📚 Syllabus & Course Curriculum
Data Science & Analytics
Module-by-module breakdown of Computer Vision with OpenCV, from foundations to a certified capstone project.
Images
• Pixels, colour spaces and the conversions that fix most beginner bugs
• Reading, writing and displaying with OpenCV, including the BGR convention
• Histograms, thresholding and contrast operations
Processing
• Convolution, blurring, sharpening and noise removal
• Edge detection with Canny and the parameter sensitivity behind it
• Erosion, dilation, opening and closing for cleaning binary masks
Features
• Corner and keypoint detection with Harris, SIFT and ORB
• Descriptor matching, homography estimation and RANSAC for outliers
• Image stitching and template matching, with their failure conditions
Geometry
• Camera model, intrinsics, distortion and calibration with a chessboard
• Optical flow and object tracking across frames
• Background subtraction for video and the lighting changes that defeat it
Deep Vision
• The dnn module for running pretrained detection and segmentation models
• Face and object detection compared against the classical cascade approach
• Choosing between a classical pipeline and a network on cost and data grounds
Earn government-registered certification in Computer Vision with OpenCV
e-Certificate and e-Marksheet issued on successful completion.
