SlideShare a Scribd company logo
1 of 18
Download to read offline
Image Recognition
NIKHIL SINGH;IIITU15210;ECE
What is image recognition?
o Image Recognition is a technology that strives to acquire, process, analyse and
understand images and high-dimensional data from real world in order to produce
numerical or symbolic information
o In other words it is a process of identifying and detecting an object or a feature in a
digital image or video
o It is also known as Computer Vision
Why we need image recognition?
o Image recognition is a vital component in robotics such as the driverless vehicles or
domestic robots. It is also important in security systems such as face recognition
o In image search engines such as Google or Bing image search whereby you use rich image
content to query for similar stuff. Like in Google photos where the system uses image
recognition to categorize your images into things like cats, dogs, people and so on
o In medical imaging such as cancer detection in x-ray images to assist doctors
o In robotic navigation systems to track motion of objects or camera tracking
o Image recognition is great for marketers in order to optimize all of their marketing
strategies. By implementing logo detection, they can gain much clearer brand insights,
data, and metrics that they wouldn’t have if they weren’t using image recognition
technology
o automatic panorama stitching, is used in commercial panorama software such as Adobe
Photoshop to recover 3D camera rotations and camera distortion matrices in order to
align images into a very wide-angle panoramas
Why we need image recognition?
• Marketers can track how well a sponsorship is doing with image recognition
and logo detection which makes it much easier to figure out how much
revenue they will return
• Over 85% of logos within images posted to social media don’t contain any tag
or text brand mention
How image recognition works?
Image Recognition Using Machine Learning:
A machine learning approach to image recognition involves identifying and extracting key
features from images and using them as input to a machine learning model
Image Recognition Using Deep Learning:
A deep learning approach to image recognition may involve the use of a convolutional
neural network to automatically learn relevant features from sample images and
automatically identify those features in new images
Fig. denoting image recognition using Machine Learning
Machine Learning vs Deep Learning
• Machine learning uses algorithms to parse data, learn from that data, and make
informed decisions based on what it has learned
• Deep learning structures algorithms in layers to create an artificial “neural
network” that can learn and make intelligent decisions on its own
• Deep learning is a subfield of machine learning. While both fall under the broad
category of artificial intelligence, deep learning is the term that’s often used to
describe how human-like artificial intelligence works
Fig. denoting image recognition using Deep Learning
Neural Network
o A neural network is a system of interconnected artificial “neurons” that
exchange messages between each other
o The connections have numeric weights that are tuned during the training process, so
that a properly trained network will respond correctly when presented with an image
or pattern to recognize
o The network consists of multiple layers of feature-detecting “neurons”. Each layer
has many neurons that respond to different combinations of inputs from the
previous layers
o Typical CNNs use 5 to 25 distinct layers of pattern recognition
Convolutional Neural Network
Understanding CNN
• First, the computer tries to identify very simple
aspects of the images: lines, edges, corners, blobs,
etc. Using that information, we build up into slightly,
just slightly more complex shapes: squares, circles,
triangles
• After a few iterations, it starts to recognize high-
level features such as eyes, nose, mouth, etc. Finally,
by putting all the pieces together, it computes a
probability score for this image for each class of
objects it could belong to (e.g., cat, dog, bird, etc)
Understanding CNN
• Now the computer sees the image as an array of
pixels values. Let’s say the cat image we saw earlier
is of size 10x10x3 (where 3 represents the three
RGB values). Then the pixel value representation, for
one of the 3 RGB color channels, would look
something like this:
• Then, it scans this entire image a bunch of times,
each time looking for one specific feature
• There are a few patterns that the computer is
interested in: blobs, circles, colors, and edges. It
prepares a few reference objects where each
represents a blob, a circle, a color, an edge, etc. It
puts the reference object on the image and scans
over the image, looking for areas of overlap
between the reference and the scanned region
Understanding CNN
• This is how the computer looks for areas of overlap
between the reference and the scanned region
• In deep learning, this “reference object” is called
a filter (also referred to as kernel), and the part of
the image that is being compared to is called
a receptive field
I have a filter that tries to identify round shapes, then
my filter might look like this:
Understanding CNN
Applying this filter on a part of the image: This image denotes a dot product
between the filter and the receptive
field to compute how much they
overlap
Once the other filters like color, blobs and edges are computed the first layer of
convolution has been completed. This is called an activation map.
Since only one filter won’t be enough to identify other features Thus this process
repeats and more convolutional layers are formed.
Practical Applications
Medical Imaging:
• extensively used for cancer detection
• Retinopathy
Industrial Application:
• fault detection in manufacturing
Practical Applications
Security:
• Face and fingerprint recognition
Application for creative media:
• Deep dream
• Human and Computer interface
Practical Applications
Geographic Information Systems:
• Terrain Classification
• Meteorology
Astronomy:
• Enhancement of telescopic images
• Recognition of Astronomical Bodies
Future Prospect and Conclusion
• Google Self-Driven Cars
• fully automated machinery used in factories
• In space exploration
• AI powered robots
• Face recognition based ATM
Image recognition is a futuristic and relatively unexplored field, with wide areas of
practical applications, including industrial, scientific and medical applications.
This field has a lot of potential for development and implementation in new areas
like space exploration, processing signal images, computer vision etc.
References
• www.whatis.techtarget.com
• www.ieeeexplore.ieee.org
• www.wolfram.com
• www.shirleydu.com
• www.unitag.io
• Basic definitions and images from www.google.com
Image recognition

More Related Content

What's hot

AI Computer vision
AI Computer visionAI Computer vision
AI Computer visionKashafnaz2
 
Automated Face Detection System
Automated Face Detection SystemAutomated Face Detection System
Automated Face Detection SystemAbhiroop Ghatak
 
Detection and recognition of face using neural network
Detection and recognition of face using neural networkDetection and recognition of face using neural network
Detection and recognition of face using neural networkSmriti Tikoo
 
Face recognization
Face recognizationFace recognization
Face recognizationleenak770
 
Object Detection & Tracking
Object Detection & TrackingObject Detection & Tracking
Object Detection & TrackingAkshay Gujarathi
 
Face detection ppt
Face detection pptFace detection ppt
Face detection pptPooja R
 
Face detection presentation slide
Face detection  presentation slideFace detection  presentation slide
Face detection presentation slideSanjoy Dutta
 
What is computer vision?
What is computer vision?What is computer vision?
What is computer vision?Qentinel
 

What's hot (20)

AI Computer vision
AI Computer visionAI Computer vision
AI Computer vision
 
Image processing
Image processingImage processing
Image processing
 
Computer vision ppt
Computer vision pptComputer vision ppt
Computer vision ppt
 
Computer vision
Computer visionComputer vision
Computer vision
 
Automated Face Detection System
Automated Face Detection SystemAutomated Face Detection System
Automated Face Detection System
 
Computer Vision
Computer VisionComputer Vision
Computer Vision
 
Computer vision
Computer visionComputer vision
Computer vision
 
Detection and recognition of face using neural network
Detection and recognition of face using neural networkDetection and recognition of face using neural network
Detection and recognition of face using neural network
 
Object detection
Object detectionObject detection
Object detection
 
Computer vision
Computer vision Computer vision
Computer vision
 
Computer Vision
Computer VisionComputer Vision
Computer Vision
 
Computer vision
Computer visionComputer vision
Computer vision
 
Face recognization
Face recognizationFace recognization
Face recognization
 
Face Detection
Face DetectionFace Detection
Face Detection
 
Object Detection & Tracking
Object Detection & TrackingObject Detection & Tracking
Object Detection & Tracking
 
Face detection ppt
Face detection pptFace detection ppt
Face detection ppt
 
Face detection presentation slide
Face detection  presentation slideFace detection  presentation slide
Face detection presentation slide
 
What is computer vision?
What is computer vision?What is computer vision?
What is computer vision?
 
Computer vision
Computer visionComputer vision
Computer vision
 
EMOTION DETECTION USING AI
EMOTION DETECTION USING AIEMOTION DETECTION USING AI
EMOTION DETECTION USING AI
 

Similar to Image recognition

Computer Vision(4).pptx
Computer Vision(4).pptxComputer Vision(4).pptx
Computer Vision(4).pptxGouthamMaliga
 
imagerecognition-191220044946 (1).pdf
imagerecognition-191220044946 (1).pdfimagerecognition-191220044946 (1).pdf
imagerecognition-191220044946 (1).pdfSUBHASHREESUDHANSUSE
 
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine LearningMakine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine LearningAli Alkan
 
Face Recognition - Deep Learning
Face Recognition - Deep LearningFace Recognition - Deep Learning
Face Recognition - Deep LearningAashish Chaubey
 
Image_recognition.pptx
Image_recognition.pptxImage_recognition.pptx
Image_recognition.pptxjohn6938
 
Introduction to computer vision and
Introduction to computer vision andIntroduction to computer vision and
Introduction to computer vision andcodeprogramming
 
Traffic Automation System
Traffic Automation SystemTraffic Automation System
Traffic Automation SystemPrabal Chauhan
 
introdaction.pptx
introdaction.pptxintrodaction.pptx
introdaction.pptxDekebatufa
 
Emotion recognition and drowsiness detection using python.ppt
Emotion recognition and drowsiness detection using python.pptEmotion recognition and drowsiness detection using python.ppt
Emotion recognition and drowsiness detection using python.pptGopi Naidu
 
Computer Vision.pdf
Computer Vision.pdfComputer Vision.pdf
Computer Vision.pdfBantuBytes
 
Class PPT based on engineering subject cv.pptx
Class PPT based on engineering subject cv.pptxClass PPT based on engineering subject cv.pptx
Class PPT based on engineering subject cv.pptxDivyaKumari588020
 
AI UNIT 4 - SRCAS JOC.pptx enjoy this ppt
AI UNIT 4 - SRCAS JOC.pptx enjoy this pptAI UNIT 4 - SRCAS JOC.pptx enjoy this ppt
AI UNIT 4 - SRCAS JOC.pptx enjoy this pptPavankalayankusetty
 
What is Computer Vision?
What is Computer Vision?What is Computer Vision?
What is Computer Vision?Kavika Roy
 
Facial emotion detection on babies' emotional face using Deep Learning.
Facial emotion detection on babies' emotional face using Deep Learning.Facial emotion detection on babies' emotional face using Deep Learning.
Facial emotion detection on babies' emotional face using Deep Learning.Takrim Ul Islam Laskar
 
Project report of thr facial expressionppt.pptx
Project report of thr facial expressionppt.pptxProject report of thr facial expressionppt.pptx
Project report of thr facial expressionppt.pptxtaxihig737
 
Final Report on Optical Character Recognition
Final Report on Optical Character Recognition Final Report on Optical Character Recognition
Final Report on Optical Character Recognition Vidyut Singhania
 
An Introduction to Digital Image Analysis.pdf
An Introduction to Digital Image Analysis.pdfAn Introduction to Digital Image Analysis.pdf
An Introduction to Digital Image Analysis.pdfThe Lifesciences Magazine
 

Similar to Image recognition (20)

Computer Vision(4).pptx
Computer Vision(4).pptxComputer Vision(4).pptx
Computer Vision(4).pptx
 
imagerecognition-191220044946 (1).pdf
imagerecognition-191220044946 (1).pdfimagerecognition-191220044946 (1).pdf
imagerecognition-191220044946 (1).pdf
 
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine LearningMakine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
 
Face Recognition - Deep Learning
Face Recognition - Deep LearningFace Recognition - Deep Learning
Face Recognition - Deep Learning
 
Image_recognition.pptx
Image_recognition.pptxImage_recognition.pptx
Image_recognition.pptx
 
Introduction to computer vision and
Introduction to computer vision andIntroduction to computer vision and
Introduction to computer vision and
 
Traffic Automation System
Traffic Automation SystemTraffic Automation System
Traffic Automation System
 
introdaction.pptx
introdaction.pptxintrodaction.pptx
introdaction.pptx
 
Ch1.pptx
Ch1.pptxCh1.pptx
Ch1.pptx
 
Emotion recognition and drowsiness detection using python.ppt
Emotion recognition and drowsiness detection using python.pptEmotion recognition and drowsiness detection using python.ppt
Emotion recognition and drowsiness detection using python.ppt
 
Computer Vision.pdf
Computer Vision.pdfComputer Vision.pdf
Computer Vision.pdf
 
Class PPT based on engineering subject cv.pptx
Class PPT based on engineering subject cv.pptxClass PPT based on engineering subject cv.pptx
Class PPT based on engineering subject cv.pptx
 
Object recognition
Object recognitionObject recognition
Object recognition
 
AI UNIT 4 - SRCAS JOC.pptx enjoy this ppt
AI UNIT 4 - SRCAS JOC.pptx enjoy this pptAI UNIT 4 - SRCAS JOC.pptx enjoy this ppt
AI UNIT 4 - SRCAS JOC.pptx enjoy this ppt
 
What is Computer Vision?
What is Computer Vision?What is Computer Vision?
What is Computer Vision?
 
Facial emotion detection on babies' emotional face using Deep Learning.
Facial emotion detection on babies' emotional face using Deep Learning.Facial emotion detection on babies' emotional face using Deep Learning.
Facial emotion detection on babies' emotional face using Deep Learning.
 
Project report of thr facial expressionppt.pptx
Project report of thr facial expressionppt.pptxProject report of thr facial expressionppt.pptx
Project report of thr facial expressionppt.pptx
 
Final Report on Optical Character Recognition
Final Report on Optical Character Recognition Final Report on Optical Character Recognition
Final Report on Optical Character Recognition
 
Face Scope.pptx
Face Scope.pptxFace Scope.pptx
Face Scope.pptx
 
An Introduction to Digital Image Analysis.pdf
An Introduction to Digital Image Analysis.pdfAn Introduction to Digital Image Analysis.pdf
An Introduction to Digital Image Analysis.pdf
 

Recently uploaded

Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationSafe Software
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Wonjun Hwang
 
My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024The Digital Insurer
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxnull - The Open Security Community
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDGMarianaLemus7
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Neo4j
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersThousandEyes
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 3652toLead Limited
 
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024BookNet Canada
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitecturePixlogix Infotech
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 

Recently uploaded (20)

Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
 
My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDG
 
Hot Sexy call girls in Panjabi Bagh 🔝 9953056974 🔝 Delhi escort Service
Hot Sexy call girls in Panjabi Bagh 🔝 9953056974 🔝 Delhi escort ServiceHot Sexy call girls in Panjabi Bagh 🔝 9953056974 🔝 Delhi escort Service
Hot Sexy call girls in Panjabi Bagh 🔝 9953056974 🔝 Delhi escort Service
 
Vulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptxVulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptx
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
 
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC Architecture
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 

Image recognition

  • 2. What is image recognition? o Image Recognition is a technology that strives to acquire, process, analyse and understand images and high-dimensional data from real world in order to produce numerical or symbolic information o In other words it is a process of identifying and detecting an object or a feature in a digital image or video o It is also known as Computer Vision
  • 3. Why we need image recognition? o Image recognition is a vital component in robotics such as the driverless vehicles or domestic robots. It is also important in security systems such as face recognition o In image search engines such as Google or Bing image search whereby you use rich image content to query for similar stuff. Like in Google photos where the system uses image recognition to categorize your images into things like cats, dogs, people and so on o In medical imaging such as cancer detection in x-ray images to assist doctors o In robotic navigation systems to track motion of objects or camera tracking o Image recognition is great for marketers in order to optimize all of their marketing strategies. By implementing logo detection, they can gain much clearer brand insights, data, and metrics that they wouldn’t have if they weren’t using image recognition technology o automatic panorama stitching, is used in commercial panorama software such as Adobe Photoshop to recover 3D camera rotations and camera distortion matrices in order to align images into a very wide-angle panoramas
  • 4. Why we need image recognition? • Marketers can track how well a sponsorship is doing with image recognition and logo detection which makes it much easier to figure out how much revenue they will return • Over 85% of logos within images posted to social media don’t contain any tag or text brand mention
  • 5. How image recognition works? Image Recognition Using Machine Learning: A machine learning approach to image recognition involves identifying and extracting key features from images and using them as input to a machine learning model Image Recognition Using Deep Learning: A deep learning approach to image recognition may involve the use of a convolutional neural network to automatically learn relevant features from sample images and automatically identify those features in new images Fig. denoting image recognition using Machine Learning
  • 6. Machine Learning vs Deep Learning • Machine learning uses algorithms to parse data, learn from that data, and make informed decisions based on what it has learned • Deep learning structures algorithms in layers to create an artificial “neural network” that can learn and make intelligent decisions on its own • Deep learning is a subfield of machine learning. While both fall under the broad category of artificial intelligence, deep learning is the term that’s often used to describe how human-like artificial intelligence works Fig. denoting image recognition using Deep Learning
  • 7. Neural Network o A neural network is a system of interconnected artificial “neurons” that exchange messages between each other o The connections have numeric weights that are tuned during the training process, so that a properly trained network will respond correctly when presented with an image or pattern to recognize o The network consists of multiple layers of feature-detecting “neurons”. Each layer has many neurons that respond to different combinations of inputs from the previous layers o Typical CNNs use 5 to 25 distinct layers of pattern recognition
  • 9. Understanding CNN • First, the computer tries to identify very simple aspects of the images: lines, edges, corners, blobs, etc. Using that information, we build up into slightly, just slightly more complex shapes: squares, circles, triangles • After a few iterations, it starts to recognize high- level features such as eyes, nose, mouth, etc. Finally, by putting all the pieces together, it computes a probability score for this image for each class of objects it could belong to (e.g., cat, dog, bird, etc)
  • 10. Understanding CNN • Now the computer sees the image as an array of pixels values. Let’s say the cat image we saw earlier is of size 10x10x3 (where 3 represents the three RGB values). Then the pixel value representation, for one of the 3 RGB color channels, would look something like this: • Then, it scans this entire image a bunch of times, each time looking for one specific feature • There are a few patterns that the computer is interested in: blobs, circles, colors, and edges. It prepares a few reference objects where each represents a blob, a circle, a color, an edge, etc. It puts the reference object on the image and scans over the image, looking for areas of overlap between the reference and the scanned region
  • 11. Understanding CNN • This is how the computer looks for areas of overlap between the reference and the scanned region • In deep learning, this “reference object” is called a filter (also referred to as kernel), and the part of the image that is being compared to is called a receptive field I have a filter that tries to identify round shapes, then my filter might look like this:
  • 12. Understanding CNN Applying this filter on a part of the image: This image denotes a dot product between the filter and the receptive field to compute how much they overlap Once the other filters like color, blobs and edges are computed the first layer of convolution has been completed. This is called an activation map. Since only one filter won’t be enough to identify other features Thus this process repeats and more convolutional layers are formed.
  • 13. Practical Applications Medical Imaging: • extensively used for cancer detection • Retinopathy Industrial Application: • fault detection in manufacturing
  • 14. Practical Applications Security: • Face and fingerprint recognition Application for creative media: • Deep dream • Human and Computer interface
  • 15. Practical Applications Geographic Information Systems: • Terrain Classification • Meteorology Astronomy: • Enhancement of telescopic images • Recognition of Astronomical Bodies
  • 16. Future Prospect and Conclusion • Google Self-Driven Cars • fully automated machinery used in factories • In space exploration • AI powered robots • Face recognition based ATM Image recognition is a futuristic and relatively unexplored field, with wide areas of practical applications, including industrial, scientific and medical applications. This field has a lot of potential for development and implementation in new areas like space exploration, processing signal images, computer vision etc.
  • 17. References • www.whatis.techtarget.com • www.ieeeexplore.ieee.org • www.wolfram.com • www.shirleydu.com • www.unitag.io • Basic definitions and images from www.google.com