Learn

1. Images as ArraysWhat a digital image really is, and how NumPy and OpenCV store it.Beginner

1. Chapter 1 · IntroductionWhat digital image processing is, where it came from, which parts of the electromagnetic spectrum it works with, and the roadmap of fundamental steps this series follows.Beginner
2. Chapter 2 · Digital Image FundamentalsHow eyes and cameras turn light into numbers, how sampling and quantization shape a digital image, and the basic math every later chapter builds on.Beginner
3. Chapter 3 · Intensity Transformations and Spatial FilteringRemap pixel values with curves and histograms, then smooth and sharpen images with small kernels: the everyday toolbox of spatial-domain enhancement.Beginner
4. Convolution & Image FilteringBlur, sharpen and find edges by sliding a 3×3 kernel across an image.Beginner
5. Chapter 4 · Filtering in the Frequency DomainHow the Fourier transform turns an image into a recipe of waves, and how editing that recipe smooths, sharpens and removes periodic noise.Intermediate
6. Chapter 5 · Image Restoration and ReconstructionModel how an image was damaged by blur and noise, then undo it with order-statistic, notch, inverse, Wiener and constrained least squares filters, and rebuild CT slices from projections.Intermediate
7. Chapter 6 · Color Image ProcessingHow color is measured and encoded, how to convert between RGB, HSI and L*a*b*, and how to transform, filter and segment color images.Intermediate
8. Chapter 7 · Wavelet and Other Image TransformsTreat every image transform as a change of basis, then build up from the DCT and Walsh–Hadamard transforms to Haar, multiresolution analysis and the fast wavelet transform.Intermediate
9. Chapter 8 · Image Compression and WatermarkingHow images are squeezed into fewer bits, from entropy and Huffman codes to JPEG, JPEG 2000 and learned codecs, and how hidden marks are written into them.Intermediate
10. Chapter 9 · Morphological Image ProcessingProbe shapes with small structuring elements: erosion, dilation, opening, closing, hit-or-miss, skeletons, reconstruction and grayscale morphology, with scikit-image code.Intermediate
11. Chapter 10 · Image Segmentation I: Edge Detection, Thresholding, and Region DetectionSplit an image into meaningful parts: find edges with gradients, LoG and Canny, link them with the Hough transform, pick thresholds with Otsu, and grow, cluster, cut and flood regions.Advanced
12. Chapter 11 · Image Segmentation II: Active Contours — Snakes and Level SetsSegment objects with curves that move: parametric snakes, gradient vector flow, balloon forces, and level-set methods such as geodesic active contours and Chan–Vese.Advanced
13. Chapter 12 · Feature ExtractionTurn regions, boundaries and whole images into compact numbers that stay the same when the object moves, turns, grows or changes brightness, from chain codes and GLCM texture to Harris, MSER and SIFT.Advanced
14. Chapter 13 · Image Pattern ClassificationFrom minimum-distance and Bayes classifiers to perceptrons, backpropagation and convolutional neural networks: how a computer decides what an image or region shows.Advanced

Coming soon

1. ML 01 · Introduction to Machine LearningWhat it means for a computer to learn from data: the learning paradigms, linear and logistic regression, cost functions, gradient descent, overfitting and evaluation, built from scratch in NumPy.Beginner
2. ML 02 · Neural Networks from Perceptron to Deep NetworksFrom a single perceptron to deep networks: activations, normalization, output layers and losses, backpropagation, optimizers, and the habits that make a network train and generalize.Intermediate

1. DL 01 · Deep Learning for Image Processing and Computer VisionHow deep learning reorganizes image processing, image analysis and computer vision: from the classical pattern-recognition pipeline to CNNs, Vision Transformers, self-supervised backbones and promptable foundation models.Intermediate
2. DL 02 · Deep Image ClassificationHow deep networks decide what an image shows: losses and metrics, datasets, the CNN and transformer architectures and why they were designed that way, modern training recipes, pre-training, robustness, calibration and interpretability.Advanced
3. DL 03 · Object Detection: From R-CNN to DETRHow deep networks find and label every object in an image: box regression, IoU, anchors, NMS and feature pyramids; two-stage, one-stage, anchor-free and transformer detectors; open-vocabulary models; and how detection is measured.Advanced
4. DL 04 · Deep Image Restoration: Low-Level VisionOne degradation model, many tasks: how deep networks undo blur, noise, low resolution, haze, rain, snow and darkness, from SRCNN and DnCNN to Restormer, all-in-one models and diffusion priors.Advanced
5. DL 05 · Low-Light Image EnhancementFrom histogram equalization and Retinex to curve estimation, Retinex transformers and diffusion models: how to brighten dark photos without amplifying noise, shifting colors or fooling the metrics.Advanced
6. DL 06 · Object Tracking: From Single-Object to Multi-ObjectHow computer vision follows objects through video: re-identification, single-object trackers from correlation filters to transformers and SAM 2, and multi-object tracking with Kalman filters, Hungarian matching, end-to-end models and the MOTA/IDF1/HOTA metrics.Advanced