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 students, practitioners and researchers who have little or no knowledge of computer vision. The program includes a series of 5 courses. Course 1, Camera and Imaging, is focused on the camera and the fundamentals of image processing, and Course 2, Features and Boundaries, describes the extraction of image features and their use in real-world application. Course 3, 3D Reconstruction - Single Viewpoint, develops tools for recovering the 3D geometry of a scene from one or more images, and Course 4, 3D Reconstruction - Multiple Viewpoints, shows how the structure of a scene can be computed using a moving camera. Finally, Course 5, Visual Perception, covers fundamental perception tasks such as image segmentation and object recognition. We believe any student who performs well in the assessments that come with the 5 courses, 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.

Courses included in the Specialization:

  • Camera and Imaging
  • Features and Boundaries
  • 3D Reconstruction - Single Viewpoint
  • 3D Reconstruction - Multiple Viewpoints
  • Visual Perception

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 images.
  • Develop techniques for recovering detailed scene geometry from multiple images taken from different viewpoints.
  • Get exposed to fundamental perceptions tasks such as image segmentation, object tracking, and object recognition.

Mastery of this program can pave the way to a successful career as a computer vision engineer or a computer vision scientist. Such individuals are in great demand not only in the field of computer vision, but also fields that rely heavily on computer vision such as driverless cars, robotics, factory automation, medical imaging, biometrics and security, digital photography, computer graphics, virtual reality, augmented reality, interactive games, human-computer interfaces, and remote exploration.

The program is designed to provide the knowledge and skills in the following areas:

  • Computer vision hardware engineer
  • Computer vision software engineer
  • Computer vision researcher/scientist

Computer vision is indispensable to many disciplines of science and engineering. This program provides a comprehensive treatment of the mathematical and physical principles of computer vision. This foundational exposure can provide a student with a unique edge in a field that is transforming the way we live our lives.

How to enroll:

You can register for the course on Coursera.

Note to the learners:

These are non-credit, non-degree bearing courses offered by Columbia University on Coursera. For all questions regarding enrollment, payment, financial aid or technical issues, please reach out to Coursera help center.