Scribd
Upload
15 views2 pages

HCI

Uploaded by

ebru.sara123
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
15 views2 pages

HCI

Uploaded by

ebru.sara123
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Computer Vision

• Mimic human visual understanding and make computers


as capable as humans for perceiving the 3D dimension.
• Building machines that achieve visual understanding.
• Developing mathematical techniques (theoretical and
algorithmic basis) for extracting the 3D information from
Images (2D).
• 2D, 3D, temporal data (time varying data)

• Computer vision problems are difficult problems.


• Why? Vision is an inverse problem. We try to recover
some unknowns given insufficient information.
• The objective of computer vision is to make computers
see and interpret the world like humans (even possibly
better than us).
• From the engineering point of view, computer vision aims
to build autonomous systems to perform some of the
tasks which the human visual system can perform and
even surpass it in many cases.
• Mention here Medical Image Understanding and mention
similarities.

Low-, Mid-, High-Level Vision

• Computer vision concepts can be categorized as low, mid,


and high-level vision techniques.
• Low-level Vision: image processing techniques, feature
detection, feature matching and early segmentation. Early
vision considers local properties of an image (e.g. Edge
detection).
• Mid-level Vision: pieces start to come together attributing
meaning. We start grouping things. Preliminary analysis
tells us there is an object and background in the picture.
• High-level vision: algorithms which makes sense of the
visual content and make computer vision live up to the
capabilities of human vision. We identify what is in the
image. (e.g., it is a dog).

Image processing

• Image processing is the use of algorithms to perform


operations on digital images.

• Image enhancement, restoration, image compression,


image segmentation, rescaling image, correcting illumination,
etc…

• Image In – Image Out

• The goal is to improve the quality of an image, extract useful


information from it.

You might also like