SlideShare a Scribd company logo
Introduction to
Computer Vision
Computer Vision Applications
● Image Recognition and Classification
● Object Detection
● Image Segmentation
● Video Analysis
● Style Transfer
● Generating new images
Computer Vision Applications
Image Classification
Extract ???
Deep Learning
● Deep learning is an approach to machine learning
characterized by deep stacks of computations.
● This depth of computation is what has enabled
deep learning models to disentangle the kinds of
complex and hierarchical patterns found in the
most challenging real-world datasets.
ML Extended
PROPRIETARY + CONFIDENTIAL
How it is done?
● You could think of each layer
in a neural network as
performing some kind of
relatively simple
transformation.
● Through a deep stack of
layers, a neural network can
transform its inputs in more
and more complex ways.
Neural Network
Image Classification
Extract - Visual Features
● a line,
● a color,
● a texture,
● a shape,
● a pattern or complex
pattern
Whole Process
Feature Extraction
The feature extraction performed by the
base consists of three basic operations:
1. Filter an image for a particular
feature (convolution)
2. Detect that feature within the filtered
image (ReLU)
3. Condense the image to enhance the
features (maximum pooling)
Filter with Convolution
Kernel
Visual features Kernel Extracts
Detect with ReLU
Condense with Maximum Pooling
The pooling step increases the proportion of active pixels to zero pixels.
How Convolution and Pooling happens?
● The convolution and pooling
operations share a common
feature: they are both performed
over a sliding window.
● With convolution, this "window"
is given by the dimensions of the
kernel, the parameter
kernel_size.
● With pooling, it is the pooling
window, given by pool_size
Stride - The Step Window moves
● We want high-quality features to
use for classification,
convolutional layers will most
often have strides=(1, 1).
● Increasing the stride Effect?
● For Pooling what should be
stride?
Padding - Treating Each Pixel Same
● When performing the sliding
window computation, there is a
question as to what to do at the
boundaries of the input.
● Staying entirely inside the input
image means the window will
never sit squarely over these
boundary pixels like it does for
every other pixel in the input.
Since we aren't treating all the
pixels exactly the same, could
there be a problem?
Want to Hear from You?
Some Interesting CV applications

More Related Content

What's hot

Object detection
Object detectionObject detection
Object detection
Jksuryawanshi
 
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
 
AI Computer vision
AI Computer visionAI Computer vision
AI Computer vision
Kashafnaz2
 
Human Emotion Recognition
Human Emotion RecognitionHuman Emotion Recognition
Human Emotion Recognition
Chaitanya Maddala
 
Deep learning based object detection basics
Deep learning based object detection basicsDeep learning based object detection basics
Deep learning based object detection basics
Brodmann17
 
CNN Tutorial
CNN TutorialCNN Tutorial
CNN Tutorial
Sungjoon Choi
 
IEEE EED2021 AI use cases in Computer Vision
IEEE EED2021 AI use cases in Computer VisionIEEE EED2021 AI use cases in Computer Vision
IEEE EED2021 AI use cases in Computer Vision
SAMeh Zaghloul
 
Image recognition
Image recognitionImage recognition
Image recognition
Nikhil Singh
 
Object Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning FrameworkObject Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning Framework
Nader Karimi
 
An introduction to Deep Learning
An introduction to Deep LearningAn introduction to Deep Learning
An introduction to Deep Learning
Julien SIMON
 
Computer vision
Computer visionComputer vision
Computer vision
Mahmoud Hussein
 
Convolutional neural network
Convolutional neural networkConvolutional neural network
Convolutional neural network
MojammilHusain
 
Image classification with Deep Neural Networks
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural Networks
Yogendra Tamang
 
Computer vision
Computer visionComputer vision
Computer vision
Kartik Kalpande Patil
 
Computer Vision for Beginners
Computer Vision for BeginnersComputer Vision for Beginners
Computer Vision for Beginners
Sanghamitra Deb
 
Convolutional Neural Network
Convolutional Neural NetworkConvolutional Neural Network
Convolutional Neural Network
Vignesh Suresh
 
Computer vision
Computer visionComputer vision
Computer vision
AnkitKamal6
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
leopauly
 
Image classification using cnn
Image classification using cnnImage classification using cnn
Image classification using cnn
SumeraHangi
 
Computer Vision
Computer VisionComputer Vision
Computer Vision
ArtiKhanchandani
 

What's hot (20)

Object detection
Object detectionObject detection
Object detection
 
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.
 
AI Computer vision
AI Computer visionAI Computer vision
AI Computer vision
 
Human Emotion Recognition
Human Emotion RecognitionHuman Emotion Recognition
Human Emotion Recognition
 
Deep learning based object detection basics
Deep learning based object detection basicsDeep learning based object detection basics
Deep learning based object detection basics
 
CNN Tutorial
CNN TutorialCNN Tutorial
CNN Tutorial
 
IEEE EED2021 AI use cases in Computer Vision
IEEE EED2021 AI use cases in Computer VisionIEEE EED2021 AI use cases in Computer Vision
IEEE EED2021 AI use cases in Computer Vision
 
Image recognition
Image recognitionImage recognition
Image recognition
 
Object Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning FrameworkObject Detection Using R-CNN Deep Learning Framework
Object Detection Using R-CNN Deep Learning Framework
 
An introduction to Deep Learning
An introduction to Deep LearningAn introduction to Deep Learning
An introduction to Deep Learning
 
Computer vision
Computer visionComputer vision
Computer vision
 
Convolutional neural network
Convolutional neural networkConvolutional neural network
Convolutional neural network
 
Image classification with Deep Neural Networks
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural Networks
 
Computer vision
Computer visionComputer vision
Computer vision
 
Computer Vision for Beginners
Computer Vision for BeginnersComputer Vision for Beginners
Computer Vision for Beginners
 
Convolutional Neural Network
Convolutional Neural NetworkConvolutional Neural Network
Convolutional Neural Network
 
Computer vision
Computer visionComputer vision
Computer vision
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
 
Image classification using cnn
Image classification using cnnImage classification using cnn
Image classification using cnn
 
Computer Vision
Computer VisionComputer Vision
Computer Vision
 

Similar to Computer Vision.pptx

Convolution Neural Network (CNN)
Convolution Neural Network (CNN)Convolution Neural Network (CNN)
Convolution Neural Network (CNN)
Suraj Aavula
 
NMO IE-2 Activity Presentation.pptx
NMO IE-2 Activity Presentation.pptxNMO IE-2 Activity Presentation.pptx
NMO IE-2 Activity Presentation.pptx
LEGENDARYTECHNICAL
 
NMO IE-2 Activity Presentation.pptx
NMO IE-2 Activity Presentation.pptxNMO IE-2 Activity Presentation.pptx
NMO IE-2 Activity Presentation.pptx
LEGENDARYTECHNICAL
 
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
Ali Alkan
 
Mnist report
Mnist reportMnist report
Mnist report
RaghunandanJairam
 
Mnist report ppt
Mnist report pptMnist report ppt
Mnist report ppt
RaghunandanJairam
 
物件偵測與辨識技術
物件偵測與辨識技術物件偵測與辨識技術
物件偵測與辨識技術
CHENHuiMei
 
cnn ppt.pptx
cnn ppt.pptxcnn ppt.pptx
cnn ppt.pptx
rohithprabhas1
 
interface and user experience. Responsive Design: Ensure the app is user-frie...
interface and user experience. Responsive Design: Ensure the app is user-frie...interface and user experience. Responsive Design: Ensure the app is user-frie...
interface and user experience. Responsive Design: Ensure the app is user-frie...
rairaistar863
 
Handwritten Digit Recognition(Convolutional Neural Network) PPT
Handwritten Digit Recognition(Convolutional Neural Network) PPTHandwritten Digit Recognition(Convolutional Neural Network) PPT
Handwritten Digit Recognition(Convolutional Neural Network) PPT
RishabhTyagi48
 
CNN.pptx.pdf
CNN.pptx.pdfCNN.pptx.pdf
CNN.pptx.pdf
Knoldus Inc.
 
UNIT-4.pdf
UNIT-4.pdfUNIT-4.pdf
UNIT-4.pdf
NiharikaThakur32
 
UNIT-4.pdf
UNIT-4.pdfUNIT-4.pdf
UNIT-4.pdf
NiharikaThakur32
 
3 CG_U1_P2_PPT_3 OpenGL.pptx
3 CG_U1_P2_PPT_3 OpenGL.pptx3 CG_U1_P2_PPT_3 OpenGL.pptx
3 CG_U1_P2_PPT_3 OpenGL.pptx
ssuser255bf1
 
Computer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonComputer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathon
Aditya Bhattacharya
 
UNIT-4.pptx
UNIT-4.pptxUNIT-4.pptx
UNIT-4.pptx
NiharikaThakur32
 
Scalable image recognition model with deep embedding
Scalable image recognition model with deep embeddingScalable image recognition model with deep embedding
Scalable image recognition model with deep embedding
捷恩 蔡
 
V2.0 open power ai virtual university deep learning and ai introduction
V2.0 open power ai virtual university   deep learning and ai introductionV2.0 open power ai virtual university   deep learning and ai introduction
V2.0 open power ai virtual university deep learning and ai introduction
Ganesan Narayanasamy
 
Real Time Sign Language Recognition Using Deep Learning
Real Time Sign Language Recognition Using Deep LearningReal Time Sign Language Recognition Using Deep Learning
Real Time Sign Language Recognition Using Deep Learning
IRJET Journal
 
Object detection with deep learning
Object detection with deep learningObject detection with deep learning
Object detection with deep learning
Sushant Shrivastava
 

Similar to Computer Vision.pptx (20)

Convolution Neural Network (CNN)
Convolution Neural Network (CNN)Convolution Neural Network (CNN)
Convolution Neural Network (CNN)
 
NMO IE-2 Activity Presentation.pptx
NMO IE-2 Activity Presentation.pptxNMO IE-2 Activity Presentation.pptx
NMO IE-2 Activity Presentation.pptx
 
NMO IE-2 Activity Presentation.pptx
NMO IE-2 Activity Presentation.pptxNMO IE-2 Activity Presentation.pptx
NMO IE-2 Activity Presentation.pptx
 
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
 
Mnist report
Mnist reportMnist report
Mnist report
 
Mnist report ppt
Mnist report pptMnist report ppt
Mnist report ppt
 
物件偵測與辨識技術
物件偵測與辨識技術物件偵測與辨識技術
物件偵測與辨識技術
 
cnn ppt.pptx
cnn ppt.pptxcnn ppt.pptx
cnn ppt.pptx
 
interface and user experience. Responsive Design: Ensure the app is user-frie...
interface and user experience. Responsive Design: Ensure the app is user-frie...interface and user experience. Responsive Design: Ensure the app is user-frie...
interface and user experience. Responsive Design: Ensure the app is user-frie...
 
Handwritten Digit Recognition(Convolutional Neural Network) PPT
Handwritten Digit Recognition(Convolutional Neural Network) PPTHandwritten Digit Recognition(Convolutional Neural Network) PPT
Handwritten Digit Recognition(Convolutional Neural Network) PPT
 
CNN.pptx.pdf
CNN.pptx.pdfCNN.pptx.pdf
CNN.pptx.pdf
 
UNIT-4.pdf
UNIT-4.pdfUNIT-4.pdf
UNIT-4.pdf
 
UNIT-4.pdf
UNIT-4.pdfUNIT-4.pdf
UNIT-4.pdf
 
3 CG_U1_P2_PPT_3 OpenGL.pptx
3 CG_U1_P2_PPT_3 OpenGL.pptx3 CG_U1_P2_PPT_3 OpenGL.pptx
3 CG_U1_P2_PPT_3 OpenGL.pptx
 
Computer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonComputer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathon
 
UNIT-4.pptx
UNIT-4.pptxUNIT-4.pptx
UNIT-4.pptx
 
Scalable image recognition model with deep embedding
Scalable image recognition model with deep embeddingScalable image recognition model with deep embedding
Scalable image recognition model with deep embedding
 
V2.0 open power ai virtual university deep learning and ai introduction
V2.0 open power ai virtual university   deep learning and ai introductionV2.0 open power ai virtual university   deep learning and ai introduction
V2.0 open power ai virtual university deep learning and ai introduction
 
Real Time Sign Language Recognition Using Deep Learning
Real Time Sign Language Recognition Using Deep LearningReal Time Sign Language Recognition Using Deep Learning
Real Time Sign Language Recognition Using Deep Learning
 
Object detection with deep learning
Object detection with deep learningObject detection with deep learning
Object detection with deep learning
 

More from GDSCIIITDHARWAD

GDSC GIT AND GITHUB
GDSC GIT AND GITHUB GDSC GIT AND GITHUB
GDSC GIT AND GITHUB
GDSCIIITDHARWAD
 
GCCP-Session 2
GCCP-Session 2GCCP-Session 2
GCCP-Session 2
GDSCIIITDHARWAD
 
GCCP - Session #3
GCCP - Session #3GCCP - Session #3
GCCP - Session #3
GDSCIIITDHARWAD
 
Copy of Week #1
Copy of Week #1Copy of Week #1
Copy of Week #1
GDSCIIITDHARWAD
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
GDSCIIITDHARWAD
 
Firebase .pptx
Firebase .pptxFirebase .pptx
Firebase .pptx
GDSCIIITDHARWAD
 
Be the next Lead.pdf
Be the next Lead.pdfBe the next Lead.pdf
Be the next Lead.pdf
GDSCIIITDHARWAD
 
Flutter Forward Event .pptx
Flutter Forward Event .pptxFlutter Forward Event .pptx
Flutter Forward Event .pptx
GDSCIIITDHARWAD
 
web-dev-day2.pdf
web-dev-day2.pdfweb-dev-day2.pdf
web-dev-day2.pdf
GDSCIIITDHARWAD
 
web-dev-day2.pdf
web-dev-day2.pdfweb-dev-day2.pdf
web-dev-day2.pdf
GDSCIIITDHARWAD
 
Web Day-01.pptx
Web Day-01.pptxWeb Day-01.pptx
Web Day-01.pptx
GDSCIIITDHARWAD
 

More from GDSCIIITDHARWAD (11)

GDSC GIT AND GITHUB
GDSC GIT AND GITHUB GDSC GIT AND GITHUB
GDSC GIT AND GITHUB
 
GCCP-Session 2
GCCP-Session 2GCCP-Session 2
GCCP-Session 2
 
GCCP - Session #3
GCCP - Session #3GCCP - Session #3
GCCP - Session #3
 
Copy of Week #1
Copy of Week #1Copy of Week #1
Copy of Week #1
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 
Firebase .pptx
Firebase .pptxFirebase .pptx
Firebase .pptx
 
Be the next Lead.pdf
Be the next Lead.pdfBe the next Lead.pdf
Be the next Lead.pdf
 
Flutter Forward Event .pptx
Flutter Forward Event .pptxFlutter Forward Event .pptx
Flutter Forward Event .pptx
 
web-dev-day2.pdf
web-dev-day2.pdfweb-dev-day2.pdf
web-dev-day2.pdf
 
web-dev-day2.pdf
web-dev-day2.pdfweb-dev-day2.pdf
web-dev-day2.pdf
 
Web Day-01.pptx
Web Day-01.pptxWeb Day-01.pptx
Web Day-01.pptx
 

Recently uploaded

CEC 352 - SATELLITE COMMUNICATION UNIT 1
CEC 352 - SATELLITE COMMUNICATION UNIT 1CEC 352 - SATELLITE COMMUNICATION UNIT 1
CEC 352 - SATELLITE COMMUNICATION UNIT 1
PKavitha10
 
Generative AI leverages algorithms to create various forms of content
Generative AI leverages algorithms to create various forms of contentGenerative AI leverages algorithms to create various forms of content
Generative AI leverages algorithms to create various forms of content
Hitesh Mohapatra
 
Software Engineering and Project Management - Introduction, Modeling Concepts...
Software Engineering and Project Management - Introduction, Modeling Concepts...Software Engineering and Project Management - Introduction, Modeling Concepts...
Software Engineering and Project Management - Introduction, Modeling Concepts...
Prakhyath Rai
 
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...
IJECEIAES
 
Applications of artificial Intelligence in Mechanical Engineering.pdf
Applications of artificial Intelligence in Mechanical Engineering.pdfApplications of artificial Intelligence in Mechanical Engineering.pdf
Applications of artificial Intelligence in Mechanical Engineering.pdf
Atif Razi
 
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.pptUnit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
KrishnaveniKrishnara1
 
Embedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoringEmbedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoring
IJECEIAES
 
官方认证美国密歇根州立大学毕业证学位证书原版一模一样
官方认证美国密歇根州立大学毕业证学位证书原版一模一样官方认证美国密歇根州立大学毕业证学位证书原版一模一样
官方认证美国密歇根州立大学毕业证学位证书原版一模一样
171ticu
 
Software Quality Assurance-se412-v11.ppt
Software Quality Assurance-se412-v11.pptSoftware Quality Assurance-se412-v11.ppt
Software Quality Assurance-se412-v11.ppt
TaghreedAltamimi
 
Manufacturing Process of molasses based distillery ppt.pptx
Manufacturing Process of molasses based distillery ppt.pptxManufacturing Process of molasses based distillery ppt.pptx
Manufacturing Process of molasses based distillery ppt.pptx
Madan Karki
 
Computational Engineering IITH Presentation
Computational Engineering IITH PresentationComputational Engineering IITH Presentation
Computational Engineering IITH Presentation
co23btech11018
 
An Introduction to the Compiler Designss
An Introduction to the Compiler DesignssAn Introduction to the Compiler Designss
An Introduction to the Compiler Designss
ElakkiaU
 
BRAIN TUMOR DETECTION for seminar ppt.pdf
BRAIN TUMOR DETECTION for seminar ppt.pdfBRAIN TUMOR DETECTION for seminar ppt.pdf
BRAIN TUMOR DETECTION for seminar ppt.pdf
LAXMAREDDY22
 
Properties Railway Sleepers and Test.pptx
Properties Railway Sleepers and Test.pptxProperties Railway Sleepers and Test.pptx
Properties Railway Sleepers and Test.pptx
MDSABBIROJJAMANPAYEL
 
Material for memory and display system h
Material for memory and display system hMaterial for memory and display system h
Material for memory and display system h
gowrishankartb2005
 
integral complex analysis chapter 06 .pdf
integral complex analysis chapter 06 .pdfintegral complex analysis chapter 06 .pdf
integral complex analysis chapter 06 .pdf
gaafergoudaay7aga
 
Rainfall intensity duration frequency curve statistical analysis and modeling...
Rainfall intensity duration frequency curve statistical analysis and modeling...Rainfall intensity duration frequency curve statistical analysis and modeling...
Rainfall intensity duration frequency curve statistical analysis and modeling...
bijceesjournal
 
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
shadow0702a
 
Seminar on Distillation study-mafia.pptx
Seminar on Distillation study-mafia.pptxSeminar on Distillation study-mafia.pptx
Seminar on Distillation study-mafia.pptx
Madan Karki
 
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
insn4465
 

Recently uploaded (20)

CEC 352 - SATELLITE COMMUNICATION UNIT 1
CEC 352 - SATELLITE COMMUNICATION UNIT 1CEC 352 - SATELLITE COMMUNICATION UNIT 1
CEC 352 - SATELLITE COMMUNICATION UNIT 1
 
Generative AI leverages algorithms to create various forms of content
Generative AI leverages algorithms to create various forms of contentGenerative AI leverages algorithms to create various forms of content
Generative AI leverages algorithms to create various forms of content
 
Software Engineering and Project Management - Introduction, Modeling Concepts...
Software Engineering and Project Management - Introduction, Modeling Concepts...Software Engineering and Project Management - Introduction, Modeling Concepts...
Software Engineering and Project Management - Introduction, Modeling Concepts...
 
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...
 
Applications of artificial Intelligence in Mechanical Engineering.pdf
Applications of artificial Intelligence in Mechanical Engineering.pdfApplications of artificial Intelligence in Mechanical Engineering.pdf
Applications of artificial Intelligence in Mechanical Engineering.pdf
 
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.pptUnit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
 
Embedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoringEmbedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoring
 
官方认证美国密歇根州立大学毕业证学位证书原版一模一样
官方认证美国密歇根州立大学毕业证学位证书原版一模一样官方认证美国密歇根州立大学毕业证学位证书原版一模一样
官方认证美国密歇根州立大学毕业证学位证书原版一模一样
 
Software Quality Assurance-se412-v11.ppt
Software Quality Assurance-se412-v11.pptSoftware Quality Assurance-se412-v11.ppt
Software Quality Assurance-se412-v11.ppt
 
Manufacturing Process of molasses based distillery ppt.pptx
Manufacturing Process of molasses based distillery ppt.pptxManufacturing Process of molasses based distillery ppt.pptx
Manufacturing Process of molasses based distillery ppt.pptx
 
Computational Engineering IITH Presentation
Computational Engineering IITH PresentationComputational Engineering IITH Presentation
Computational Engineering IITH Presentation
 
An Introduction to the Compiler Designss
An Introduction to the Compiler DesignssAn Introduction to the Compiler Designss
An Introduction to the Compiler Designss
 
BRAIN TUMOR DETECTION for seminar ppt.pdf
BRAIN TUMOR DETECTION for seminar ppt.pdfBRAIN TUMOR DETECTION for seminar ppt.pdf
BRAIN TUMOR DETECTION for seminar ppt.pdf
 
Properties Railway Sleepers and Test.pptx
Properties Railway Sleepers and Test.pptxProperties Railway Sleepers and Test.pptx
Properties Railway Sleepers and Test.pptx
 
Material for memory and display system h
Material for memory and display system hMaterial for memory and display system h
Material for memory and display system h
 
integral complex analysis chapter 06 .pdf
integral complex analysis chapter 06 .pdfintegral complex analysis chapter 06 .pdf
integral complex analysis chapter 06 .pdf
 
Rainfall intensity duration frequency curve statistical analysis and modeling...
Rainfall intensity duration frequency curve statistical analysis and modeling...Rainfall intensity duration frequency curve statistical analysis and modeling...
Rainfall intensity duration frequency curve statistical analysis and modeling...
 
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
 
Seminar on Distillation study-mafia.pptx
Seminar on Distillation study-mafia.pptxSeminar on Distillation study-mafia.pptx
Seminar on Distillation study-mafia.pptx
 
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
 

Computer Vision.pptx

  • 2.
  • 3. Computer Vision Applications ● Image Recognition and Classification ● Object Detection ● Image Segmentation ● Video Analysis ● Style Transfer ● Generating new images
  • 7. ● Deep learning is an approach to machine learning characterized by deep stacks of computations. ● This depth of computation is what has enabled deep learning models to disentangle the kinds of complex and hierarchical patterns found in the most challenging real-world datasets. ML Extended PROPRIETARY + CONFIDENTIAL
  • 8. How it is done?
  • 9. ● You could think of each layer in a neural network as performing some kind of relatively simple transformation. ● Through a deep stack of layers, a neural network can transform its inputs in more and more complex ways. Neural Network
  • 10. Image Classification Extract - Visual Features ● a line, ● a color, ● a texture, ● a shape, ● a pattern or complex pattern
  • 12. Feature Extraction The feature extraction performed by the base consists of three basic operations: 1. Filter an image for a particular feature (convolution) 2. Detect that feature within the filtered image (ReLU) 3. Condense the image to enhance the features (maximum pooling)
  • 16. Condense with Maximum Pooling The pooling step increases the proportion of active pixels to zero pixels.
  • 17.
  • 18. How Convolution and Pooling happens? ● The convolution and pooling operations share a common feature: they are both performed over a sliding window. ● With convolution, this "window" is given by the dimensions of the kernel, the parameter kernel_size. ● With pooling, it is the pooling window, given by pool_size
  • 19. Stride - The Step Window moves ● We want high-quality features to use for classification, convolutional layers will most often have strides=(1, 1). ● Increasing the stride Effect? ● For Pooling what should be stride?
  • 20. Padding - Treating Each Pixel Same ● When performing the sliding window computation, there is a question as to what to do at the boundaries of the input. ● Staying entirely inside the input image means the window will never sit squarely over these boundary pixels like it does for every other pixel in the input. Since we aren't treating all the pixels exactly the same, could there be a problem?
  • 21. Want to Hear from You? Some Interesting CV applications

Editor's Notes

  1. This session will go into a little more detail about machine learning. It is helpful if you have already completed some introduction to machine learning but if you have any questions please ask.
  2. Here is a list representing some of the things a machine learning system can be trained to do. Question: What are some examples of features and products that you assume use machine learning? How could you tell it was ML?
  3. Here is a list representing some of the things a machine learning system can be trained to do. Question: What are some examples of features and products that you assume use machine learning? How could you tell it was ML?
  4. Here is a list representing some of the things a machine learning system can be trained to do. Question: What are some examples of features and products that you assume use machine learning? How could you tell it was ML?
  5. Use your computer and go to news.google.com or some other search engine to find and read a couple of online news articles involving applications of ML. Note: Sometimes news stories refer to ML as artificial intelligence (AI). While you are reading, think about these questions. Give learners 20 minutes to complete this task.
  6. Let's review. How would you explain machine learning? Answers could include (shown on the following slides): Machine learning is a specific field of AI where a system learns to find patterns in examples in order to make predictions. Computers learning how to do a task without being explicitly programmed to do so.
  7. Here's one definition.
  8. Use your computer and go to news.google.com or some other search engine to find and read a couple of online news articles involving applications of ML. Note: Sometimes news stories refer to ML as artificial intelligence (AI). While you are reading, think about these questions. Give learners 20 minutes to complete this task.
  9. Use your computer and go to news.google.com or some other search engine to find and read a couple of online news articles involving applications of ML. Note: Sometimes news stories refer to ML as artificial intelligence (AI). While you are reading, think about these questions. Give learners 20 minutes to complete this task.
  10. In the previous slide, I said supervised machine learning is analogous to a student taking a test. Let's say I created the 4 machine learning regression models above. Which one is the best? It depends on your goal and what variable you are trying to optimize for. To grade how well a model is doing on its test, machine learning practitioners measure the distance between the model's prediction (indicated in these graphs by the blue line) and the example data. This is known as loss. [Click to animate slide] With the loss displayed. Which model is best at achieving the goal? [Click to animate slide] Model #3 has the lowest loss which indicates this model is best at achieving the goal.
  11. Features are the variables which distinguish one example from another. They tell the machine learning model what parts of the data to look for patterns for achieving the goal. The first three variables would probably help the model determine a home price the other two probably would not. So lots of data is crucial to a machine learning system but it needs to be helpful and relevant data. Though you never know until you experiment to see what variables truly make an impact.
  12. Ask learners to come up with a list of features which might be helpful in recommending the next video to watch. The last two might turn out to be very important variables, there's no way to know unless you experiment.
  13. Ask learners to come up with a list of features which might be helpful in recommending the next video to watch. The last two might turn out to be very important variables, there's no way to know unless you experiment.
  14. What about the scenario make it suitable for ML? Lots of examples of data Can run experiments to see which variables have an effect What is the benefit for the business or individual? The model can get the most visibility for their customer Would a human perform the job better? With so many variables, a human could get a sense for optimal times for a specific situation but it would become complex if the product, influencer, audience, etc were changed What are the inputs to the system? Potential variables could include: Time of day, person posting, brand, product, social network How could the ML model go wrong? If trained only for a specific type of post, product, etc it might not generalize to another scenario If the training data is for the wrong demographic (gender, age, marital status, etc) the patterns might not be relevant.
  15. Give learners 2 minutes to create their own scenario. Have them turn to the person next to them and present the scenario. The other person has 2 minutes to answer the questions on the slide. Learners swap roles and repeat steps 2 and 3.
  16. Features are the variables which distinguish one example from another. They tell the machine learning model what parts of the data to look for patterns for achieving the goal. The first three variables would probably help the model determine a home price the other two probably would not. So lots of data is crucial to a machine learning system but it needs to be helpful and relevant data. Though you never know until you experiment to see what variables truly make an impact.
  17. Features are the variables which distinguish one example from another. They tell the machine learning model what parts of the data to look for patterns for achieving the goal. The first three variables would probably help the model determine a home price the other two probably would not. So lots of data is crucial to a machine learning system but it needs to be helpful and relevant data. Though you never know until you experiment to see what variables truly make an impact.
  18. Features are the variables which distinguish one example from another. They tell the machine learning model what parts of the data to look for patterns for achieving the goal. The first three variables would probably help the model determine a home price the other two probably would not. So lots of data is crucial to a machine learning system but it needs to be helpful and relevant data. Though you never know until you experiment to see what variables truly make an impact.
  19. Let's review. How would you explain machine learning? Answers could include (shown on the following slides): Machine learning is a specific field of AI where a system learns to find patterns in examples in order to make predictions. Computers learning how to do a task without being explicitly programmed to do so.