#36 Spatial Domain Filtering | Modern Computer Vision скачать в хорошем качестве

#36 Spatial Domain Filtering | Modern Computer Vision

Welcome to 'Modern Computer Vision' course ! Building on the previous lecture, we'll revisit the Laplacian of the Gaussian (LoG) and see how a difference of Gaussians (DoG) can approximate it, offering computational benefits. We'll then shift our focus to the popular Gaussian filter, a smoothing filter used in image processing. We'll learn how to construct a discrete version of this filter with a specific standard deviation and understand how it differs from a uniform filter. Get ready to be surprised by unsharp masking, a technique that sharpens images by actually blurring them first. We'll also tackle the problem of denoising, specifically addressing additive white Gaussian noise (AWGN) and salt and pepper noise. We'll learn how averaging multiple images can reduce noise and how this idea is applied locally using filters. For pesky salt and pepper noise, we'll introduce the median filter, which effectively removes outliers. NPTEL Courses permit certifications that can be used for Course Credits in Indian Universities as per the UGC and AICTE notifications. To understand various certification options for this course, please visit https://nptel.ac.in/courses/108106189 #LaplacianOfTheGaussian #DifferenceOfGaussians #GaussianFilter #UnsharpMasking #Denoising #SaltAndPepperNoise #MedianFilter