Computer Vision
Computer vision builds systems that extract structured information from images and video: detecting objects, recognizing faces, segmenting scenes, reading text, and interpreting spatial relationships. It combines image processing, machine learning, and geometry to give machines visual perception.
itArtificial intelligence and machine learning | OpenSkills.info
Intro
Computer Vision
Computer vision turns pixels into useful information. A computer vision system can assign a label to an image, locate objects, mark each pixel by category, track motion, or estimate structure. The output supports another decision or action.
Use this mental model:
scene → sensor → pixels → preprocessing → model → prediction → product decision
The model is only one part of the system. Lighting, camera position, labels, preprocessing, decision thresholds, and the people affected by the result can matter as much as the model architecture.
What an image becomes
A digital image is an array of numeric pixel values. A color image often has separate channels for red, green, and blue. A video adds a time dimension. Frameworks represent these arrays as tensors so models can process batches of images efficiently.
Pixels do not carry meaning by themselves. The same object can occupy different positions, scales, and orientations. Its appearance changes with lighting, background, motion blur, occlusion, lens behavior, and sensor noise. A useful system must handle the variation expected in its operating environment.
Preprocessing puts inputs into the form a model expects. Common operations include resizing, cropping, color conversion, and normalization. Training-time augmentation creates altered examples, such as crops or flips, to expose the model to relevant variation. An augmentation is valid only when it preserves the intended label. A horizontal flip may be sensible for a flower, but wrong for text or a directional traffic sign.
Continue the course
This section is part of the paid course.
See pricing to subscribe, or log in if you already have access.
Where this skill leads
Relevant careers
See how this topic contributes to broader role-level skill maps.
Sources
- https://docs.opencv.org/master/d6/d00/tutorial_py_root.html
Supports
- Images as arrays with pixel and channel operations
- Geometric transforms, filtering, feature detection, video analysis, camera calibration, and classical object detection
- The role of explicit image processing alongside learned models
- https://www.tensorflow.org/tutorials/images/classification
Supports
- The image classification workflow from data loading through training, testing, and deployment conversion
- Training and validation datasets, overfitting, data augmentation, and dropout
- Image resizing, batching, and model input preparation
- https://www.tensorflow.org/tutorials/images/segmentation
Supports
- Semantic segmentation as per-pixel classification
- Image and mask preprocessing, matching augmentation, class imbalance, and encoder-decoder models
- Transfer of a pretrained image encoder into a segmentation model
- https://docs.pytorch.org/tutorials/beginner/transfer_learning_tutorial
Supports
- Fine-tuning a pretrained convolutional network
- Using a pretrained network as a fixed feature extractor
- Separate training and validation phases and evaluation on custom images
- https://docs.pytorch.org/tutorials/intermediate/torchvision_tutorial.html
Supports
- Object detection as prediction of bounding boxes and class scores
- Instance segmentation as an additional mask prediction for each object
- Custom dataset targets, transfer learning, and adaptation of a pretrained Mask R-CNN model
- https://arxiv.org/abs/2010.11929
Supports
- A transformer applied to sequences of image patches
- Large-scale pretraining followed by transfer to image recognition benchmarks
- Vision Transformer as an alternative to convolutional architectures for image classification
- https://scikit-learn.org/stable/modules/model_evaluation.html
Supports
- Confusion matrices and classification reports
- Precision as control of false positives and recall as coverage of actual positives
- F-measures, multiclass averaging, and threshold-sensitive evaluation
- https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GroupKFold.html
Supports
- Evaluation folds with non-overlapping groups
- Keeping every defined group in only one test fold
- Group-aware splitting for related samples
- https://developers.google.com/machine-learning/crash-course/overfitting/dividing-datasets
Supports
- Separate training, validation, and test sets
- Validation during development and test data for final evaluation
- Evaluation on unseen data after model choices are made
- https://developers.google.com/machine-learning/crash-course/production-ml-systems/monitoring
Supports
- Input schemas, feature checks, important data slices, and real-world metrics
- Training-serving skew, model age, reproducible data generation, and production quality monitoring
- Version tracking, latency, memory, throughput, and live model evaluation
- https://developers.google.com/machine-learning/managing-ml-projects/production
Supports
- Compute and quota planning for training and serving
- Logging, monitoring, alerting, deployment approval, staged rollout, and rollback
- Data drift, prediction drift, quality degradation, latency, and outages
- https://airc.nist.gov/airmf-resources/airmf/
Supports
- AI risk management across design, development, use, and evaluation
- Trustworthiness considerations including validity, safety, security, transparency, privacy, and fairness
- Govern, Map, Measure, and Manage functions across the AI lifecycle
- https://airc.nist.gov/airmf-resources/airmf/5-sec-core/
Supports
- Continuous risk management and documented measurement of fairness and bias
- Governance, context mapping, measurement, impact assessment, and management of deployed AI risk