Are You a Computer Vision Expert?



9 Questions

What is computer vision?

What is the difference between the scientific and technological discipline of computer vision?

What are some sub-domains of computer vision?

What is the largest area of computer vision applications?

What is the classical problem in computer vision, image processing, and machine vision?

What is the best algorithm for object recognition tasks?

What is image restoration used for?

What are image-understanding systems (IUS) composed of?

What are vision processing units?


Computerized information extraction from images: A detailed summary

  • Computer vision is an interdisciplinary field that involves acquiring, processing, analyzing, and understanding digital images to produce numerical or symbolic information using models constructed with the aid of geometry, physics, statistics, and learning theory.

  • The scientific discipline of computer vision is concerned with the theory behind artificial systems that extract information from images, while the technological discipline of computer vision seeks to apply its theories and models for the construction of computer vision systems.

  • Sub-domains of computer vision include scene reconstruction, object detection, event detection, video tracking, object recognition, 3D pose estimation, learning, indexing, motion estimation, visual servoing, 3D scene modeling, and image restoration.

  • Adopting computer vision technology can be painstaking for organizations as there is no single point solution for it, and there are very few companies that provide a unified and distributed platform or an Operating System where computer vision applications can be easily deployed and managed.

  • Computer vision began in the late 1960s, at universities pioneering artificial intelligence, with the goal of mimicking the human visual system as a stepping stone to endowing robots with intelligent behavior.

  • Studies in the 1970s formed the early foundations for many of the computer vision algorithms that exist today, including extraction of edges from images, labeling of lines, non-polyhedral and polyhedral modeling, representation of objects as interconnections of smaller structures, optical flow, and motion estimation.

  • By the 1990s, some of the previous research topics became more active than others. Research in projective 3-D reconstructions led to better understanding of camera calibration, and methods for sparse 3-D reconstructions of scenes from multiple images were developed.

  • Applications of computer vision include medical computer vision, or medical image processing, characterised by the extraction of information from image data to diagnose a patient, supporting medical research, and enhancing images interpreted by humans. Machine vision refers to a process of combining automated image analysis with other methods and technologies to provide automated inspection and robot guidance in industrial applications.

  • Military applications are probably one of the largest areas of computer vision, with the detection of enemy soldiers or vehicles and missile guidance being some examples.

  • Autonomous vehicles use computer vision for navigation, e.g., for knowing where they are or mapping their environment (SLAM), detecting obstacles, and ensuring navigational safety.

  • Materials such as rubber and silicon are being used to create sensors that allow for applications such as detecting micro undulations and calibrating robotic hands.

  • Computer graphics produces image data from 3D models, and computer vision often produces 3D models from image data. There is also a trend towards a combination of the two disciplines, e.g., as explored in augmented reality.

  • The fields most closely related to computer vision are image processing, image analysis, and machine vision. There is a significant overlap in the range of techniques and applications covered, and the basic techniques used and developed in these fields are similar, but various characterizations distinguish each of the fields from the others.Computer Vision: Overview and Applications

  • Computer vision involves acquiring, processing, analyzing, and understanding digital images and extracting high-dimensional data from the real world to produce numerical or symbolic information.

  • Object recognition is the classical problem in computer vision, image processing, and machine vision, which determines whether the image data contains a specific object, feature, or activity.

  • Convolutional neural networks are the best algorithms for object recognition tasks, and they are based on the ImageNet Large Scale Visual Recognition Challenge, where the performance of convolutional neural networks is now close to that of humans.

  • Motion estimation is a computer vision task that processes an image sequence to produce an estimate of the velocity either at each point in the image or in the 3D scene or even of the camera that produces the images.

  • Scene reconstruction aims to compute a 3D model of the scene given one or more images of a scene or a video.

  • Image restoration is used to recover or restore the image as it was intended to be when the original image is degraded or damaged due to external factors like lens wrong positioning, transmission interference, low lighting, or motion blurs.

  • The organization of a computer vision system is highly application-dependent, and some systems are stand-alone applications that solve a specific measurement or detection problem, while others constitute a sub-system of a larger design.

  • Image-understanding systems (IUS) include three levels of abstraction: low level, intermediate level, and high level, and the representational requirements in the designing of IUS for these levels are: representation of prototypical concepts, concept organization, spatial knowledge, temporal knowledge, scaling, and description by comparison and differentiation.

  • Most computer vision systems use visible-light cameras passively viewing a scene at frame rates of at most 60 frames per second, while a few computer vision systems use image-acquisition hardware with active illumination or something other than visible light or both.

  • Advances in digital signal processing and consumer graphics hardware have made high-speed image acquisition, processing, and display possible for real-time systems on the order of hundreds to thousands of frames per second.

  • Egocentric vision systems are composed of a wearable camera that automatically takes pictures from a first-person perspective.

  • Vision processing units are emerging as a new class of processor, to complement CPUs and graphics processing units (GPUs) in this role.


Test your knowledge of computer vision and its applications with our quiz! From scene reconstruction to object recognition, image restoration to motion estimation, this quiz covers a wide range of topics in the field. Are you familiar with the history of computer vision, or the latest algorithms used in object recognition? Take the quiz to find out!

Ready to take the quiz?

Play Quiz