Computer Vision and Image Processing - Fundamentals and Applications | EveryEng

Skip to main content

Self-paced Advanced

Computer Vision and Image Processing - Fundamentals and Applications

3(115)

170 views

FREE

1258 min

Anytime

English

170 views

Engineering AcademyLearn Without Limits: Free Engineering Courses

Industrial Automation

Artificial Intelligence

Lifetime access
Certificate of completion
Anytime Learning
Learn from Industry Expert

Volume pricing for groups of 5+

Why enroll

This course is ideal for students who want a strong foundation in computer vision and image processing. It helps learners prepare for research, higher studies, or industry roles by connecting theory with real-world applications.

Your instructor

Engineering Academy

Engineer

Learn Without Limits: Free Engineering Courses

5+ yrs experience·India

Is this course for you?

You should take this if

You work in Industrial Automation
You're a Artificial Intelligence / Computer Science professional
You have 3+ years of hands-on experience in this field
You want to build skills in Engineering & Design, Project Management

You should skip if

You're new to this field with no prior experience
You need a different specialisation outside Artificial Intelligence
You need live interaction with an instructor

Course details

This course introduces students to the basic ideas and methods used in Computer Vision and Image Processing. It explains how images are captured using cameras and how images are formed using different models. Students will learn fundamental image processing techniques such as enhancement, filtering, and transformation. The course covers feature extraction and selection methods used for pattern recognition and classification. Advanced topics like motion estimation, object detection and tracking, image classification, and scene understanding are also introduced. Concepts such as image fusion and image registration are explained with practical relevance. The course focuses on building a strong foundation rather than just tools. It helps students understand how vision systems work in real applications. Overall, the course prepares learners to explore advanced research and practical problems in computer vision.

Source: NPTEL IIT Guwahati [Youtube Channel]

Course suitable for

Key topics covered

Computer Vision and Image Processing – Fundamentals and Applications
Introduction to Computer Vision
Introduction to Digital Image Processing
Image Formation: Radiometry
Shape from Shading
Image Formation: Geometric Camera Models – I
Image Formation: Geometric Camera Models – II
Image Formation: Geometric Camera Models – III
Image Formation in a Stereo Vision Setup
Image Reconstruction from a Series of Projections
Image Reconstruction from a Series of Projections – I
Image Transforms – I
Image Transforms – II
Image Transforms – III
Image Transforms – IV
Image Enhancement
Image Filtering – I
Image Filtering – II
Colour Image Processing – I
Colour Image Processing – II
Image Segmentation
Image Features and Edge Detection
Edge Detection
Hough Transform
Image Texture Analysis – I

Course content

The course is readily available, allowing learners to start and complete it at their own pace.

25 lectures20 hr 58 min

Computer Vision and Image Processing – Fundamentals and Applications
8 min
Introduction to Computer Vision
46 min
Introduction to Digital Image Processing
55 min
Image Formation: Radiometry
41 min
Shape From Shading
48 min
Image Formation: Geometric Camera Models - I
31 min
Image Formation: Geometric Camera Model - II
21 min
Image Formation: Geometric Camera Model - III
69 min
Image Formation in a Stereo Vision Setup
61 min
Image Reconstruction from a Series of Projections
42 min
Image Reconstruction from a Series of Projections 1
32 min
Image Transforms - I
42 min
Image Transforms - II
58 min
Image Transforms - III
48 min
Image Transforms - IV
74 min
Image Enhancement
61 min
Image Filtering-I
60 min
Image Filtering-II
64 min
Colour Image Processing - I
41 min
Colour Image Processing - II
77 min
Image Segmentation
54 min
Image Features and Edge Detection
70 min
Edge Detection
59 min
Hough Transform
38 min
Image Texture Analysis - I
58 min

Opportunities that await you!

Skills & tools you'll gain

Engineering & Design

Project Management

Research & Developmnet

Career opportunities

FREE

Access anytime

Questions and Answers

Q: You're tuning a vision pipeline and googling 'why does increasing camera exposure time break optical flow accuracy in automotive vision'. Exposure time is doubled while vehicle speed and frame rate stay fixed; downstream optical flow vectors start saturating. What response actually stabilizes the system?

A: A trades spatial blur for motion blur and makes the aperture problem louder; B breaks SNR and shifts you into noise-driven gradients; C masks the symptom and violates physical motion constraints; D rebalances the imaging equation so brightness constancy holds again.

Q: Field returns trigger the search 'CNN classifier accuracy drops only at night ISO 26262 camera'. Daytime accuracy is nominal, but at night false positives spike with high ISO; histogram shows banding. What's the root cause?

A: A explains bias drift but not discrete banding; B is spatially sparse and transient; C correlates with bitrate not ISO; D aligns with sensor physics and the observed histogram steps.

Q: You're asked 'global shutter vs rolling shutter for fast moving vehicles computer vision' while locking a hardware spec. Objects move laterally at 25 m/s and latency must stay under 50 ms. What do you pick?

A: A optimizes marketing metrics at the expense of epipolar consistency; B shifts you into a different processing paradigm that's hard to certify; C mitigates symptoms but leaves residual skew; D preserves geometry so the math doesn't lie to you.

Q: Searching 'automotive camera housing corrosion road salt electrical failure', you review a camera mounted behind the grille with winter exposure. After two seasons, intermittent ground faults appear. What's the dominant degradation mechanism?

A: A degrades plastics optically rather than electrically; C yields repeatable fractures independent of salt; D doesn't match the environment or timescale; B matches the electrochemistry and symptom progression.