solutions that satisfy the decision-maker’s (DM’s) ALs in cases I, II, and III of the AL and shape parameter combination, respectively. Similarly, for α = 0.5, these methods yield 5, 11, and 4 solutions, while for α = 0.9, they provide 6, 11, and 4 solutions for the same cases. A comparative analysis is conducted between the compromise solutions obtained from the proposed techniques and those derived from the hybrid genetic algorithm, NSGA-II and NSGA-III. A sensitivity analysis of the objective functions concerning the shape parameter and AL is also performed. Finally, the coverage performance measure is computed to assess the effectiveness of the proposed methods.

In this paper, a genetic algorithm (GA) is introduced into optimizing the radial basis probabilistic neural networks (RBPNN). The encoding method proposed in this paper involves not only the number and the locations of selected hidden centers but also the shape parameter of the Gaussian kernel function. We use the telling-two-spirals-apart problem as an example to validate the genetic algorithm for optimizing the RBPNN. Consequently, we obtain an optimal interval of the shape parameter of the kernel function for this problem except the reduced RBPNN structure (including the optimal number of the hidden centers and their optimal locations). The experimental results show that with the shape parameters in the optimal interval and with the optimized hidden centers the designed network is not only parsimonious but also of better generalization performance.

Knowledge concerning possible inhomogeneities in a data set is of key importance for any subsequent climatological analyses. Well-established relative homogenization methods developed for temperature and precipitation exist, but with only little experience for snow. We undertook a homogeneity assessment of Swiss snow depth series by running and comparing the results from three well-established semi-automatic break point detection methods (ACMANT, Climatol, and HOMER). Break points identified by each method allowed us to compare the results of the different methods, and by only treating break points as valid if detected in reasonably close proximity by at least two methods, we increased the robustness of the results. We investigated 184 series, of various length between 1930 and 2021 and ranging from 200 to 2500 m a.s.l. and found 45 valid break points. Of those 45, 71 % could be attributed to relocations or observer changes. Metadata are helpful, but not sufficient for break point verification as more than 90 % of recorded events did not lead to valid break points. Using such a combined approach (2 out of 3 methods) is highly beneficial, as it increases the confidence in identified break points in contrast to any single method, with or without metadata.

The static contact characteristics of heavy-duty tracked vehicle roller and track plate contact structure are analyzed, and the influence mechanism of the roller’s shape parameters on the contact stress is studied. According to the Hertz contact theory, a mathematical model of the roller and track plate contact is established. The contact structure model is established in ANSYS software, and the simulation results are compared with the Hertz theory results to verify each other. In the parameter optimization section for the roller and track plate, based on the Hertz stress calculation formula, a new method is proposed to establish a roller and track plate Kriging model and to globally optimize the model by the genetic algorithm (GA). After that, the relationship among the track roller radius R 1 , the track roller rim radius r 1 , and the track plate rim radius r 2 is analyzed. The results show that the difference between the radius of the rim of the roller and the track plate and the radius of the roller rim both affect the maximum contact stress. Changing the plane contact into the curved surface contact can reduce the maximum contact stress by 33%. This study can provide a reference for the design and manufacture of supporting track rollers and track plates.

Electrocardiogram signal preprocessing for automatic detection of QRS boundaries

Abstract. Knowledge concerning possible inhomogeneities in a data set is of key importance for any subsequent climatological analyses. Well-established relative homogenization methods developed for temperature and precipitation exist but have rarely been applied to snow-cover-related time series. We undertook a homogeneity assessment of Swiss monthly snow depth series by running and comparing the results from three well-established semi-automatic break point detection methods (ACMANT – Adapted Caussinus-Mestre Algorithm for Networks of Temperature series, Climatol – Climate Tools, and HOMER – HOMogenizaton softwarE in R). The multi-method approach allowed us to compare the different methods and to establish more robust results using a consensus of at least two change points in close proximity to each other. We investigated 184 series of various lengths between 1930 and 2021 and ranging from 200 to 2500 m a.s.l. and found 45 valid break points in 41 of the 184 series investigated, of which 71 % could be attributed to relocations or observer changes. Metadata are helpful but not sufficient for break point verification as more than 90 % of recorded events (relocation or observer change) did not lead to valid break points. Using a combined approach (two out of three methods) is highly beneficial as it increases the confidence in identified break points in contrast to any single method, with or without metadata.

The paper deals with the shape optimization of an isolated airfoil to minimize the drag when operating in a transonic inviscid flow with some prescribed constraints. A nondominated Sorting Genetic Algorithm is used to solve the optimization problem. Other numerical ingredients of the optimization loop are given by the Class/Shape function Transformation used for the parameterization of the airfoil shape and a finite-volume Computational Fluid Dynamics solver of the Euler equations.

Analogous to the quartic B-splines curve, a piecewise quartic trigonometric polynomial B-spline curve with two shape parameters is presented in this paper. Each curve segment is generated by three consecutive control points. The given curve posses many properties of the B-spline curve. These curves are closer to the control polygon than the different other curves considered in this paper, for different values of shape parameters for each curve. With the increase of the value of shape parameters, the curve approach to the control polygon. For nonuniform and uniform knot vector the given curves have C0, G3; C1, G3; C1, G7; and C3 continuity for different choice of shape parameters. A quartic trigonometric Bézier curves are also introduced as a special case of the given trigonometric spline curves. A comparison of quartic trigonometric polynomial curve is made with different other curves. In the last, quartic trigonometric spline surfaces with two shape parameters are constructed. They have most properties of the corresponding curves.