Optimal Edge Perservation in Volume Rendering Using Canny Edge Detector
N. Revathy, Srinivasan Janarthanam, Thangavel Karthikeyan · 2013
This paper presents a method to preserve sharp edge details in splatting for volume rendering. Conventional splatting algorithms produce fuzzy images for views close to the volume model. Computing the weighted average of the pixel values in a window is a basic module in many computer vision operators. The process is reformulated in a linear vector space and the role of the different subspaces is emphasized Within this framework well known artifacts of the gradient-based edge detectors, such as large spurious responses can be explained quantitatively. Initialization of weights between the input and lone hidden layer by transforming pixel coordinates of the input pattern block into its equivalent one-dimensional representation. Initialization process exhibits better rate of convergence of the back propagation training compare to the randomization of initial weights. We propose a new guide edge linear interpolation technique via address filter and data fusion. For a pixel two sets of observation are defined in two orthogonal directions, and each set produces an estimated value of the pixel. Both multispectral (MS) and panchromatic (PAN) images are provided with different spatial and spectral resolutions. Multispectral classification detects object classes only according to the spectral property of the pixel. These estimates of direction, following the model the different measures of the lack of noisy pixels are fused by linear least mean square estimation error (LMMSE) technique in a more robust estimate, and statistics two sets of observations. Panchromatic image segmentation enables the extraction of detailed objects, like road networks, that are useful in map updating in Geographical Information Systems (GIS), environmental inspection, transportation and urban planning, etc. It also presents a simplified version to reduce computational cost without sacrificing much the interpolation performance.