Artificial Intelligence & Data Science is coming soon
We're still writing and reviewing the notes for every subject, and we'll open it when every subject is ready. Meanwhile you can practise aptitude, ask Aria about any subject, or see the branches that are ready.
Artificial Intelligence & Data Science
Computer Vision
Image fundamentals, filtering and noise, frequency domain and edges, features and segmentation, detection.
Notes for Computer Vision are being written and reviewed. Until they're up, Aria teaches every topic — ask for any part of the syllabus, with worked numericals.
Coming next in Computer Vision
- Computer vision pipeline· notes coming
- Digital image representation· notes coming
- Sampling and quantisation· notes coming
- Colour models· notes coming
- Intensity transformations· notes coming
- Histogram equalisation· notes coming
- Convolution and smoothing filters· notes coming
- Sharpening filters· notes coming
- Noise models and noise removal· notes coming
- Fourier transform of images· notes coming
- Frequency domain filtering· notes coming
- Gradient edge detectors· notes coming
- Canny edge detector· notes coming
- Corner detection· notes coming
- Texture analysis· notes coming
- Thresholding and Otsu's method· notes coming
- Region-based segmentation· notes coming
- Morphological operations· notes coming
- Shape descriptors· notes coming
- Object detection· notes coming
- Object tracking with Kalman filters· notes coming
- Optical flow· notes coming
- Stereo vision and depth· notes coming
- Face detection and recognition· notes coming
- Wavelet-based image enhancement· notes coming
- Image transforms: DFT, DCT, Walsh-Hadamard and Haar· notes coming
- Restoration with mean and order-statistic filters· notes coming
- Texture features: GLCM, LBP and Gabor filters· notes coming
- Background subtraction and motion segmentation· notes coming
- SIFT, SURF and BRISK features· notes coming
- Bag of visual words· notes coming
- Classifying image features: SVM, KNN and random forests· notes coming
- CNNs for image classification· notes coming
- Vision transformers· notes coming
- GANs for images· notes coming
- R-CNN family, SSD and YOLO· notes coming
- Semantic segmentation with U-Net· notes coming
- Centroid-based object tracking· notes coming
- Image compression: redundancy and fidelity criteria· notes coming
- Lossless compression: Huffman, LZW and run-length coding· notes coming
- Transform coding and image file formats· notes coming
- Hit-or-miss transform and morphological algorithms· notes coming
- Colour image processing and transformations· notes coming
- Binary shape analysis and skeletons· notes coming
- Active contours· notes coming
- Hough transform and RANSAC· notes coming
- Shape from shading and photometric stereo· notes coming
- Eigenfaces· notes coming
- Particle filters and tracking under occlusion· notes coming
- Vision for driver assistance: roads, signs and pedestrians· notes coming
- Generalised Hough transform· notes coming
- 3D object recognition and reconstruction· notes coming
- Structure from motion and bundle adjustment· notes coming
- Graph-based segmentation: normalised cuts and mean shift· notes coming
- Camera models and calibration· notes coming