görüntü-işleme

Learn to build a basic OCR application using kNN knowledge. We use OpenCV's digits.png dataset to recognize handwritten digits achieving ~91% accuracy.

Learn the concepts of the k-Nearest Neighbour (kNN) algorithm. We cover classification, feature space, weighted kNN, and implement a simple example with OpenCV.

Learn to create a depth map from stereo images. We cover cv.StereoBM.create() for disparity map computation and the parameters for tuning the results.

Learn the basics of multiview geometry. We cover epipole, epipolar lines, epipolar constraint, Fundamental Matrix and Essential Matrix, with OpenCV code to find and draw epilines.

Learn to exploit the calib3d module to create 3D effects in images. We cover cv.solvePnP() and cv.projectPoints() to draw 3D coordinate axes and a cube on a chessboard.

Learn about types of distortion caused by cameras and how to find intrinsic/extrinsic properties. We cover cv.calibrateCamera() and cv.undistort() using a chessboard pattern.

Learn background subtraction techniques to detect moving objects in video streams. We cover cv.createBackgroundSubtractorMOG2() and KNN-based background subtraction.

Learn optical flow using Lucas-Kanade and Farneback methods. We cover cv.calcOpticalFlowPyrLK() for sparse and cv.calcOpticalFlowFarneback() for dense optical flow.

Learn to use Meanshift and Camshift algorithms for object tracking in video. We cover cv.meanShift() and cv.CamShift() for histogram-based object tracking.