Call us: 
Advanced Diploma in Computer Vision
-
By
NPTEL
- 27/07/2020
Course Description
In this free online course, you are introduced to the exciting field of computer vision. You will learn about the technologies, applications, benefits and science.
The course begins with the fundamental principles of image processing. It then covers the principles of projective geometry and homography. Computations of projection camera matrices are presented, as well as important concepts relating to epipolar geometry. You will study the techniques involved in feature detection and learn about the frameworks necessary for feature matching and model fitting.
This course will be of interest to students studying computer imaging and AI technologies. It will also be of interest to those working in the industry or those wishing to gain employment in this area. Start this course today and learn more about computer vision and its applications.
What you'll learn in this course?
-
Image Processing
-
Technology
-
Deep Learning
-
Computer Science
-
Computer Vision
Course Curriculum
- Learning Outcomes
- Projective Geometry
- Projective Space
- Projective Geometry II
- Projective Plane
- Conics
- Projective Transformation
- Homography Matrix
- Direct Linear Transformation
- Homography I
- Computation of Homography
- Homography II
- Properties of Projective Transformation
- Homography III
- Angles Under Homography
- Lesson Summary
- Learning Outcomes
- Feature Detection and Description I
- Feature Detection
- Feature Detection and Description II
- Scale Invariant Detection
- Feature Detection and Description III
- Detectors and Descriptors
- Feature Detection and Description IV
- Local Binary Pattern
- Co-occurence Matrix
- Feature Detection and Description V
- Global Image Descriptor
- Lesson Summary
- Learning Outcomes
- Feature Matching and Model Fitting I
- Matching Criteria
- Feature Matching and Model Fitting II
- Applications of K-D Tree
- Feature Matching and Model Fitting III
- Model Fitting
- Feature Matching and Model Fitting IV
- Model Fitting Frameworks
- Feature Matching and Model Fitting V
- Space Representation
- Lesson Summary
- Learning Outcomes
- Clustering and Classification I
- Lloyd Implementation
- Clustering and Classification II
- Naive Bayes Classification
- Clustering and Classification III
- Linear Discriminant Analysis
- Clustering and Classification IV
- Batch Relaxation and Perceptron Model
- Clustering and Classification V
- Gradient Computation
- Delta Rule and Model Classifier
- Lesson Summary
- Learning Outcomes
- Dimensional Reduction and Sparse Representation I
- Principal Component Algorithm
- Dimensional Reduction and Sparse Representation II
- Measure of Separation
- Dimensional Reduction and Sparse Representation III
- Matching Pursuit
- Dimensional Reduction and Sparse Representation IV
- K - Means Clustering
- Lesson Summary
- Learning Outcomes
- Deep Neural Architecture I
- Supervised Learning
- Deep Neural Architecture II
- Convolution Neural Networks
- Deep Neural Architecture III
- Deep Neural Networks
- Deep Neural Architecture IV
- Regional Convolutional Neural Networks
- Deep Neural Architecture V
- Convolution Operations
- Semantic Segmentation
- Deep Neural Architecture VI
- Recurrent Neural Network
- Lesson Summary
NPTEL
India
Duration
Modules
Certifications
