First Principles of Computer Vision Specialization Certificate

Offered By - Columbia University on Coursera: (https://www.coursera.org/specializations/firstprinciplesofcomputervision)

📍 About Professional Certificate

• This specialization presents the first comprehensive treatment of the foundations of computer vision. It focuses on the mathematical and physical underpinnings of vision and has been designed for learners, practitioners and researchers who have little or no knowledge of computer vision.

• The program includes a series of 5 courses. Any learner who completes this specialization has the potential to build a successful career in computer vision, a thriving field that is expected to increase in importance in the coming decades.

What you will learn :

• Master the working principles of a digital camera and learn the fundamentals of imaging processing

• Create a theory of feature detection and develop algorithms for extracting features from images

• Explore novel methods for using visual cues (shading, defocus, etc.) to recover the 3D shape of an object from multiple images or viewpoints

• Get exposed to fundamental perceptions tasks such as image segmentation, object tracking, and object recognition

📙 Course Structures

There are 5 Courses in this Certificate Specialization as follows:

• Course-1 : Camera and Imaging

What you will learn :

• Learn how a camera works and how an image is formed using a lens

• Understand how an image sensor works and its key characteristics

• Design cameras that capture high dynamic range and wide angle images

• Learn to create binary images and use them to build a simple object recognition system

• Course-2 : Features and Boundaries

What you will learn :

• Learn how to detect edges and corners in images.

• Develop active contours (snakes) to find complex object boundaries.

• Learn about the Hough Transform for finding simple parametric shapes in images.

• Learn about image transformations and how to estimate the homography between two images.

• Course-3 : 3D Reconstruction - Single Viewpoint

What you will learn :

• Learn radiometric concepts related to light and how it interacts with scenes.

• Understand reflectance models and the different physical mechanisms that determine the appearance of a surface.

• Develop a method for recovering the shape of a surface from its shading.

• Understand the principle of photometric stereo where a dense surface normal map of the scene is obtained by varying the illumination direction.

• Course-4 : 3D Reconstruction - Multiple Viewpoints

What you will learn :

• Develop a comprehensive model of a camera and learn how to calibrate a camera by estimating its parameters.

• Develop a simple stereo system that uses two cameras of known configuration to estimate the 3D structure of a scene.

• Design an algorithm for recovering both the structure of the scene and the motion of the camera from a video.

• Develop optical flow algorithms for estimating the motion of points in a video sequence.

• Course-5 : Visual Perception

What you will learn :

• Design algorithms for detecting meaningful changes in a scene

• Develop methods for tracking objects in a video while the object undergoes changes in pose and illumination

• Learn several approaches to segmenting an image into meaningful regions

• Create an end-to-end pipeline for learning and recognizing objects based on their visual appearance