← Back

Introduction to Computer Vision and Image Processing

IBM · View on Coursera ↗

Or see the score while you browse.

Taught by Aije Egwaikhide, Joseph Santarcangelo

Data ScienceComputer Science

Coursera
4.3
headline rating
↓
2.2
gap
Starisk
2.1
Inflated

About the course

Unlock the power of computer vision to add intelligence to images and videos! This course equips you with practical skills to understand and apply computer vision (CV)—a rapidly growing branch of AI and machine learning that drives innovations from self-driving cars to augmented reality.

Read more

Through guided, hands-on labs using Python, Pillow, and OpenCV, you’ll perform essential image processing tasks such as filtering, enhancement, classification, and object detection—all within JupyterLab Notebooks for a seamless learning experience. By the end of the course, you’ll apply transfer learning with a pre-trained deep neural network to build an image classification model, experimenting with different hyperparameters to enhance its performance on a provided dataset. To take this, you need to have a foundational knowledge of Python, machine learning, and deep learning. In just a few weeks, you’ll learn to turn pixels into insights and launch your journey into AI-powered visual intelligence. Enroll today and start creating the future with computer vision!

The dissent

The most-upvoted critical review (62 votes, 1.0★).

“Another course with potential, ruined by a flakey operational platform. IBM Cloud as provisioned in this course is not fit for purpose, end of story. Exercises are often impossible to do because servers, storage or proxies in the IBM cloud are down, and the instructions are not always complete either.”

1.0 / 5

Read the full review on Coursera ↗

Coursera's 4.3 comes from 1,440 ratings. Of those, 9.1% are 1–2★.

Starisk reads the reviews learners voted most helpful, and weights each by the square root of its votes: a review with 80 upvotes counts about five times one with 2. Unvoted reviews are not skipped out of laziness — by this model they carry no evidence that other students endorsed them.

That measures what the most-endorsed reviews say, not “true quality.” The rating distribution above is the whole population, so you can see the sample next to it.

Reviews read on 3 Nov 2026.Read them on Coursera ↗