Course Objective & Scope
Computer vision projects often stall because of a poorly defined task, insufficient data or unrealistic accuracy expectations. This programme starts with how images are represented at pixel level and works hands-on through classical techniques such as colour spaces, filtering, and edge and corner detection with OpenCV.
Classification, object detection and segmentation are then distinguished, and a short prototype is built with pretrained models (torchvision, Ultralytics YOLO). Participants leave with a draft visual data pipeline built around a sample scenario from their own organisation.
Who Should Attend?
- Software developers new to computer vision
- Data scientists moving from tabular data to image data
- Product and technical project managers evaluating image-based projects
- Prerequisite: basic Python; no deep learning experience required
Key Takeaways
- Read, transform and preprocess images with OpenCV
- Map a business problem to the right computer vision task
- Produce classification and detection outputs with a pretrained model
- Interpret core metrics such as accuracy, precision, recall and IoU
- Roughly estimate the data, labelling and hardware needs of a use case
Curriculum
Digital Images and Colour Spaces
- Pixels, channels, resolution and bit depth
- RGB, HSV and greyscale conversions
Classical Image Processing with OpenCV
- Filtering, thresholding and morphological operations
- Edge, corner and contour detection
Computer Vision Task Types
- Differences between classification, object detection, segmentation and OCR
- Sample use cases and choosing a task
A First Prototype with Pretrained Models
- Inference with torchvision and Ultralytics YOLO
- Visualising outputs and failure examples
Data, Labelling and Metrics
- Data collection, labelling tools and dataset splits
- Evaluation with precision, recall and IoU
Other Courses in This Category
-
CNN architectures (ResNet, EfficientNet, ConvNeXt) in PyTorch, transfer learning, data augmentation and training loops, for developers and data scientists who need to train and evaluate image models on company data.
- Live Course
- 5 modules
-
Self-supervised learning (DINOv2), vision foundation models (SAM 2, Grounding DINO), synthetic data, active learning and large-scale training, for experienced computer vision engineers tackling hard production problems.
- Live Course
- 5 modules
-
Object detection and instance segmentation with YOLO, RT-DETR and Mask R-CNN: labelling, training, mAP-based evaluation and tracking integration, for teams building an end-to-end detection/segmentation prototype.
- Live Course
- 5 modules
-
Computer Vision Bootcamp
Comprehensive Computer Vision Bootcamp ranging from classical image processing techniques to PyTorch-based CNN, Vision Transformer (ViT), Swin Transformer, and ConvNeXt architectures. Hands-on projects cover object detection with YOLO and DETR, segmentation with SAM and U-Net, video analysis, 3D vision (NeRF, Gaussian Splatting), Diffusion models, and model deployment with ONNX/TensorRT.
- Live Course
- 13 modules
-
Semantic, instance and panoptic segmentation: pixel-level training with U-Net, DeepLabV3+, SegFormer, Mask2Former and SAM 2, Dice/mIoU evaluation and mask-based measurement, for industrial, medical and satellite imagery teams.
- Live Course
- 6 modules
-
ViT, DeiT, Swin and DINOv2 architectures: patch embedding, self-attention, comparison with CNNs and fine-tuning with Hugging Face, for engineers selecting and adapting transformer-based models for vision tasks.
- Live Course
- 5 modules
Get in touch
