0% found this document useful (0 votes)
30 views21 pages

CV 1

Uploaded by

Bilal Khan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
30 views21 pages

CV 1

Uploaded by

Bilal Khan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 21

Computer Vision

Bilal Khan
Computer Vision
Computer vision is a field of artificial intelligence (AI) that enables
computers to interpret and understand visual information from the
world.
It seeks to replicate and improve upon the human visual system's ability
to process and make sense of visual data.
The goal of computer vision is to develop algorithms and models that
can analyze and interpret images or videos, extracting meaningful
information and insights.
Key tasks in computer vision include
• Image Recognition/Classification: Identifying and categorizing objects or patterns within
images.
• Object Detection: Locating and identifying multiple objects within an image or video.
• Image Segmentation: Dividing an image into segments or regions to understand the
structure and relationships between different parts.
• Face Recognition: Identifying and verifying individuals based on facial features.
• Gesture Recognition: Interpreting gestures or movements made by humans.
• OCR (Optical Character Recognition): Recognizing and extracting text from images or
scanned documents.
• Pose Estimation: Determining the spatial positions of objects or people in an image or
video.
• Scene Understanding: Analyzing and comprehending the content and context of a scene.
• Computer vision applications are widespread
and can be found in various fields, including
healthcare (medical image analysis),
automotive (autonomous vehicles),
surveillance, agriculture, manufacturing, and
augmented reality, among others.

• Advances in deep learning, particularly


convolutional neural networks (CNNs), have
significantly contributed to the progress and
success of computer vision tasks in recent
years.
Why Computer Vision is important
Automation and Efficiency: Computer vision enables automation of tasks that traditionally required
human visual perception. This can lead to increased efficiency, productivity, and cost savings in
industries such as manufacturing, where automated quality control and inspection can be implemented.

Enhanced User Experience: In consumer applications, computer vision contributes to improved user
experiences. For example, it is used in facial recognition for unlocking smartphones, gesture control in
gaming consoles, and image recognition in social media applications.

Medical Imaging: In healthcare, computer vision plays a crucial role in medical image analysis. It aids
in the diagnosis and detection of diseases, assists in surgical procedures, and helps in monitoring patient
health. Early detection of medical conditions can lead to more effective treatments.
Autonomous Systems: In the automotive industry, computer vision is a key component of autonomous
vehicles. It helps in object detection, lane keeping, and navigating complex environments. This
technology has the potential to enhance road safety and reduce accidents.

Security and Surveillance: Computer vision is widely used in security and surveillance systems for
monitoring and analyzing video feeds. It can detect suspicious activities, track objects, and identify
individuals, contributing to public safety.

Agriculture: In agriculture, computer vision applications can help in crop monitoring, disease detection,
and yield prediction. This assists farmers in making informed decisions and optimizing resource usage.

Retail and E-commerce: Computer vision is utilized in retail for tasks such as inventory management,
shelf monitoring, and customer analytics. In e-commerce, it can enhance the shopping experience
through features like visual search and augmented reality try-on.
Accessibility: Computer vision technologies contribute to accessibility solutions for individuals with
disabilities. For example, it can be used to develop systems that assist the visually impaired in
navigating their surroundings.

Scientific Research: In scientific research, computer vision is employed for tasks like image analysis in
biology and astronomy. It helps researchers process large amounts of visual data and extract meaningful
insights.

Environmental Monitoring: Computer vision can be used for environmental monitoring, including
analyzing satellite imagery for tracking deforestation, monitoring wildlife, and assessing the impact of
climate change.
Scope of Computer Vision
The scope of computer vision is broad and continually expanding, with ongoing
advancements in technology and increasing applications across various industries. Here are
some aspects that highlight the scope of computer vision:

Industry Applications: Computer vision finds applications in numerous industries, including


healthcare, automotive, agriculture, manufacturing, retail, security, and more. As technology
continues to advance, new opportunities for utilizing computer vision in diverse sectors
emerge.

Autonomous Systems: The development of autonomous systems, such as self-driving cars


and drones, heavily relies on computer vision. As the technology matures, we can expect
more sophisticated and widespread implementation of autonomous solutions in
transportation and other domains.
Healthcare and Medical Imaging: Computer vision has a significant role in medical image analysis,
aiding in the diagnosis and treatment of various medical conditions. The scope includes not only
traditional medical imaging but also emerging areas such as personalized medicine and telemedicine.

Augmented Reality (AR) and Virtual Reality (VR): Computer vision plays a crucial role in AR and
VR applications, enhancing user experiences by overlaying digital information onto the real world or
creating immersive virtual environments.

Surveillance and Security: The demand for advanced surveillance and security systems is driving the
growth of computer vision applications. This includes object detection, facial recognition, and behavior
analysis for public safety and security purposes.

Human-Computer Interaction: Computer vision contributes to the development of natural and


intuitive interfaces between humans and computers. Gesture recognition, facial expression analysis, and
gaze tracking are examples of how computer vision enhances human-computer interaction.
Robotics: In robotics, computer vision enables robots to perceive and interact with their environment.
This is crucial for tasks such as object manipulation, navigation, and collaboration with humans.

Environmental Monitoring: Computer vision is used in environmental monitoring, including the


analysis of satellite imagery for tracking changes in landscapes, monitoring wildlife, and assessing
environmental conditions.

Retail and E-commerce: Computer vision applications in retail include inventory management,
customer analytics, cashier-less checkout systems, and augmented reality features for online shopping.

Entertainment and Gaming: Computer vision enhances the gaming experience by enabling gesture-
based controls, facial recognition for personalized avatars, and immersive simulations in virtual
environments.

Accessibility Solutions: Computer vision contributes to the development of accessibility solutions,


making technology more inclusive for individuals with disabilities. This includes text-to-speech,
gesture-based controls, and other assistive technologies.
The scope of computer vision is dynamic and influenced by ongoing research, technological
breakthroughs, and the identification of new use cases.

As computational power and data availability continue to increase, the potential applications of
computer vision are likely to expand, creating new opportunities for innovation and impact across
multiple domains.
Fundamentals of Image Formation

Image formation is an analog to digital conversion of an image with the help of 2D Sampling
and Quantization techniques that is done by the capturing devices like cameras. In general,
we see a 2D view of the 3D world.

In the same way, the formation of the analog image took place. It is basically a conversion of
the 3D world that is our analog image to a 2D world that is our Digital image.

Generally, a frame grabber or a digitizer is used for sampling and quantizing the analog
signals.
Imaging
The mapping of a 3D world object into a 2D digital image plane is called imaging. In order to do so,
each point on the 3D object must correspond to the image plane. We all know that light reflects from
every object that we see thus enabling us to capture all those light-reflecting points in our image plane.

Various factors determine the quality of the image like spatial factors or the lens of the capturing
device.
Color and Pixelation
In digital imaging, a frame grabber is placed at the image plane which is like a sensor. It aims to focus
the light on it and the continuous image is pixelated via the reflected light by the 3D object. The light
that is focused on the sensor generates an electronic signal.

Each pixel that is formed may be colored or grey depending on the intensity of the sampling and
quantization of the light that is reflected and the electronic signal that is generated via them.

All these pixels form a digital image. The density of these pixels determines the image quality. The more
the density the more the clear and high-resolution image we will get.
Forming a Digital Image
To form or create an image that is digital in nature, we need to have a continuous conversion of data into
a digital form. Thus, we require two main steps to do so:

Sampling (2D): Sampling is a spatial resolution of the digital image. And the rate of sampling
determines the quality of the digitized image. The magnitude of the sampled image is determined as a
value in image processing. It is related to the coordinates values of the image.

Quantization: Quantization is the number of grey levels in the digital image. The transition of the
continuous values from the image function to its digital equivalent is called quantization. It is related to
the intensity values of the image.

The normal human being acquires a high level of quantization levels to get the fine shading details of the
image. The more quantization levels will result in the more clear image.
Satellite Image Processing
Satellite Image Processing is an important field in research and development and consists of
the images of earth and satellites taken by the means of artificial satellites.

Firstly, the photographs are taken in digital form and later are processed by the computers to
extract the information. Statistical methods are applied to the digital images and after
processing the various discrete surfaces are identified by analyzing the pixel values.

The satellite imagery is widely used to plan the infrastructures or to monitor the
environmental conditions or to detect the responses of upcoming disasters.
In broader terms we can say that the Satellite Image Processing is a kind of remote sensing
which works on pixel resolutions to collect coherent information about the earth surface.
Majorly there are four kinds of resolutions associated with satellite imagery. These are:

Spatial resolution – It is determined by the sensors Instantaneous Field of View(IFoV) and is defined as
the pixel size of an image that is visible to the human eye being measured on the ground. Since it has
high resolving power or the ability to separate and hence is termed as Spatial Resolution.

Spectral resolution – This resolution measures the wavelength internal size and determines the number
of wavelength intervals that the sensor measures.

Temporal resolution – The word temporal is associated with time or days and is defined as the time that
passes between various imagery cloud periods.

Radiometric resolution – This resolution provides the actual characteristics of the image and is
generally expressed in bits size. It gives the effective bit depth and records the various levels of
brightness of imaging system.
Image Formats
Image Format describes how data related to the image will be stored. Data can be stored in
compressed, Uncompressed, or vector format. Each format of the image has a different advantage and
disadvantage. Image types such as TIFF are good for printing while JPG or PNG, are best for the web.

TIFF(.tif, .tiff) Tagged Image File Format this format store image data without losing any data. It does
not perform any compression on images, and a high-quality image is obtained but the size of the image
is also large, which is good for printing, and professional printing.

JPEG (.jpg, .jpeg) Joint Photographic Experts Group is a loss-prone (lossy) format in which data is
lost to reduce the size of the image. Due to compression, some data is lost but that loss is very less. It is
a very common format and is good for digital cameras, nonprofessional prints, E-Mail, Powerpoint,
etc., making it ideal for web use.

GIF (.gif) GIF or Graphics Interchange Format files are used for web graphics. They can be animated
and are limited to only 256 colors, which can allow for transparency. GIF files are typically small in
size and are portable.
PNG (.png) PNG or Portable Network Graphics files are a lossless image format. It was
designed to replace gif format as gif supported 256 colors unlike PNG which support 16
million colors.

Bitmap (.bmp) Bit Map Image file is developed by Microsoft for windows. It is same as
TIFF due to lossless, no compression property. Due to BMP being a proprietary format, it is
generally recommended to use TIFF files.

EPS (.eps) Encapsulated PostScript file is a common vector file type. EPS files can be opened
in applications such as Adobe Illustrator or CorelDRAW.

RAW Image Files (.raw, .cr2, .nef, .orf, .sr2) These Files are unprocessed and created by a
camera or scanner. Many digital SLR cameras can shoot in RAW, whether it be a .raw, .cr2, or
.nef. These images are the equivalent of a digital negative, meaning that they hold a lot of
image information. These images need to be processed in an editor such as Adobe Photoshop
or Lightroom. It saves metadata and is used for photography.
What is meant by image saved with transparency?

Images saved with transparency look good on colored background whereas images without
transparency will have a white background which will be visible on colored background.

You might also like