36 skills found · Page 1 of 2
JiangWZW / Realtime GPU Contour Curves From 3D MeshA real-time, GPU-driven method to generate 2D curves from 3D mesh’s contour.
zhang-tao-whu / E2ecE2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation
gaomingqi / FACM[ICIP 2016] A MATLAB implementation of the texture segmentation method in paper: "A factorization based active contour model for texture segmentation", IEEE International Conference on Image Processing (ICIP 2016).
zalkikar / BBOX GradCAMBoundary box creation using a GradCAM heat-map from a pre-trained image classification model.
majroy / PyCMA collection of visualization and data processing tools written in Python for performing the contour method for determining residual stress
Tsarpf / ProcgenReal-time meshing the contours of 3D scalar fields with the dual contouring algorithm in plain C++ and OpenGL/CUDA. Along with seam handling and growable octrees.
oesteban / RegSegRegSeg is a simultaneous segmentation and registration method that uses active contours without edges (ACWE) extracted from structural images. The contours evolve through a free-form deformation field supported by the B-spline basis to optimally map the contours onto the data in the target space.
Mahtab-Shabani / Retinal Blood Vessel Segmentation By Active ContourIn this project, I implement an enhanced active contour method that uses discrete wavelet transform for energy minimization to increase the accuracy.
swatijha2496 / FACE RECOGNITION USING OPENCV IN PYTHONFace is most commonly used biometric to recognize people. Face recognition has received substantial attention from researchers due to human activities found in various applications of security like airport, criminal detection, face tracking, forensic etc. Compared to other biometric traits like palm print, Iris, finger print etc., face biometrics can be non-intrusive. They can be taken even without user’s knowledge and further can be used for security based applications like criminal detection, face tracking, airport security, and forensic surveillance systems. Face recognition involves capturing face image from a video or from a surveillance camera. They are compared with the stored database. Face biometrics involves training known images, classify them with known classes and then they are stored in the database. When a test image is given to the system it is classified and compared with stored database. Face biometrics is a challenging field of research with various limitations imposed for a machine face recognition like variations in head pose, change in illumination, facial expression, aging, occlusion due to accessories etc.,. Various approaches were suggested by researchers in overcoming the limitations stated. 72 Automatic face recognition involves face detection, feature extraction and face recognition. Face recognition algorithms are broadly classified into two classes as image template based and geometric feature based. The template based methods compute correlation between face and one or more model templates to find the face identity. Principal component analysis, linear discriminate analysis, kernel methods etc. are used to construct face templates. The geometric feature based methods are used to analyze explicit local features and their geometric relations (elastic bung graph method). Multi resolution tools such as contour lets, ridge lets were found to be useful for analyzing information content of images and found its application in image processing, pattern recognition, and computer vision. Curvelets transform is used for texture classification and image de-noising. Application of Curvelets transform for feature extraction in image processing is still under research.
jnuber / RaspberryPi Object Tracking USB WebCam# This object tracking solutions utilize the "Triangle Similarity" method. # In brief, the triangle similarity takes an object (marker) with a known # width. The object is placed at some distance from the camera. Preferably # the same camera to be used for detection and tracking. # # A photo/image is taken of the object using the same camera to be used for # object detection. We then measure the apparent width in pixels. Using # this image as a fixed reference point, if the camera moves away from the # object, the number of pixels measuring the object's width decreases. If # the camera moves closer to the object, the number of pixels increases. # One can calculate the distance with pretty good accuracy. The higher the # quality of the reference image, the better the accuracy. These attributes # include: good lighting, good color contrast, accurate distance, as close to # 90% camera angle as possible. In some cases, camera calibration and # focal length maybe required. However I found using the piCam,pinhole or # fish-eye distortion wasn't an issue. # # Solution Approach # This solution uses a reference or calibration image of the object to # track. The object/marker width is determined by the number of pixels. # Once this has been established, the main loop does the following: # - looks for an object with similar contours as the reference object # - if found, target identified # - determines target width in pixels # - calculates distance based on a % difference from the # reference/calibration image # - locate target center # - display/print target details # - for Raspberry Pi, get CPU temperature as well. # # This version previews the target, paints the target's boarders and provides # target data on the preview screen. This an excellent method of viewing # and debugging the code. Also included were performance stats for the # various functions. If using for robotics or autonomous mode, all the # above can be commented/removed for maximum performance. Through testing, # with good target LIGHTING, I was achieving 30+ FPS. (Raspberry Pi 3, # piCam ver2, Multitheaded Camera streaming feed, Python 3.6.
JamesPardue / RadialDualContouringProject extends on Dual Contouring mesh generation methods in order to make them performant enough for extensive real time use by scaling voxel size with distance from point of interest.
huoguanying / MERSF Sonar Image SegmentationA Robust and Fast Method for Sidescan Sonar Image Segmentation Using Nonlocal Despeckling and Active Contour Model
turtleizzy / Pytorch IctmA pytorch implementation of Geodesic Active Contour & Chan-Vese model on 2d/3d image solved with iterative convolution-thresholding method (ICTM).
gjpelletier / Delta MethodConfidence and prediction intervals for nonlinear regression using the delta-method or parametric bootstrap, bivariate KDE contour plots, and bivariate quantile plots for Python and Jupyter Notebook
pratikgirigoswami / Exemplar Based Image Inpainting• Image inpainting is the process of seamlessly filling in holes of arbitrary topology in an image to preserve its overall continuity. It is an ancient art of fixing accidental damage and recreating lost information. • Object removal or modification in the original images can be carried out through image inpainting methods. • In this project, various algorithms of Partial Derivative Equation based and Exemplar-based families have been studied and implemented. Results using Total Variation (TV) and Curvature Driven Diffusion (CDD) methods show that CDD produces a better visual quality of results. However, it fails to restore texture information. • To solve this problem, Exemplar-based algorithms are studied and implemented. Traditionally, the data term present in this algorithm is based on the strength of the isophote found using the gradient. The problem with the gradient operator is studied, and a better contour preserving data term is proposed. The proposed data term uses the strength of structure line found using Infinite size Symmetric Exponential Filter (ISEF). This filter helps overcome the drawback of which overcomes the drawback of insensibility to noise and precision of edge localization present in traditional data term. • Results are compared by quantitative analysis using PSNR, SSIM, and FSIM. Subjective analysis is done using Mean Opinion Score. It is proved that the proposed method produces better visual results compared to few other existing exemplar-based methods. • Methods/Keywords: Exemplar-based Image Inpainting, PDE-based Image Inpainting, ISEF Filter, Priority Computation, Isophote, Curvature Driven Diffusion • Software/Tools/Programming Language Used: MATLAB, C
HomerReid / LibBeynC++ and Julia implementations of Beyn's contour-integral method for nonlinear eigenproblems
ZhiyaoZhao / Towards Measuring Shape Similarity Of Polygons Based On Multiscale Features And Grid Context DescripIn spatial analysis application, measuring the shape similarity of polygons is crucial for polyg-onal object retrieval and shape clustering. As a complex cognition process, measuring shape similarity should be able to find out the difference of polygons as objects in observation in terms of visual perception and the difference of the region, boundary, and structure formed by the polygons from the mathematic point of view. In the existing approaches, shape similarity of polygons is calculated by only comparing their mathematic characteristics while not taking the human perception into consideration. Aiming to solve this problem, we use the features of con-text and texture of polygons, since they are basic visual perception elements to fit the cognition purpose. In this paper, we propose a contour diffusion method for the similarity measurement of polygons. By converting a polygon into grid representation, the contour feature is represent-ed as a multiscale statistic feature, and the region feature is transformed into condensed grid context features. Instead of treating shape similarity as a distance between two representations of polygons, the proposed method observes it as a correlation between textures extracted by shape feature. The experiments show that the accuracy of the proposed method is superior to that of the turning function and Fourier descriptor.
PrathamNawal / YOLO Object DetectionCompared different methods of object detection i.e HOG + SVM , Contour plot and Yolo Object Detection
zyangalex / Themodynamic And Heat Transfer Visualization Transient Two Dimensional ConductionNumerically solves the transient two dimensional conduction problem using the finite difference method and plots color contour plot. Assumes transient 2D conduction with constant properties.
valenpe7 / Scientific Visualizationcollection of methods for scattered data interpolation, colormaps and iso-contours calculation, export to .kml (Google Earth))
