Computer Vision

List of AI applications used for each.

Computer Vision is a branch of AI that deals with enabling computers to interpret and understand the visual world.

  • Image and Video Processing
    • Image Pre-processing
    • Image Enhancement
      • Noise Reduction: The process of eliminating unwanted Noise from digital images.
      • Image Sharpening: The technique of increasing the edge contrast of an image to make it look sharper.
    • Image Restoration
      • De-blurring: The process of removing blur from an image caused by camera shake or motion.
        • Super-resolution: The technique of increasing the resolution of an image beyond its original resolution.
    • Video Processing
      • Video Stabilization: The process of reducing the shaking and jittering in video footage.
      • Object Tracking: The technique of tracking the movement of an object in a video sequence.
  • Image and Video Analysis
    • Optical Character Recognition (OCR)
    • Background Removal
    • Image Question-answer
    • Image and Video Classification
      • Image Classification: The process of categorizing images based on their visual content.
        • Video Classification: The technique of categorizing videos based on their visual and audio content.
    • Detection of Objects
      • Object Detection
      • Image Recognition: The process of recognizing and identifying objects within digital images.
      • Video Recognition: The technique of recognizing and identifying objects within video sequences.
      • Face Detection: The process of detecting and locating human faces in digital images.
      • Pedestrian Detection: The technique of detecting and locating pedestrians in video sequences.
      • Motion Detection: The process of identifying motion in a sequence of images or video. This is typically done by comparing consecutive frames and detecting changes in pixel values.
    • Satellite Imagery Analysis: Analysis of satellite imagery for tasks such as land use classification, object detection, and change detection.
    • Behavior Analysis: The task of analyzing and understanding human behavior in surveillance footage.
    • Scene Understanding: The ability of a computer vision system to interpret the content of a scene, including the objects present, their relationships, and the actions taking place.
      • Scene Segmentation: The process of partitioning a digital image into multiple regions based on their visual content.
      • Scene Reconstruction: The technique of creating a 3D model of a scene from multiple 2D images.
    • Anomaly Detection
      • Anomaly Detection: The process of identifying unusual or abnormal behavior in digital images or video sequences.
        • Object Tracking and Counting: The technique of tracking and counting the number of objects in a video sequence.
  • Image and Video Recognition
    • Image Generation: The process of generating new digital images based on existing data.
      • Video Generation: The technique of generating new video sequences based on existing data.
  • Robotics and Automation
    • Visual Servoing: The technique of controlling the motion of a robot using visual feedback.
    • Object Manipulation
      • Pick-and-Place: The process of picking up an object and placing it in a new location.
      • Bin Picking: The technique of picking objects out of a bin using a robotic arm.
    • Quality Inspection
      • Defect Detection: The process of detecting and classifying defects in manufactured products.
      • Measurement: The technique of measuring the dimensions of objects in a digital image.
  • 3D
    • Augmented Reality (AR): The integration of digital information into the real world, often through the use of computer vision. This can include tasks such as object tracking, scene recognition, and 3D reconstruction.
    • Virtual Reality (VR): This application involves creating immersive virtual environments using computer vision techniques. Examples include training simulations, virtual tours, and entertainment.
    • 3D Reconstruction: The process of creating a 3D model from a series of 2D images. This is often done using stereo vision techniques, which involve capturing images from two or more different viewpoints and then triangulating the position of points in 3D space.

Natural Language Processing

Natural Language Processing (NLP) focuses on the interaction between computers and human language, enabling machines to understand, interpret, generate, and make sense of human language in a valuable way.

  • Natural Language Understanding (NLU)
    • Sentiment Analysis: The process of determining the emotional tone of a piece of text, such as whether it is positive, negative, or neutral.
    • Topic Modeling: The identification of the main themes or topics that occur in a collection of documents.
    • Named Entity Recognition (NER): The process of identifying and categorizing named entities, such as people, organizations, and locations, in text.
    • Part-of-speech Tagging (POS): The process of identifying the part of speech (noun, verb, adjective, etc.) of each word in a sentence.
  • Natural Language Generation (NLG)
    • Text Summarization: The process of generating a short summary of a longer piece of text.
    • Chatbots: Computer programs that can carry on a conversation with a human user in natural language.
    • Machine Translation: The automatic translation of text from one language to another.
    • Generate handwritten text
    • Code Generation
  • Natural Language Interfaces (NLI): Systems that enable users to interact with computers using natural language, allowing for more intuitive and user-friendly interactions by translating human language into machine-readable commands or queries.
    • Question Answering (QA): The process of automatically answering questions posed in natural language.
    • Voice Assistants: Digital assistants that use natural language processing to understand and respond to voice commands, such as Amazon's Alexa or Apple's Siri.
  • Natural Language Interaction (NLI): Natural Language Interaction (NLI) refers to the two-way communication between humans and computers using natural language, enabling users to interact with machines in a more conversational and intuitive manner, and allowing machines to understand, interpret, and generate human language in a meaningful way.
    • Dialogue Systems: Computer systems that can engage in conversation with users, often used in customer service or support applications.
    • Conversational Agents: Software programs that can understand and respond to natural language input, often used in chatbots or voice assistants.
  • Natural Language Information Retrieval (NLIR): It is a subfield of Information Retrieval (IR) that deals with the storage, retrieval, and manipulation of information using natural language queries, enabling users to search and access relevant data by expressing their information needs in their own words.
    • Information Extraction (IE): The process of automatically extracting structured information from unstructured text data.
    • Text Classification: The process of categorizing text into predefined classes or categories.
      • Spam Classification
    • Semantic Search: The process of searching for text based on its meaning, rather than just its keywords.

Recommender Systems

Recommender Systems are a type of information filtering system that seek to predict user preferences and provide personalized recommendations by analyzing patterns and relationships in user behavior, item attributes, and/or social interactions.

  • E-commerce
  • Music and Video Streaming
  • Social Media
  • News and Content Websites
  • Online Advertising
  • Job Matching
  • Travel and Hospitality
  • Finance
  • Education
  • Gaming
  • Book Recommendation
  • Food and Recipe Recommendation
  • Fitness and Wellness
  • Real Estate
  • Tourism and Travel Guides


Robotics deals with the design and development of robots that can perform tasks that typically require human intelligence. Examples include autonomous vehicles, drones, and industrial robots.

  • Perception
    • Object Recognition: The ability of a robot to identify and classify objects in its environment.
    • Scene Understanding: The ability of a robot to understand the layout and structure of its environment.
    • Semantic Mapping: The ability of a robot to create a map of its environment that includes semantic information, such as the locations of objects and landmarks.
    • Visual Servoing: The use of computer vision to control the movement of a robot.
  • Learning from Demonstration
    • Programming by Demonstration: The ability of a robot to learn new tasks by observing a human demonstrator.
    • Imitation Learning: The ability of a robot to imitate the behavior of a human or another robot.
    • Inverse Reinforcement Learning: The ability of a robot to learn the underlying reward function of a task by observing a human demonstrator.
  • Motion Planning and Control
    • Motion Planning: The ability of a robot to plan its movements in complex environments.
    • Trajectory Planning: The ability of a robot to plan its trajectory through space and time.
    • Motion Control: The ability of a robot to control its movements to achieve a desired goal.
    • Reinforcement Learning: The ability of a robot to learn from trial and error to improve its performance in a task.
  • Decision Making and Control
    • Decision Making: The ability of a robot to make decisions based on its goals, constraints, and environment.
    • Control Theory: The use of mathematical models to control the behavior of a robot.
    • Adaptive Control: The ability of a robot to adapt its behavior to changing conditions.
  • Human-Robot Interaction
    • Natural Language Processing: The ability of a robot to understand and generate natural language.
    • Speech Recognition: The ability of a robot to recognize and transcribe spoken language.
    • Computer Vision: The ability of a robot to interpret visual information from its environment.
    • Haptic Feedback: The use of tactile feedback to improve the interaction between a robot and its environment.

Expert Systems

Expert Systems are AI systems that mimic the decision-making abilities of a human expert in a specific domain.

  • Medical Diagnosis
  • Financial Analysis
  • Law Consultation
  • Tutoring Systems
  • Quality Control
  • Configuration of Computer Systems
  • Flight Reservation Systems
  • Credit Approval
  • Insurance Underwriting
  • Real Estate Appraisal

Cognitive Computing

This branch of AI deals with the design and development of systems that can simulate human thought processes. Examples include question-answering systems, recommendation systems, and conversational agents.

Affective Computing

This branch of AI deals with the design and development of systems that can recognize, interpret, and simulate human emotions. Examples include emotion recognition from facial expressions, speech, and text, and affective user interfaces.

Multi-agent Systems

This branch of AI deals with the design and development of systems that consist of multiple interacting intelligent agents. Examples include swarm intelligence, game theory, and negotiation systems.

Knowledge Representation and Reasoning

This branch of AI deals with the design and development of systems that can represent and reason with knowledge in a formal way. Examples include ontologies, semantic networks, and rule-based systems.

Human-Computer Interaction (HCI)

This branch of AI deals with the design and development of interfaces that enable effective interaction between humans and computers. Examples include gesture recognition, voice recognition, and haptic interfaces.

Autonomous Systems

Enables machines to operate independently without human intervention, used in applications like self-driving cars, drones, and autonomous robots.

Adversarial AI

Concerned with developing AI systems that can resist and respond to attacks, used in applications like CyberSecurity, fraud detection, and anomaly detection.


This branch combines AI with biology and computer science to analyze and interpret biological data, such as genetic sequences and protein structures.

Game AI

This involves the development of AI systems that can play and excel at various games, from simple board games to complex video games.

Reinforcement Learning

Reinforcement Learning is a type of machine learning that focuses on training agents to make decisions in dynamic environments by rewarding desired behaviors and penalizing undesired ones.