Project 3: StructureFromMotion (Full Pipeline)

Image Segmentation is the process of partitioning an image into multiple segments(superpixels). The goal is to represent the image as something that is easier to analyze. In other words, image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain characteristics.

A function that aligns two sets of points using global image transformation (similarity, affine, or perspective) and returns T where T is a transformation that maps non-zero points in im1 to non-zero points in im2.

Template matching is a technique in digital image processing for finding small parts of an image which match a template image.

CIFAR-10 is an established computer-vision dataset used for object recognition. It is a subset of the 80 million tiny images dataset and consists of 60,000 32x32 color images containing one of 10 object classes, with 6000 images per class. Using this we develop a model that can classify images

The Gaussian pyramid provides a representation of the same image at multiple scales, using simple lowpass filtering and decimation techniques. The Laplacian pyramid provides a coarse representation of the image as well as a set of detail images (bandpass components) at different scales. This program generates both at various N values

A hybrid image is an image that is perceived in one of two different ways, depending on viewing distance, based on the way humans process visual input.

Semantic segmentation classifies image pixels into one or more classes which are semantically interpret able. CNNs for semantic segmentation typically use a fully convolutional network (FCN) architecture, which replaces the fully connected layers of a traditional CNN with convolutional layers.