Computer vision

Computer Vision is a subfield of Artificial intelligence. The purpose of computer vision is to program a computer to "understand" a scene or features in an image.

Typical goals of computer vision include:

• The detection, segmentation, location, and recognition of certain objects in images (e.g., human faces)
• Registration of different views of the same scene or object
• Tracking an object through an image sequence
• Mapping a scene to a three-dimensional model of the scene; such a model might be used by a robot to navigate the imaged scene
• Estimation of the three-dimensional poses of humans and their limbs

These goals are achieved by means of pattern recognition, statistical learning, projective geometry, image processing, graph theory and other fields. Cognitive computer vision[?] is strongly related to cognitive psychology and biological computation[?].

In the related fields machine vision and medical imaging, systems using computer vision techniques are sold in markets worth billions of US dollars per year.

See also

• artificial intelligence
• image processing, digital image processing
• machine vision
• medical imaging
• morphological image processing
• Herbert Freeman
• David Marr[?]
• Jerome Lemelson[?]
• Affective Computing

External links

• The Computer Vision Homepage (http://www-2.cs.cmu.edu/~cil/vision.html)
• CVonline On-Line Compendium of Computer Vision (http://www.dai.ed.ac.uk/CVonline/)