HW
Hannah Weiss
3 days ago
Rare mix of depth and readability. The worked examples are the clearest I have seen on this subject.
Free preview available. Sign in and subscribe to unlock the full book.
Vizuara AI Labs · intermediate
Computer Vision Bootcamp
From OpenCV pixels to detection, segmentation, and deployment.
A hands-on tour through modern computer vision: image processing with OpenCV, object detection with the R-CNN family and YOLO, and pixel-level segmentation with Mask R-CNN and U-Net. Every architecture is built, coded from scratch, and shipped as a real project — from a burglar alarm to license-plate recognition and fall detection.
37 capsules142 figures~7 hoursby Dr. Raj Dandekar
Read on your Kindle or e-reader
Download the EPUB and read offline — perfect for the train. Works on Kindle, Kobo, Apple Books & more.
00Foundations of Computer Vision4 capsules
Foundations of Computer Vision — 4 chapters.
01What Is Computer Vision?conceptfree12 min02An Image Is a Tensorintuitionfree10 min03The CV Task Landscapeconcept🔒12 min04Your Toolchain: Python, NumPy, OpenCVcode🔒11 min01OpenCV and Classical Image Processing5 capsules
OpenCV and Classical Image Processing — 5 chapters.
05Reading Images and Videocode🔒11 min06Resizing, Cropping, and Color Spacescode🔒11 min07Blurring and Canny Edge Detectioncode🔒11 min08Drawing and Annotation on Imagescode🔒10 min09Project: A Motion-Based Burglar Alarmproject🔒11 min02OpenCV Meets Deep Learning3 capsules
OpenCV Meets Deep Learning — 3 chapters.
10Detection, Tracking, Counting, Segmentationconcept🔒11 min11The COCO Dataset and Pretrained YOLOconcept🔒11 min12Project: Real-Time Object Counting on Videoproject🔒12 min03Object Detection: The R-CNN Family5 capsules
Object Detection: The R-CNN Family — 5 chapters.
13What Object Detection Really Asksconcept🔒11 min14Intersection over Union (IoU)math🔒12 min15R-CNN: Selective Search and Warpsconcept🔒10 min16Fast R-CNN and Faster R-CNNconcept🔒12 min17Project: Faster R-CNN in Colabproject🔒12 min04Instance Segmentation with Mask R-CNN4 capsules
Instance Segmentation with Mask R-CNN — 4 chapters.
18Detection vs Segmentationconcept🔒10 min19The Mask R-CNN Architectureconcept🔒11 min20RoI Pooling vs RoI Aligndeep-dive🔒11 min21Project: Mask R-CNN for Pedestriansproject🔒9 min05Semantic Segmentation with U-Net5 capsules
Semantic Segmentation with U-Net — 5 chapters.
22The Encoder-Decoder Ideaintuition🔒11 min23U-Net Architecture and Skip Connectionsconcept🔒11 min24Training U-Net: Loss and Metricsmath🔒12 min25U-Net Variants: Attention, Residual, U-Net++deep-dive🔒12 min26Project: Crack Detection and Hugging Face Hostingproject🔒12 min06Real-Time Detection with YOLO5 capsules
Real-Time Detection with YOLO — 5 chapters.
27You Only Look Onceconcept🔒11 min28The Grid, Boxes, and Class Probabilitiesmath🔒12 min29Confidence, NMS, and YOLO vs R-CNNconcept🔒12 min30Fine-Tuning YOLOv8 with Transfer Learningcode🔒11 min31Project: License Plate Recognition with OCRproject🔒11 min07Data, Roboflow, and Shipping Apps4 capsules
Data, Roboflow, and Shipping Apps — 4 chapters.
32Datasets, Annotation, and Roboflowconcept🔒12 min33Training and Roboflow Universecode🔒13 min34Deploying with Streamlitcode🔒12 min35Project: Elderly Fall Detectionproject🔒12 min08Putting It All Together2 capsules
Putting It All Together — 2 chapters.
36Choosing the Right Architectureintuition🔒11 min37Capstone: Ship Your Own Vision Systemproject🔒11 minRatings & reviews
1,469 readersRate this book
EP
Elena Petrova
4 months ago
I read the free preview on a whim and ended up finishing the whole thing in two sittings. Superb pacing.
ML
Mei Lin
7 months ago
Finally a book that explains the hard parts without hand-waving. The figures alone are worth it.