Computer Vision and Image Processing

Chapter - 1
Introduction Computer Vision and Image Processing

By Diriba Regasa (MSc)

 What is a computer vision?

• Is one of the fields of AI that trains and enables computers to

understand the visual world.
• Computers can use digital images and deep learning models
to accurately identify and classify objects and react to them.
• CV is the field of computer science that focuses on creating
digital systems that can process, analyze and make sense of
visual data (images or videos) in the same way that humans do.
• The concept of computer vision is based on teaching computers
to process an image at a pixel level and understand it.
• Technically, machines attempt to retrieve visual information, handle it,
and interpret results through special software algorithms.

2
…

3
 …

 Computer vision systems can be used for:

• Object classification
– The system parses visual content and classifies the object on a photo/video
to the defined category.
– Example: the system can find a dog among all objects in the image.
• Object identification
– The system parses visual content and identifies a particular object on a
photo/video.
– Example: the system can find a specific dog among the dogs in the image.
• Object tracking
– The system processes video finds the object that match search criteria and
track its movement.

4
 What is image?

• An image is a visual representation of something.

• Digital image is a binary representation of visual data.
– An image is represented by its dimensions (height and width) based on the
number of pixels.
• example, if the dimensions of an image are 500 x 400 (width x height),
the total number of pixels in the image is 200000.
• This pixel is a point on the image that takes on a specific shade, opacity
or color. It is usually represented in one of the following:
– Grayscale - A pixel is an integer with a value between 0 to 255 (0 is
completely black and 255 is completely white).
– RGB - A pixel is made up of 3 integers between 0 to 255 (the
integers represent the intensity of red, green, and blue).
– RGBA - It is an extension of RGB with an added alpha field, which
represents the opacity of the image.
5
 What is image processing

• Image processing is the process of transforming an image into

a digital form and performing certain operations to get some
useful information from it.
• Image processing requires fixed sequences of operations that
are performed at each pixel of an image.
• The image processor performs the first sequence of operations
on the image, pixel by pixel.
– Once this is fully done, it will begin to perform the second
operation, and so on.
– The output value of these operations can be computed at
any pixel of the image.

6
 Types of Image Processing

There are five main types of image processing:

• Visualization - find objects that are not visible in the image
• Recognition - distinguish or detect objects in the image
• Sharpening and restoration - create an enhanced image from the
original image
• Pattern recognition - measure the various patterns around the
objects in the image
• Retrieval - browse and search images from a large database of
digital images that are similar to the original image

7
 Fundamental steps in image processing

• Image Acquisition - first step in image processing. It involves

retrieving the image from a source, usually a hardware-based
source.
• Image Enhancement - the process of bringing out and highlighting
certain features of interest in an image that has been obscured.
This can involve changing the brightness, contrast, etc.
• Image Restoration - the process of improving the appearance of an
image. However, unlike image enhancement, image restoration is
done using certain mathematical or probabilistic models.
• Color Image Processing - includes a number of color modeling
techniques in a digital domain. This step has gained prominence
due to the significant use of digital images over the internet.

8
 …

• Wavelets and Multiresolution Processing - used to represent images in

various degrees of resolution. The images are subdivided into
wavelets or smaller regions for data compression and for
pyramidal representation.
• Compression - a process used to reduce the storage required to save
an image or the bandwidth required to transmit it. This is done
particularly when the image is for use on the Internet.
• Morphological Processing - is a set of processing operations for
morphing images based on their shapes.
• Segmentation - is one of the most difficult steps of image
processing. It involves partitioning an image into its constituent
parts or objects.

9
 …

• Representation and Description - After an image is segmented into

regions in the segmentation process, each region is represented
and described in a form suitable for further computer processing.
– Representation deals with the image’s characteristics and
regional properties.
– Description deals with extracting quantitative information that
helps differentiate one class of objects from the other.
• Recognition - assigns a label to an object based on its description.
• Knowledge Base - Knowledge may be as simple as detailing
regions of an image where the information of interest is known to
be located, thus limiting the search that has to be conducted in
seeking that information.

10
 Related fields in CV

• Computer vision is a field of study that deals with how

computers can be made to understand and interpret images and
video.
• The field encompasses several subfields, including:
• Image processing: This deals with the manipulation of images,
such as enhancement, restoration, and compression.
• Object recognition and tracking: This deals with identifying and
tracking objects within images and videos.
• Motion and stereo: This deals with understanding the motion of
objects and the 3D structure of scenes.
• Scene understanding: This deals with understanding the context
and layout of images and videos.

11
 …

• Machine learning for computer vision: This deals with using

machine learning techniques to improve computer vision
algorithms.
• Robotics and control: This deals with using computer vision to
control robots and other autonomous systems.
• Augmented reality: This deals with overlaying digital
information on top of the real world.
• Biometrics: This deals with using computer vision to identify
individuals based on their physical characteristics.
• Medical imaging: This deals with using computer vision to
analyze medical images.

12
…

13
 Computer Vision Vs image processing

• Computer vision (CV) and image processing are two closely

related fields that utilize techniques from artificial intelligence
(AI) and pattern recognition to derive meaningful information
from images, videos, and other visual inputs.
• Image processing algorithms are used to extract information
from images, restore and compress image and video data, and
build new experiences in virtual and augmented reality.
• Computer vision uses image processing to recognize and
categorize image data.

14
 …

Image Processing Computer Vision

Focused on extracting information from
Focused on processing the raw input
the input images or videos to have a
images to enhance them or preparing
proper understanding of them to predict
them to do other tasks
the visual input like human brain.
Uses methods like Anisotropic diffusion, Image processing is one of the methods
Hidden Markov models, Independent that is used for computer vision along
component analysis, Different Filtering with other Machine learning techniques,
etc. CNN etc.
Image Processing is a subset of Computer Computer Vision is a superset of Image
Vision. Processing.
Example: Rescaling image (Digital
Example: Object detection, Face
Zoom), Correcting illumination,
detection, Hand writing recognition etc.
Changing tones etc.
15
 Application of CV and IP

Application of CV
 Computer Vision gives the machines the sense of sight it
allows them to see and explore the world.
– Transportation
– Healthcare
– Manufacturing
– Construction
– Agriculture
– Retail

16
 Transportation

• Self-driving cars: Computer vision is used to detect and classify

objects (e.g., road signs or traffic lights), create 3D maps or motion
estimation, and played a key role in making autonomous vehicles a
reality.
• Self-driving cars collect data on their surroundings from sensors and
cameras, interpret it, and respond accordingly.

17
 …

Pedestrian detection- It uses cameras to automatically identify and

locate the pedestrians in images or videos while considering variations
related to body attire and position, occlusion, illuminance in different
scenarios, and background clutter.

18
 …

• Parking occupancy detection- computer vision is already widely

used for visual parking lot occupancy detection in Parking Guidance
and Information (PGI) systems.

19
 …

• Traffic flow analysis- drone and camera-based traffic flow

tracking and estimation. The algorithms can now accurately track
and count freeway traffic or monitor and analyze traffic density in
urban areas (e.g., at intersections), helping to design better traffic
management systems and improve road safety.

20
 …

• Road condition monitoring- used for defect detection and found

application in assessing the infrastructure condition by monitoring
changes in concrete and asphalt.
• Automated Pavement Distress (PD) detection has proven successful
in increasing road maintenance allocation efficiency and decreasing
the safety risk related to accidents.
• Computer vision algorithms use the collected image data that is later
processed to build automatic crack detection.

21
 Health Care

X-Ray analysis- In the context of medical X-ray imaging,

computer vision can be successfully applied to treatment and
research, MRI reconstruction, or surgeries planning.

22
 …

Cancer detection- Image recognition allows doctors to identify

anomalies and changes by comparing cancerous and non-
cancerous cells in images.

23
 …

Digital pathology- computer vision can now process medical image

data to detect and identify the type of pathology on display.
• It is used for :
– Image analysis and interpretation
– Detailed inspections of sample tissues
– Pathology types matching to earlier cases
– Diagnosis accuracy and early detection

24
 Manufacturing

Product assemble

Defect inspection

Reading text and barcode 25

 Construction

Predictive maintenance
PPE detection
26
 Agriculture

Crop and yield monitoring Insect detection Aerial survey and imaging

Livestock health monitoring Plant disease detection 27

 Retail

Foot traffic and people counting Automatic replenishment

Intelligent video analytics Self-checkout 28

 Application of IP

Medical Image Retrieval

Traffic Sensing Technologies Image Reconstruction

29
The End