Chapter one

Introduction
 “One picture is worth more than ten thousand words”. Anonymous
 What is a computer vision?

 An image may be defined as a two-dimensional function, f ( x, y ), where x and y are spatial

(plane) coordinates, and the amplitude of f at any pair of coordinates ( x, y ) is called the in-
tensity or gray level of the image at that point.
 When x, y, and the intensity values of f are all finite, discrete quantities, we call the image a
digital image.
 The field of digital image processing (DIP) refers to processing digital images by means of a
digital computer.
 DI is composed of a finite number of elements, each of which has a particular location and
value.
 These elements are called picture elements, image elements, pels, and pixels. Pixel is the term
 Cont…
Computer vision is the automated extraction of information from images.

Information can mean anything from 3D models, camera position, object detection and

recognition to grouping and searching image content.

 In this course we take a wide definition of computer vision and include things like image

warping, de-noising and augmented reality.

 Sometimes computer vision tries to mimic human vision, sometimes uses a data and statis-

tical approach, sometimes geometry is the key to solving problems.

Practical computer vision contains a mix of programming, modeling, and mathematics

Cont…
Computer

Vision Vs image processing
There is no general agreement regarding where image processing stops and other related areas, such as image
analysis and computer vision, start.

 Sometimes, a distinction is made by defining image processing as a discipline in which both the input and
output of a process are images.

 On the other hand, there are fields such as computer vision whose ultimate goal is to use computers to emulate
human vision, including learning and being able to make inferences and take actions based on visual inputs.

 This area itself is a branch of AI whose objective is to emulate human intelligence.

 The area of image analysis (also called image understanding) is in between image processing and computer
vision.
Cont…
 However, one useful paradigm is to consider three types of computerized processes in this
continuum: low, mid, and high level processes.

 Low-level processes involve primitive operations such as image preprocessing to reduce

noise, contrast enhancement, and image sharpening.

 A low level process is characterized by the fact that both its inputs and outputs are images.

 Mid-level processing of images involves tasks such as s description of those objects to

reduce them to a form suitable for computer processing, and classification (recognition) of
individual objects.
Cont…
 A mid-level process is characterized by the fact that its inputs generally are images, but its outputs are attributes
extracted from those images

 Finally, higher-level processing involves “making sense” of an ensemble of recognized objects, as in image
analysis, and, at the far end of the continuum, performing the cognitive functions normally associated with human
vision.

 The logical place of overlap between image processing and image analysis is the area of recognition of individual
regions or objects in an image.

 Thus, DIP encompasses processes whose inputs and outputs are images and, in addition, includes processes that
extract attributes from images up to, and including, the recognition of individual objects.
Why we study Computer vision?
 Cameras are appearing everywhere:

 the webcams on your laptops;

 the surveillance cameras around the airport;

 the cameras built in to your mobile phones;

 cameras on satellites;

 cameras taking medical images such as ultrasound and X-ray

 At present most of these images are just looked at by people

 e.g. most webcams are just used for teleconferencing.

 Why we study Computer vision?
 However, the processing of images from all these cameras can be automated,
allowing us to do things never before considered:

 the webcam as a tracking device in place of the mouse

 the surveillance cameras used to identify thieves and alert security

 the camera on your phone used to capture images of signs and automatically
translate them

 medical cameras used to diagnose conditions more reliably than the best expert

 cameras on robots allowing them to interact with the world just like us.
Application
 Fast-growing collection of useful applications of CV:
 Automated surveillance
 Face recognition and biometrics
 Obstacle avoidance
 Object recognition
 Autonomous driving
 Cartography( Maps from aerial and satellite images)
 Space science(planetary exploration)
 Medicine (pathology, surgery, diagnosis)
 Remote Sensing
 Industrial inspection
 Robotic control
 Agriculture (quality inspection , disease monitoring)
Related Fields
AI

Computer Image
Graphics Processing

Computer
Vision

Pattern
Robotics
Recognition
Why is computer vision difficult?

 An image is a two-dimensional optical projection,

but the world we wish to make sense of visual is
three-dimensional.
We need to invert the 3D 2D projection in order
to recover world properties (object properties)
But the 2D 3D inversion is mathematically
difficult
 Challenges: Face Recognition

 Which two pictures show the same person?

 Most algorithms for computer vision select 1 and 2 as the same person, since those
images are more similar than 1 and 3.
Challenges: object intra-class variation
Challenges: illumination
Challenges: Activity Understanding
Challenges: Activity Understanding
 Fundamental steps in image processing
 Image Acquisition፡ it could be as simple as being given an image that is already in digital form.

 Generally, the image acquisition stage involves pre-processing, such as scaling etc.

 Image Enhancement፡ enhancement techniques is to bring out detail that is obscured, or simply to high-
light certain features of interest in an image. changing brightness & contrast etc.

 Image Restoration፡ Image restoration is an area that also deals with improving the appearance of an im-
age.

 However, unlike enhancement, which is subjective, image restoration is objective.

 Color Image Processing፡ Color image processing is an area that has been gaining its importance because
of the significant increase in the use of digital images over the Internet.
Cont…
 Compression: deals with techniques for reducing the storage required to save an image or the bandwidth
to transmit it

 Morphological Processing: deals with tools for extracting image components that are useful in the rep-
resentation and description of shape

 Segmentation: procedures partition an image into its constituent parts or objects. In general, autono-
mous segmentation is one of the most difficult tasks in digital image processing

 Representation and Description: Choosing a representation is only part of the solution for transforming
raw data into a form suitable for subsequent computer processing.

 Description deals with extracting attributes that result in some quantitative information of interest or are
basic for differentiating one class of objects from another.

 Object recognition: Recognition is the process that assigns a label, such as, “vehicle” to an object based
on its descriptors.
Thank you!