Affective AI (Emotion AI)
- Definition
- Affective AI, also called emotion AI, is technology that infers a person's emotional state from signals such as voice tone, facial expression, and word choice. Its use carries privacy and consent obligations.
Showing 20 of 30 terms
Anchor Box
- Definition
- An anchor box is a preset rectangle of a fixed size and shape that an object detection model uses as a starting point, adjusting it to fit the objects it finds.
Annotation Format
- Definition
- An annotation format is the file structure used to store image labels, such as boxes, masks, and classes, and to link each label to its image, typically in JSON, XML, or CSV.
Augmented Reality (AR)
- Definition
- Augmented reality (AR) overlays digital information, such as labels, instructions, or 3D models, on a live view of the physical world through a phone, tablet, smart glasses, or headset.
Bounding Box
- Definition
- A bounding box is the rectangle drawn around an object in an image to mark its position and size. Detection models predict them, and annotators draw them to create training data.
Computer Vision
- Definition
- Computer vision is the field of AI that lets software extract meaning from images and video, such as identifying objects, reading text, or measuring parts. It drives inspection, document capture, and safety…
Computer Vision Platform
- Definition
- A computer vision platform is software that covers the full life cycle of vision models: collecting and labeling images, training, deploying to cameras or servers, and monitoring results in production.
Convolutional Filter
- Definition
- A convolutional filter is a small grid of weights that slides across an image to detect a local pattern such as an edge or texture. Stacks of learned filters form a convolutional…
Convolutional Neural Network (CNN)
- Definition
- A convolutional neural network is a deep learning model that scans images with small learned filters to detect edges, textures, and shapes, making it the standard architecture for visual recognition tasks.
Data Annotation
- Definition
- Data annotation is the work of marking raw data with the labels a model should learn, such as drawing boxes around objects in images or tagging clauses in contracts.
Data Labels
- Definition
- Data labels are the known answers attached to training examples, such as "fraud" on a transaction or "defect" on a photo, that a supervised learning model learns to reproduce.
Edge AI
- Definition
- Edge AI is the running of machine learning models directly on local devices such as cameras, gateways, industrial PCs, and phones, so decisions are made where the data is captured.
Facial Recognition
- Definition
- Facial recognition is a biometric technology that identifies or verifies a person by comparing the geometry of their face with stored templates. It is tightly regulated and carries high privacy and bias…
Feature Extraction
- Definition
- Feature extraction is the conversion of raw data such as images, audio, or text into a compact set of numeric values that capture its useful content, so that a model can learn…
Image Generation
- Definition
- Image generation is the use of AI models, mostly diffusion models, to create new images from text prompts or reference pictures. Businesses use it for marketing visuals, product mockups, and synthetic training…
Image Recognition
- Definition
- Image recognition is the ability of software to identify what an image contains, such as a product, a person, a scene, or a defect, by comparing it with patterns learned from labeled…
Image Segmentation
- Definition
- Image segmentation assigns every pixel in an image to a class or an object, producing exact outlines instead of boxes. It is used to measure areas, isolate regions, and find irregular defects.
ImageNet
- Definition
- ImageNet is a large labeled image dataset, with over a million photographs sorted into a thousand categories in its benchmark subset, on which modern deep learning for computer vision first proved itself.
Intelligent Character Recognition (ICR)
- Definition
- Intelligent character recognition (ICR) is OCR extended to handwriting. It uses neural networks trained on handwritten samples to read hand-printed fields on forms, checks, and notes, with a confidence score per field.
Intelligent Document Processing (IDP)
- Definition
- Intelligent document processing (IDP) combines OCR, classification, and language models to turn invoices, contracts, forms, and other documents into validated structured data that flows into business systems.
Machine Vision
- Definition
- Machine vision is the use of industrial cameras, lighting, and image analysis software to inspect, measure, guide, and identify parts on a production line, usually in real time and tied to plant…
Object Detection
- Definition
- Object detection is a computer vision task that finds every object of interest in an image, labels each one, and marks its position with a bounding box and a confidence score.
Object Tracking
- Definition
- Object tracking follows a detected object from frame to frame in a video, assigning it a persistent identity so a system can count objects, measure dwell time, and trace paths.
Optical Character Recognition (OCR)
- Definition
- Optical character recognition (OCR) converts images of printed text, such as scans, photos, and PDFs, into machine-readable characters that software can search, extract, and process.
Outsourced Labeling
- Definition
- Outsourced labeling is paying an external vendor or crowd to annotate images and other training data. It scales labeling quickly but raises quality control and confidentiality issues that need contractual and technical…
Siamese Network
- Definition
- A Siamese network is a neural network that runs two inputs through identical twin branches and compares the results, learning to judge whether the inputs match rather than what class they belong…
Video Analytics
- Definition
- Video analytics applies computer vision to live or recorded video to detect events, count objects, and measure activity, turning camera footage into alerts and operational data.
Vision-Language Model (VLM)
- Definition
- A vision-language model (VLM) is a large language model that also accepts images, so it can describe photos, read documents, answer questions about charts, and follow instructions that mix text and pictures.
Visual Inspection (AI Quality Inspection)
- Definition
- AI visual inspection uses cameras and trained vision models to check products for defects, missing components, and assembly errors during production, replacing or assisting manual inspection.
Visual Search
- Definition
- Visual search finds items that look like a query image instead of matching typed keywords. It converts images to embeddings and retrieves the nearest matches from a catalog or archive.
No terms match your search.
Try a broader keyword or another category.