Overview

Introduction to Computer Vision guides learners through the essential algorithms and methods to help computers 'see' and interpret visual data. You will first learn the core concepts and techniques that have been traditionally used to analyze images. Then, you will learn modern deep learning methods, such as neural networks and specific models designed for image recognition, and how it can be used to perform more complex tasks like object detection and image segmentation. Additionally, you will learn the creation and impact of AI-generated images and videos, exploring the ethical considerations of such technology. This course can be taken for academic credit as part of CU Boulder’s MS in Data Science or MS in Computer Science degrees offered on the Coursera platform. These fully accredited graduate degrees offer targeted courses, short 8-week sessions, and pay-as-you-go tuition. Admission is based on performance in three preliminary courses, not academic history. CU degrees on Coursera are ideal for recent graduates or working professionals. Learn more: MS in Data Science: https://www.coursera.org/degrees/master-of-science-data-science-boulder MS in Computer Science: https://coursera.org/degrees/ms-computer-science-boulder

Syllabus

Image, Function, and Transform

Welcome to Introduction to Computer Vision, the first course in the Computer Vision specialization. In this first module, you'll be introduced to how this course operates "by Hand" and "in Excel." Then, you'll build a foundation in image matrices and arrays to explore different image types: binary, grayscale, and RGB. Next, you'll transition into using functions to perform basic image operations such as addition, negation, and masking. You'll then be introduced to the concept of image transformation through linear algebra. Finally, you'll perform translation, scaling, and rotation matrix operations.

Feature and Compare

This module dives into feature extraction—quantitative measures that describe image content. Students compute features such as image mass, center, and statistical moments to describe the shape and structure of images. These are implemented both manually and in Excel. The module also explores how to compare images using distance metrics and similarity measures, offering insight into how visual data can be analyzed, categorized, and classified.

Filter 1D & 2D

Filtering techniques are central to detecting patterns in images. This module introduces learners to 1D and 2D filters, covering foundational concepts like convolution, cross-correlation, and Gaussian smoothing. Through both manual and spreadsheet-based exercises, learners apply various filters (e.g., mean, Laplacian, Sobel) and morphological operations like dilation and erosion. These filtering methods enhance image features, detect edges, and prepare data for further processing.

Camera and Epipolar

This module delves into key concepts of camera models and their role in computer vision and photogrammetry. You will learn about the Extrinsic Matrix, exploring how it defines the position and orientation of a camera in 3D space. Understand the Pinhole Camera Model, a simplified optical system that forms the basis for many computer vision applications, alongside the Intrinsic Matrix, which captures the internal parameters of the camera. Epipolar geometry is examined, with a focus on its significance in 3D reconstruction and stereo vision. The module covers the motivation behind epipolar geometry, breaking down its basic components, and explaining the Essential Matrix, which encapsulates the geometric relationship between camera views, as well as the Fundamental Matrix, a core component in epipolar geometry that represents the relationship between two cameras in stereo vision.