SlideShare a Scribd company logo
Object Recognition Tutorial
Beatrice van Eden
- Part time PhD Student at the University of the Witwatersrand.
- Fulltime employee of the Council for Scientific and Industrial Research.
Research Problem
• Hierarchical concept
formation
• This research will allow a robot to
learn about its environment
autonomously
• Build a concept about these
environments
• Even if it has not seen that specific
instance previously
Why Object Recognition
• Environments are build up by different objects
• RGB-D Sensor for perception
• Concept formation need some base line to work from
• Exposure to ML techniques
• Cascading classifiers
• Convolutional Neural Networks
• Support Vector Machine
Index: Cascading Classifiers
• Cascading classifiers
• Haar-like features
• Local binary patterns
• Implementation
• Results
Cascading classifiers
• Cascading is a particular case of ensemble
learning based on the concatenation of several
classifiers, using all information collected from
the output from a given classifier as additional
information for the next classifier in the cascade.
Haar-like features
• The difference of the sum of pixels of areas inside the
rectangle
• The values indicate certain characteristics of a particular area
of the image.
Haar-like features
• The Viola-Jones detector is a strong, binary classifier build of
several weak detectors
• Does a certain sub-region of the original image contain an
instance of the object of interest or not
Local binary patterns
• Divide the examined window into cells (e.g. 16x16 pixels for
each cell).
• For each pixel in a cell, compare the pixel to each of its 8
neighbours (on its left-top, left-middle, left-bottom, right-top,
etc.). Follow the pixels along a circle, i.e. clockwise or counter-
clockwise.
• Where the centre pixel's value is greater than the neighbour's
value, write "1". Otherwise, write "0". This gives an 8-digit
binary number.
• Compute the histogram, over the cell, of the frequency of
each "number" occurring.
• Optionally normalize the histogram.
• Concatenate (normalized) histograms of all cells. This gives the
feature vector for the window.
Local binary patterns
• a Powerful feature for texture classification
• LBP is faster but less accurate than Haar.
• LBP does all the calculations in integers. Haar uses floats.
• LBP few hours of training Haar few days
Implementation
• SAMPLES - How many images do we need?
• Depend on a variety of factors, including the quality of the
images, the object you want to recognize, the method to
generate the samples, the CPU power you have and probably
some magic.
• Positive images 50 -> 1500, list in .txt file.
• Negative images 1500, list in .txt file.
Implementation
• Create samples with OpenCV, generates a large number of
positive samples from our positive images, by applying
transformations and distortions. Used a Perl script to combine
positive image with negative image
• *.vec file are created, merge them into one
• opencv_haartraining and opencv_traincascade.
opencv_traincascade supports both Haar [Viola2001] and LBP
[Liao2007] (Local Binary Patterns) features.
Implementation
Implementation
• http://coding-robin.de/2013/07/22/train-your-own-opencv-
haar-classifier.html
• Video LBP – Coke Can
• Video Haar – Coke Can
• Video LBP – Face recognition
• Choose amount of stages to train
Results
• To be generated – working on confusion matrix
•
Index: CNN
• Convolutional Neural Networks
• Example
• Overview and Intuition
• Implementation
• Results
Convolutional Neural Networks
• Neural network vs. Convolutional neural network
• Layers used to build ConvNets
• Convolutional Layer, Pooling Layer, and Fully-Connected Layer
(exactly as seen in regular Neural Networks).
Example
• Input:
• Image: width 32, height 32, three colour channels.
• CONV layer:
• Local filter over previous layer
• Dot product between weights and sliding region in the input volume.
[32x32x12]
• RELU layer:
• Apply an elementwise activation function, such as the max(0,x)
thresholding at zero. This leaves the size of the volume unchanged.
• POOL layer:
• Down sampling operation along the spatial dimensions (width,
height). [16x16x12]
• FC layer:
• Compute the class scores. As with ordinary Neural Networks each
neuron in this layer will be connected to all the numbers in the
previous volume.
Convolutional Neural Networks
• CNN is a type of feed-forward artificial neural network where
the individual neurons are tiled in such a way that they
respond to overlapping regions in the visual field.
Overview and Intuition
• CONV layer's parameters consist of a set of learnable filters
• Every filter is small spatially (along width and height), but
extends through the full depth of the input volume
• As we slide the filter, across the input, we are computing the
dot product between the entries of the filter and the input
• Intuitively, the network will learn filters that activate when
they see some specific type of feature at some spatial position
in the input
• Stacking these activation maps for all filters along the depth
dimension forms the full output volume
Convolutional Neural Networks
• Three hyperparameters control the size of the output volume:
the depth, stride and zero-padding
• Depth of the output volume is a hyperparameter that we can
pick. It controls the number of neurons in the Conv layer that
connect to the same region of the input volume.
• We specify the stride with which we allocate depth columns
around the spatial dimensions (width and height).
• Zero padding allow us to control the spatial size of the output
volumes.
Example filters learned
Implementation
http://danielnouri.org/notes/2014/12/17/using-convolutional-neural-nets-to-detect-facial-keypoints-tutorial/#the-data
• Lasagne, a library for building neural networks with Python
and Theano.
• CPU vs. CUDA-capable GPU
• Ran the MNIST example (Recognise 0-9 digits).
• Facial key point
• Data available as *.csv files. Load training
and test data.
• Video CNN – Coke Can
• Video CNN – Coke Can
The predictions of
net1 on the left
compared to the
predictions of net2.
Results
• To be generated – working on confusion matrix
•
Index: SVM
• Support Vector Machine
• Histogram of Oriented Gradients
• Implementation
• Results
Support Vector Machine
• Given a set of training examples, each marked for belonging to
one of two categories, an SVM training algorithm builds a
model that assigns new examples into one category or the
other.
What is the goal of the Support
Vector Machine (SVM)?
• The goal of a support vector machine is to find the optimal
separating hyperplane which maximizes the margin of the
training data.
Histogram of Oriented Gradients
• The technique counts occurrences of gradient orientation in
localized portions of an image
• The descriptor is made up of M*N cells covering the image
window in a grid.
• Each cell is represented by a histogram of edge orientations,
where the number of discretized edge orientations is a parameter
(usually 9).
• The cell histogram is visualized by a 'star' showing the strength of
the edge orientations in the histogram: the stronger a specific
orientation, the longer it is relative to the others.
• Note that there are various normalization schemes:
• Local schemes, in which the cell in normalized with respect to
neighboring cells only [Dalal-Triggs]
• Global schemes, in which the orientation length is normalized by
all the cells
• Also note that some authors use multiple local normalizations per
cell
Histogram of Oriented Gradients
The example below shows a model of a bike (from Felzenszwalb et al.)
with HoG consisting of 7*11 cells, each with 8 orientations
• (a) Test image
• (b) Gradient image of the test image
• (c) Orientation and magnitude of Gradient in each cell
• (d) HoG of cells
• (e) Average gradient image over the training example
• (f) Weights of positive SVM in the block
• (g) HoG descriptor weighted by the positive SVM weights
Histogram of Oriented Gradients
Implementation
• http://solvedstack.com/questions/svm-classifier-based-on-
hog-features-for-object-detection-in-opencv
• http://thebrainiac1.blogspot.com/2012/07/v-
behaviorurldefaultvmlo.html
• Video HoG – Coke Can
• Video HoG – Face recognition
Implementation
Results
• To be generated – working on confusion matrix
Conclusion
• Cascading classifiers
• Convolutional Neural Networks
• Support Vector Machine
Thank you

More Related Content

What's hot

Introduction to CNN
Introduction to CNNIntroduction to CNN
Introduction to CNN
Shuai Zhang
 
PR-217: EfficientDet: Scalable and Efficient Object Detection
PR-217: EfficientDet: Scalable and Efficient Object DetectionPR-217: EfficientDet: Scalable and Efficient Object Detection
PR-217: EfficientDet: Scalable and Efficient Object Detection
Jinwon Lee
 
PR-270: PP-YOLO: An Effective and Efficient Implementation of Object Detector
PR-270: PP-YOLO: An Effective and Efficient Implementation of Object DetectorPR-270: PP-YOLO: An Effective and Efficient Implementation of Object Detector
PR-270: PP-YOLO: An Effective and Efficient Implementation of Object Detector
Jinwon Lee
 
Introduction to Convolutional Neural Networks
Introduction to Convolutional Neural NetworksIntroduction to Convolutional Neural Networks
Introduction to Convolutional Neural Networks
Hannes Hapke
 
Deep learning
Deep learningDeep learning
Deep learning
Rouyun Pan
 
ShuffleNet - PR054
ShuffleNet - PR054ShuffleNet - PR054
ShuffleNet - PR054
Jinwon Lee
 
Rethinking Attention with Performers
Rethinking Attention with PerformersRethinking Attention with Performers
Rethinking Attention with Performers
Joonhyung Lee
 
Exploring Randomly Wired Neural Networks for Image Recognition
Exploring Randomly Wired Neural Networks for Image RecognitionExploring Randomly Wired Neural Networks for Image Recognition
Exploring Randomly Wired Neural Networks for Image Recognition
Yongsu Baek
 
PR-317: MLP-Mixer: An all-MLP Architecture for Vision
PR-317: MLP-Mixer: An all-MLP Architecture for VisionPR-317: MLP-Mixer: An all-MLP Architecture for Vision
PR-317: MLP-Mixer: An all-MLP Architecture for Vision
Jinwon Lee
 
Machine Learning - Introduction to Convolutional Neural Networks
Machine Learning - Introduction to Convolutional Neural NetworksMachine Learning - Introduction to Convolutional Neural Networks
Machine Learning - Introduction to Convolutional Neural Networks
Andrew Ferlitsch
 
End-to-End Object Detection with Transformers
End-to-End Object Detection with TransformersEnd-to-End Object Detection with Transformers
End-to-End Object Detection with Transformers
Seunghyun Hwang
 
Machine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural NetworkMachine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural Network
Richard Kuo
 
PR-231: A Simple Framework for Contrastive Learning of Visual Representations
PR-231: A Simple Framework for Contrastive Learning of Visual RepresentationsPR-231: A Simple Framework for Contrastive Learning of Visual Representations
PR-231: A Simple Framework for Contrastive Learning of Visual Representations
Jinwon Lee
 
Neural networks
Neural networksNeural networks
Neural networks
HarshitGupta367
 
Overview of Convolutional Neural Networks
Overview of Convolutional Neural NetworksOverview of Convolutional Neural Networks
Overview of Convolutional Neural Networks
ananth
 
PR-169: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
PR-169: EfficientNet: Rethinking Model Scaling for Convolutional Neural NetworksPR-169: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
PR-169: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Jinwon Lee
 
Convolutional Neural Network and Its Applications
Convolutional Neural Network and Its ApplicationsConvolutional Neural Network and Its Applications
Convolutional Neural Network and Its Applications
Kasun Chinthaka Piyarathna
 
Convolutional neural network
Convolutional neural networkConvolutional neural network
Convolutional neural network
Itachi SK
 
Learning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for GraphsLearning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for Graphs
Mathias Niepert
 
PR243: Designing Network Design Spaces
PR243: Designing Network Design SpacesPR243: Designing Network Design Spaces
PR243: Designing Network Design Spaces
Jinwon Lee
 

What's hot (20)

Introduction to CNN
Introduction to CNNIntroduction to CNN
Introduction to CNN
 
PR-217: EfficientDet: Scalable and Efficient Object Detection
PR-217: EfficientDet: Scalable and Efficient Object DetectionPR-217: EfficientDet: Scalable and Efficient Object Detection
PR-217: EfficientDet: Scalable and Efficient Object Detection
 
PR-270: PP-YOLO: An Effective and Efficient Implementation of Object Detector
PR-270: PP-YOLO: An Effective and Efficient Implementation of Object DetectorPR-270: PP-YOLO: An Effective and Efficient Implementation of Object Detector
PR-270: PP-YOLO: An Effective and Efficient Implementation of Object Detector
 
Introduction to Convolutional Neural Networks
Introduction to Convolutional Neural NetworksIntroduction to Convolutional Neural Networks
Introduction to Convolutional Neural Networks
 
Deep learning
Deep learningDeep learning
Deep learning
 
ShuffleNet - PR054
ShuffleNet - PR054ShuffleNet - PR054
ShuffleNet - PR054
 
Rethinking Attention with Performers
Rethinking Attention with PerformersRethinking Attention with Performers
Rethinking Attention with Performers
 
Exploring Randomly Wired Neural Networks for Image Recognition
Exploring Randomly Wired Neural Networks for Image RecognitionExploring Randomly Wired Neural Networks for Image Recognition
Exploring Randomly Wired Neural Networks for Image Recognition
 
PR-317: MLP-Mixer: An all-MLP Architecture for Vision
PR-317: MLP-Mixer: An all-MLP Architecture for VisionPR-317: MLP-Mixer: An all-MLP Architecture for Vision
PR-317: MLP-Mixer: An all-MLP Architecture for Vision
 
Machine Learning - Introduction to Convolutional Neural Networks
Machine Learning - Introduction to Convolutional Neural NetworksMachine Learning - Introduction to Convolutional Neural Networks
Machine Learning - Introduction to Convolutional Neural Networks
 
End-to-End Object Detection with Transformers
End-to-End Object Detection with TransformersEnd-to-End Object Detection with Transformers
End-to-End Object Detection with Transformers
 
Machine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural NetworkMachine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural Network
 
PR-231: A Simple Framework for Contrastive Learning of Visual Representations
PR-231: A Simple Framework for Contrastive Learning of Visual RepresentationsPR-231: A Simple Framework for Contrastive Learning of Visual Representations
PR-231: A Simple Framework for Contrastive Learning of Visual Representations
 
Neural networks
Neural networksNeural networks
Neural networks
 
Overview of Convolutional Neural Networks
Overview of Convolutional Neural NetworksOverview of Convolutional Neural Networks
Overview of Convolutional Neural Networks
 
PR-169: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
PR-169: EfficientNet: Rethinking Model Scaling for Convolutional Neural NetworksPR-169: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
PR-169: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
 
Convolutional Neural Network and Its Applications
Convolutional Neural Network and Its ApplicationsConvolutional Neural Network and Its Applications
Convolutional Neural Network and Its Applications
 
Convolutional neural network
Convolutional neural networkConvolutional neural network
Convolutional neural network
 
Learning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for GraphsLearning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for Graphs
 
PR243: Designing Network Design Spaces
PR243: Designing Network Design SpacesPR243: Designing Network Design Spaces
PR243: Designing Network Design Spaces
 

Viewers also liked

Face Recognition using C#
Face Recognition using C#Face Recognition using C#
Face Recognition using C#
Luigi Oliveto
 
What goes on during haar cascade face detection
What goes on during haar cascade face detectionWhat goes on during haar cascade face detection
What goes on during haar cascade face detection
Onibiyo Joshua Toluse
 
Dissertation final report
Dissertation final reportDissertation final report
Dissertation final reportSmriti Tikoo
 
Open cv nesne tespiti haar cascade sınıflandırıcısı
Open cv nesne tespiti haar cascade sınıflandırıcısıOpen cv nesne tespiti haar cascade sınıflandırıcısı
Open cv nesne tespiti haar cascade sınıflandırıcısı
MeSutPikin
 
Face Recognition with OpenCV and scikit-learn
Face Recognition with OpenCV and scikit-learnFace Recognition with OpenCV and scikit-learn
Face Recognition with OpenCV and scikit-learn
Shiqiao Du
 
Face Detection
Face DetectionFace Detection
Face Detection
Amr Sheta
 
Face Recognition using OpenCV
Face Recognition using OpenCVFace Recognition using OpenCV
Face Recognition using OpenCV
Vasile Chelban
 
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
 
Object detection
Object detectionObject detection
Object detection
Somesh Vyas
 
FACE RECOGNITION TECHNOLOGY
FACE RECOGNITION TECHNOLOGYFACE RECOGNITION TECHNOLOGY
FACE RECOGNITION TECHNOLOGY
JASHU JASWANTH
 
Face recognition ppt
Face recognition pptFace recognition ppt
Face recognition pptSantosh Kumar
 

Viewers also liked (11)

Face Recognition using C#
Face Recognition using C#Face Recognition using C#
Face Recognition using C#
 
What goes on during haar cascade face detection
What goes on during haar cascade face detectionWhat goes on during haar cascade face detection
What goes on during haar cascade face detection
 
Dissertation final report
Dissertation final reportDissertation final report
Dissertation final report
 
Open cv nesne tespiti haar cascade sınıflandırıcısı
Open cv nesne tespiti haar cascade sınıflandırıcısıOpen cv nesne tespiti haar cascade sınıflandırıcısı
Open cv nesne tespiti haar cascade sınıflandırıcısı
 
Face Recognition with OpenCV and scikit-learn
Face Recognition with OpenCV and scikit-learnFace Recognition with OpenCV and scikit-learn
Face Recognition with OpenCV and scikit-learn
 
Face Detection
Face DetectionFace Detection
Face Detection
 
Face Recognition using OpenCV
Face Recognition using OpenCVFace Recognition using OpenCV
Face Recognition using OpenCV
 
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
 
FACE RECOGNITION TECHNOLOGY
FACE RECOGNITION TECHNOLOGYFACE RECOGNITION TECHNOLOGY
FACE RECOGNITION TECHNOLOGY
 
Face recognition ppt
Face recognition pptFace recognition ppt
Face recognition ppt
 

Similar to Wits presentation 6_28072015

intro-to-cnn-April_2020.pptx
intro-to-cnn-April_2020.pptxintro-to-cnn-April_2020.pptx
intro-to-cnn-April_2020.pptx
ssuser3aa461
 
Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)
DonghyunKang12
 
Computer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonComputer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathon
Aditya Bhattacharya
 
A Survey of Convolutional Neural Networks
A Survey of Convolutional Neural NetworksA Survey of Convolutional Neural Networks
A Survey of Convolutional Neural Networks
Rimzim Thube
 
Deep Learning
Deep LearningDeep Learning
Deep Learning
Pierre de Lacaze
 
A Neural Network that Understands Handwriting
A Neural Network that Understands HandwritingA Neural Network that Understands Handwriting
A Neural Network that Understands Handwriting
Shivam Sawhney
 
Mnist soln
Mnist solnMnist soln
Mnist soln
DanishFaisal4
 
TensorFlow.pptx
TensorFlow.pptxTensorFlow.pptx
TensorFlow.pptx
Jayesh Patil
 
Cahall Final Intern Presentation
Cahall Final Intern PresentationCahall Final Intern Presentation
Cahall Final Intern PresentationDaniel Cahall
 
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
 
Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...
Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...
Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...
Sergey Karayev
 
Image Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyImage Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A survey
NUPUR YADAV
 
Teach a neural network to read handwriting
Teach a neural network to read handwritingTeach a neural network to read handwriting
Teach a neural network to read handwriting
Vipul Kaushal
 
Convolutional neural networks
Convolutional neural networksConvolutional neural networks
Convolutional neural networks
Mohammad Imran
 
Recurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRURecurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRU
ananth
 
Automatic Attendace using convolutional neural network Face Recognition
Automatic Attendace using convolutional neural network Face RecognitionAutomatic Attendace using convolutional neural network Face Recognition
Automatic Attendace using convolutional neural network Face Recognition
vatsal199567
 
Application of machine learning and cognitive computing in intrusion detectio...
Application of machine learning and cognitive computing in intrusion detectio...Application of machine learning and cognitive computing in intrusion detectio...
Application of machine learning and cognitive computing in intrusion detectio...
Mahdi Hosseini Moghaddam
 
PR-108: MobileNetV2: Inverted Residuals and Linear Bottlenecks
PR-108: MobileNetV2: Inverted Residuals and Linear BottlenecksPR-108: MobileNetV2: Inverted Residuals and Linear Bottlenecks
PR-108: MobileNetV2: Inverted Residuals and Linear Bottlenecks
Jinwon Lee
 
Artificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningArtificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep Learning
Sujit Pal
 

Similar to Wits presentation 6_28072015 (20)

intro-to-cnn-April_2020.pptx
intro-to-cnn-April_2020.pptxintro-to-cnn-April_2020.pptx
intro-to-cnn-April_2020.pptx
 
Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)
 
Computer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonComputer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathon
 
A Survey of Convolutional Neural Networks
A Survey of Convolutional Neural NetworksA Survey of Convolutional Neural Networks
A Survey of Convolutional Neural Networks
 
Deep Learning
Deep LearningDeep Learning
Deep Learning
 
A Neural Network that Understands Handwriting
A Neural Network that Understands HandwritingA Neural Network that Understands Handwriting
A Neural Network that Understands Handwriting
 
Mnist soln
Mnist solnMnist soln
Mnist soln
 
TensorFlow.pptx
TensorFlow.pptxTensorFlow.pptx
TensorFlow.pptx
 
Cahall Final Intern Presentation
Cahall Final Intern PresentationCahall Final Intern Presentation
Cahall Final Intern Presentation
 
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
 
Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...
Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...
Lecture 2.B: Computer Vision Applications - Full Stack Deep Learning - Spring...
 
Image Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyImage Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A survey
 
Teach a neural network to read handwriting
Teach a neural network to read handwritingTeach a neural network to read handwriting
Teach a neural network to read handwriting
 
DL.pdf
DL.pdfDL.pdf
DL.pdf
 
Convolutional neural networks
Convolutional neural networksConvolutional neural networks
Convolutional neural networks
 
Recurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRURecurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRU
 
Automatic Attendace using convolutional neural network Face Recognition
Automatic Attendace using convolutional neural network Face RecognitionAutomatic Attendace using convolutional neural network Face Recognition
Automatic Attendace using convolutional neural network Face Recognition
 
Application of machine learning and cognitive computing in intrusion detectio...
Application of machine learning and cognitive computing in intrusion detectio...Application of machine learning and cognitive computing in intrusion detectio...
Application of machine learning and cognitive computing in intrusion detectio...
 
PR-108: MobileNetV2: Inverted Residuals and Linear Bottlenecks
PR-108: MobileNetV2: Inverted Residuals and Linear BottlenecksPR-108: MobileNetV2: Inverted Residuals and Linear Bottlenecks
PR-108: MobileNetV2: Inverted Residuals and Linear Bottlenecks
 
Artificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningArtificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep Learning
 

More from Beatrice van Eden

US learning
US learningUS learning
US learning
Beatrice van Eden
 
Wits presentation 4_17062015
Wits presentation 4_17062015Wits presentation 4_17062015
Wits presentation 4_17062015Beatrice van Eden
 
Wits presentation 5_30062015
Wits presentation 5_30062015Wits presentation 5_30062015
Wits presentation 5_30062015Beatrice van Eden
 
Wits presentation 3_02062015
Wits presentation 3_02062015Wits presentation 3_02062015
Wits presentation 3_02062015Beatrice van Eden
 
Wits presentation 2_19052015
Wits presentation 2_19052015Wits presentation 2_19052015
Wits presentation 2_19052015Beatrice van Eden
 
Wits presentation 1_21042015
Wits presentation 1_21042015Wits presentation 1_21042015
Wits presentation 1_21042015
Beatrice van Eden
 
CHAMP: a Bespoke Integrated System for Mobile Manipulation
CHAMP: a Bespoke Integrated System for Mobile ManipulationCHAMP: a Bespoke Integrated System for Mobile Manipulation
CHAMP: a Bespoke Integrated System for Mobile Manipulation
Beatrice van Eden
 
Machine learning group - Practical examples
Machine learning group - Practical examplesMachine learning group - Practical examples
Machine learning group - Practical examples
Beatrice van Eden
 
Kernal methods part2
Kernal methods part2Kernal methods part2
Kernal methods part2
Beatrice van Eden
 
SANAE 50 newsletter 2011 06
SANAE 50 newsletter 2011 06 SANAE 50 newsletter 2011 06
SANAE 50 newsletter 2011 06 Beatrice van Eden
 
Sanae50 newsletter apr2011_final_300dpi
Sanae50 newsletter apr2011_final_300dpiSanae50 newsletter apr2011_final_300dpi
Sanae50 newsletter apr2011_final_300dpiBeatrice van Eden
 
Sanae50 newsletter march2011_draft2_300dpi
Sanae50 newsletter march2011_draft2_300dpiSanae50 newsletter march2011_draft2_300dpi
Sanae50 newsletter march2011_draft2_300dpiBeatrice van Eden
 

More from Beatrice van Eden (19)

US learning
US learningUS learning
US learning
 
Wits presentation 4_17062015
Wits presentation 4_17062015Wits presentation 4_17062015
Wits presentation 4_17062015
 
Wits presentation 5_30062015
Wits presentation 5_30062015Wits presentation 5_30062015
Wits presentation 5_30062015
 
Wits presentation 3_02062015
Wits presentation 3_02062015Wits presentation 3_02062015
Wits presentation 3_02062015
 
Wits presentation 2_19052015
Wits presentation 2_19052015Wits presentation 2_19052015
Wits presentation 2_19052015
 
Wits presentation 1_21042015
Wits presentation 1_21042015Wits presentation 1_21042015
Wits presentation 1_21042015
 
CHAMP: a Bespoke Integrated System for Mobile Manipulation
CHAMP: a Bespoke Integrated System for Mobile ManipulationCHAMP: a Bespoke Integrated System for Mobile Manipulation
CHAMP: a Bespoke Integrated System for Mobile Manipulation
 
Machine learning group - Practical examples
Machine learning group - Practical examplesMachine learning group - Practical examples
Machine learning group - Practical examples
 
Kernal methods part2
Kernal methods part2Kernal methods part2
Kernal methods part2
 
Probability distributionv1
Probability distributionv1Probability distributionv1
Probability distributionv1
 
SANAE 50 newsletter 2011 06
SANAE 50 newsletter 2011 06 SANAE 50 newsletter 2011 06
SANAE 50 newsletter 2011 06
 
Sanae 50 may newsletter
Sanae 50 may newsletterSanae 50 may newsletter
Sanae 50 may newsletter
 
Some more greetings
Some more greetingsSome more greetings
Some more greetings
 
Photo midwinter 2011
Photo midwinter 2011Photo midwinter 2011
Photo midwinter 2011
 
Mid winter artigas uruguay
Mid winter artigas uruguayMid winter artigas uruguay
Mid winter artigas uruguay
 
Mid winter final
Mid winter finalMid winter final
Mid winter final
 
Sanae50 newsletter apr2011_final_300dpi
Sanae50 newsletter apr2011_final_300dpiSanae50 newsletter apr2011_final_300dpi
Sanae50 newsletter apr2011_final_300dpi
 
Sanae50 newsletter march2011_draft2_300dpi
Sanae50 newsletter march2011_draft2_300dpiSanae50 newsletter march2011_draft2_300dpi
Sanae50 newsletter march2011_draft2_300dpi
 
Sanae50 newsletter feb2011
Sanae50 newsletter feb2011Sanae50 newsletter feb2011
Sanae50 newsletter feb2011
 

Recently uploaded

Students, digital devices and success - Andreas Schleicher - 27 May 2024..pptx
Students, digital devices and success - Andreas Schleicher - 27 May 2024..pptxStudents, digital devices and success - Andreas Schleicher - 27 May 2024..pptx
Students, digital devices and success - Andreas Schleicher - 27 May 2024..pptx
EduSkills OECD
 
How libraries can support authors with open access requirements for UKRI fund...
How libraries can support authors with open access requirements for UKRI fund...How libraries can support authors with open access requirements for UKRI fund...
How libraries can support authors with open access requirements for UKRI fund...
Jisc
 
Template Jadual Bertugas Kelas (Boleh Edit)
Template Jadual Bertugas Kelas (Boleh Edit)Template Jadual Bertugas Kelas (Boleh Edit)
Template Jadual Bertugas Kelas (Boleh Edit)
rosedainty
 
Fish and Chips - have they had their chips
Fish and Chips - have they had their chipsFish and Chips - have they had their chips
Fish and Chips - have they had their chips
GeoBlogs
 
GIÁO ÁN DẠY THÊM (KẾ HOẠCH BÀI BUỔI 2) - TIẾNG ANH 8 GLOBAL SUCCESS (2 CỘT) N...
GIÁO ÁN DẠY THÊM (KẾ HOẠCH BÀI BUỔI 2) - TIẾNG ANH 8 GLOBAL SUCCESS (2 CỘT) N...GIÁO ÁN DẠY THÊM (KẾ HOẠCH BÀI BUỔI 2) - TIẾNG ANH 8 GLOBAL SUCCESS (2 CỘT) N...
GIÁO ÁN DẠY THÊM (KẾ HOẠCH BÀI BUỔI 2) - TIẾNG ANH 8 GLOBAL SUCCESS (2 CỘT) N...
Nguyen Thanh Tu Collection
 
special B.ed 2nd year old paper_20240531.pdf
special B.ed 2nd year old paper_20240531.pdfspecial B.ed 2nd year old paper_20240531.pdf
special B.ed 2nd year old paper_20240531.pdf
Special education needs
 
Polish students' mobility in the Czech Republic
Polish students' mobility in the Czech RepublicPolish students' mobility in the Czech Republic
Polish students' mobility in the Czech Republic
Anna Sz.
 
Synthetic Fiber Construction in lab .pptx
Synthetic Fiber Construction in lab .pptxSynthetic Fiber Construction in lab .pptx
Synthetic Fiber Construction in lab .pptx
Pavel ( NSTU)
 
Ethnobotany and Ethnopharmacology ......
Ethnobotany and Ethnopharmacology ......Ethnobotany and Ethnopharmacology ......
Ethnobotany and Ethnopharmacology ......
Ashokrao Mane college of Pharmacy Peth-Vadgaon
 
Additional Benefits for Employee Website.pdf
Additional Benefits for Employee Website.pdfAdditional Benefits for Employee Website.pdf
Additional Benefits for Employee Website.pdf
joachimlavalley1
 
Supporting (UKRI) OA monographs at Salford.pptx
Supporting (UKRI) OA monographs at Salford.pptxSupporting (UKRI) OA monographs at Salford.pptx
Supporting (UKRI) OA monographs at Salford.pptx
Jisc
 
Language Across the Curriculm LAC B.Ed.
Language Across the  Curriculm LAC B.Ed.Language Across the  Curriculm LAC B.Ed.
Language Across the Curriculm LAC B.Ed.
Atul Kumar Singh
 
Unit 2- Research Aptitude (UGC NET Paper I).pdf
Unit 2- Research Aptitude (UGC NET Paper I).pdfUnit 2- Research Aptitude (UGC NET Paper I).pdf
Unit 2- Research Aptitude (UGC NET Paper I).pdf
Thiyagu K
 
Welcome to TechSoup New Member Orientation and Q&A (May 2024).pdf
Welcome to TechSoup   New Member Orientation and Q&A (May 2024).pdfWelcome to TechSoup   New Member Orientation and Q&A (May 2024).pdf
Welcome to TechSoup New Member Orientation and Q&A (May 2024).pdf
TechSoup
 
The Roman Empire A Historical Colossus.pdf
The Roman Empire A Historical Colossus.pdfThe Roman Empire A Historical Colossus.pdf
The Roman Empire A Historical Colossus.pdf
kaushalkr1407
 
CLASS 11 CBSE B.St Project AIDS TO TRADE - INSURANCE
CLASS 11 CBSE B.St Project AIDS TO TRADE - INSURANCECLASS 11 CBSE B.St Project AIDS TO TRADE - INSURANCE
CLASS 11 CBSE B.St Project AIDS TO TRADE - INSURANCE
BhavyaRajput3
 
Mule 4.6 & Java 17 Upgrade | MuleSoft Mysore Meetup #46
Mule 4.6 & Java 17 Upgrade | MuleSoft Mysore Meetup #46Mule 4.6 & Java 17 Upgrade | MuleSoft Mysore Meetup #46
Mule 4.6 & Java 17 Upgrade | MuleSoft Mysore Meetup #46
MysoreMuleSoftMeetup
 
ESC Beyond Borders _From EU to You_ InfoPack general.pdf
ESC Beyond Borders _From EU to You_ InfoPack general.pdfESC Beyond Borders _From EU to You_ InfoPack general.pdf
ESC Beyond Borders _From EU to You_ InfoPack general.pdf
Fundacja Rozwoju Społeczeństwa Przedsiębiorczego
 
Thesis Statement for students diagnonsed withADHD.ppt
Thesis Statement for students diagnonsed withADHD.pptThesis Statement for students diagnonsed withADHD.ppt
Thesis Statement for students diagnonsed withADHD.ppt
EverAndrsGuerraGuerr
 
Introduction to Quality Improvement Essentials
Introduction to Quality Improvement EssentialsIntroduction to Quality Improvement Essentials
Introduction to Quality Improvement Essentials
Excellence Foundation for South Sudan
 

Recently uploaded (20)

Students, digital devices and success - Andreas Schleicher - 27 May 2024..pptx
Students, digital devices and success - Andreas Schleicher - 27 May 2024..pptxStudents, digital devices and success - Andreas Schleicher - 27 May 2024..pptx
Students, digital devices and success - Andreas Schleicher - 27 May 2024..pptx
 
How libraries can support authors with open access requirements for UKRI fund...
How libraries can support authors with open access requirements for UKRI fund...How libraries can support authors with open access requirements for UKRI fund...
How libraries can support authors with open access requirements for UKRI fund...
 
Template Jadual Bertugas Kelas (Boleh Edit)
Template Jadual Bertugas Kelas (Boleh Edit)Template Jadual Bertugas Kelas (Boleh Edit)
Template Jadual Bertugas Kelas (Boleh Edit)
 
Fish and Chips - have they had their chips
Fish and Chips - have they had their chipsFish and Chips - have they had their chips
Fish and Chips - have they had their chips
 
GIÁO ÁN DẠY THÊM (KẾ HOẠCH BÀI BUỔI 2) - TIẾNG ANH 8 GLOBAL SUCCESS (2 CỘT) N...
GIÁO ÁN DẠY THÊM (KẾ HOẠCH BÀI BUỔI 2) - TIẾNG ANH 8 GLOBAL SUCCESS (2 CỘT) N...GIÁO ÁN DẠY THÊM (KẾ HOẠCH BÀI BUỔI 2) - TIẾNG ANH 8 GLOBAL SUCCESS (2 CỘT) N...
GIÁO ÁN DẠY THÊM (KẾ HOẠCH BÀI BUỔI 2) - TIẾNG ANH 8 GLOBAL SUCCESS (2 CỘT) N...
 
special B.ed 2nd year old paper_20240531.pdf
special B.ed 2nd year old paper_20240531.pdfspecial B.ed 2nd year old paper_20240531.pdf
special B.ed 2nd year old paper_20240531.pdf
 
Polish students' mobility in the Czech Republic
Polish students' mobility in the Czech RepublicPolish students' mobility in the Czech Republic
Polish students' mobility in the Czech Republic
 
Synthetic Fiber Construction in lab .pptx
Synthetic Fiber Construction in lab .pptxSynthetic Fiber Construction in lab .pptx
Synthetic Fiber Construction in lab .pptx
 
Ethnobotany and Ethnopharmacology ......
Ethnobotany and Ethnopharmacology ......Ethnobotany and Ethnopharmacology ......
Ethnobotany and Ethnopharmacology ......
 
Additional Benefits for Employee Website.pdf
Additional Benefits for Employee Website.pdfAdditional Benefits for Employee Website.pdf
Additional Benefits for Employee Website.pdf
 
Supporting (UKRI) OA monographs at Salford.pptx
Supporting (UKRI) OA monographs at Salford.pptxSupporting (UKRI) OA monographs at Salford.pptx
Supporting (UKRI) OA monographs at Salford.pptx
 
Language Across the Curriculm LAC B.Ed.
Language Across the  Curriculm LAC B.Ed.Language Across the  Curriculm LAC B.Ed.
Language Across the Curriculm LAC B.Ed.
 
Unit 2- Research Aptitude (UGC NET Paper I).pdf
Unit 2- Research Aptitude (UGC NET Paper I).pdfUnit 2- Research Aptitude (UGC NET Paper I).pdf
Unit 2- Research Aptitude (UGC NET Paper I).pdf
 
Welcome to TechSoup New Member Orientation and Q&A (May 2024).pdf
Welcome to TechSoup   New Member Orientation and Q&A (May 2024).pdfWelcome to TechSoup   New Member Orientation and Q&A (May 2024).pdf
Welcome to TechSoup New Member Orientation and Q&A (May 2024).pdf
 
The Roman Empire A Historical Colossus.pdf
The Roman Empire A Historical Colossus.pdfThe Roman Empire A Historical Colossus.pdf
The Roman Empire A Historical Colossus.pdf
 
CLASS 11 CBSE B.St Project AIDS TO TRADE - INSURANCE
CLASS 11 CBSE B.St Project AIDS TO TRADE - INSURANCECLASS 11 CBSE B.St Project AIDS TO TRADE - INSURANCE
CLASS 11 CBSE B.St Project AIDS TO TRADE - INSURANCE
 
Mule 4.6 & Java 17 Upgrade | MuleSoft Mysore Meetup #46
Mule 4.6 & Java 17 Upgrade | MuleSoft Mysore Meetup #46Mule 4.6 & Java 17 Upgrade | MuleSoft Mysore Meetup #46
Mule 4.6 & Java 17 Upgrade | MuleSoft Mysore Meetup #46
 
ESC Beyond Borders _From EU to You_ InfoPack general.pdf
ESC Beyond Borders _From EU to You_ InfoPack general.pdfESC Beyond Borders _From EU to You_ InfoPack general.pdf
ESC Beyond Borders _From EU to You_ InfoPack general.pdf
 
Thesis Statement for students diagnonsed withADHD.ppt
Thesis Statement for students diagnonsed withADHD.pptThesis Statement for students diagnonsed withADHD.ppt
Thesis Statement for students diagnonsed withADHD.ppt
 
Introduction to Quality Improvement Essentials
Introduction to Quality Improvement EssentialsIntroduction to Quality Improvement Essentials
Introduction to Quality Improvement Essentials
 

Wits presentation 6_28072015

  • 1. Object Recognition Tutorial Beatrice van Eden - Part time PhD Student at the University of the Witwatersrand. - Fulltime employee of the Council for Scientific and Industrial Research.
  • 2. Research Problem • Hierarchical concept formation • This research will allow a robot to learn about its environment autonomously • Build a concept about these environments • Even if it has not seen that specific instance previously
  • 3. Why Object Recognition • Environments are build up by different objects • RGB-D Sensor for perception • Concept formation need some base line to work from • Exposure to ML techniques • Cascading classifiers • Convolutional Neural Networks • Support Vector Machine
  • 4. Index: Cascading Classifiers • Cascading classifiers • Haar-like features • Local binary patterns • Implementation • Results
  • 5. Cascading classifiers • Cascading is a particular case of ensemble learning based on the concatenation of several classifiers, using all information collected from the output from a given classifier as additional information for the next classifier in the cascade.
  • 6. Haar-like features • The difference of the sum of pixels of areas inside the rectangle • The values indicate certain characteristics of a particular area of the image.
  • 7. Haar-like features • The Viola-Jones detector is a strong, binary classifier build of several weak detectors • Does a certain sub-region of the original image contain an instance of the object of interest or not
  • 8. Local binary patterns • Divide the examined window into cells (e.g. 16x16 pixels for each cell). • For each pixel in a cell, compare the pixel to each of its 8 neighbours (on its left-top, left-middle, left-bottom, right-top, etc.). Follow the pixels along a circle, i.e. clockwise or counter- clockwise. • Where the centre pixel's value is greater than the neighbour's value, write "1". Otherwise, write "0". This gives an 8-digit binary number. • Compute the histogram, over the cell, of the frequency of each "number" occurring. • Optionally normalize the histogram. • Concatenate (normalized) histograms of all cells. This gives the feature vector for the window.
  • 9. Local binary patterns • a Powerful feature for texture classification • LBP is faster but less accurate than Haar. • LBP does all the calculations in integers. Haar uses floats. • LBP few hours of training Haar few days
  • 10. Implementation • SAMPLES - How many images do we need? • Depend on a variety of factors, including the quality of the images, the object you want to recognize, the method to generate the samples, the CPU power you have and probably some magic. • Positive images 50 -> 1500, list in .txt file. • Negative images 1500, list in .txt file.
  • 11. Implementation • Create samples with OpenCV, generates a large number of positive samples from our positive images, by applying transformations and distortions. Used a Perl script to combine positive image with negative image • *.vec file are created, merge them into one • opencv_haartraining and opencv_traincascade. opencv_traincascade supports both Haar [Viola2001] and LBP [Liao2007] (Local Binary Patterns) features.
  • 13. Implementation • http://coding-robin.de/2013/07/22/train-your-own-opencv- haar-classifier.html • Video LBP – Coke Can • Video Haar – Coke Can • Video LBP – Face recognition • Choose amount of stages to train
  • 14. Results • To be generated – working on confusion matrix •
  • 15. Index: CNN • Convolutional Neural Networks • Example • Overview and Intuition • Implementation • Results
  • 16. Convolutional Neural Networks • Neural network vs. Convolutional neural network • Layers used to build ConvNets • Convolutional Layer, Pooling Layer, and Fully-Connected Layer (exactly as seen in regular Neural Networks).
  • 17. Example • Input: • Image: width 32, height 32, three colour channels. • CONV layer: • Local filter over previous layer • Dot product between weights and sliding region in the input volume. [32x32x12] • RELU layer: • Apply an elementwise activation function, such as the max(0,x) thresholding at zero. This leaves the size of the volume unchanged. • POOL layer: • Down sampling operation along the spatial dimensions (width, height). [16x16x12] • FC layer: • Compute the class scores. As with ordinary Neural Networks each neuron in this layer will be connected to all the numbers in the previous volume.
  • 18. Convolutional Neural Networks • CNN is a type of feed-forward artificial neural network where the individual neurons are tiled in such a way that they respond to overlapping regions in the visual field.
  • 19. Overview and Intuition • CONV layer's parameters consist of a set of learnable filters • Every filter is small spatially (along width and height), but extends through the full depth of the input volume • As we slide the filter, across the input, we are computing the dot product between the entries of the filter and the input • Intuitively, the network will learn filters that activate when they see some specific type of feature at some spatial position in the input • Stacking these activation maps for all filters along the depth dimension forms the full output volume
  • 20. Convolutional Neural Networks • Three hyperparameters control the size of the output volume: the depth, stride and zero-padding • Depth of the output volume is a hyperparameter that we can pick. It controls the number of neurons in the Conv layer that connect to the same region of the input volume. • We specify the stride with which we allocate depth columns around the spatial dimensions (width and height). • Zero padding allow us to control the spatial size of the output volumes. Example filters learned
  • 21. Implementation http://danielnouri.org/notes/2014/12/17/using-convolutional-neural-nets-to-detect-facial-keypoints-tutorial/#the-data • Lasagne, a library for building neural networks with Python and Theano. • CPU vs. CUDA-capable GPU • Ran the MNIST example (Recognise 0-9 digits). • Facial key point • Data available as *.csv files. Load training and test data. • Video CNN – Coke Can • Video CNN – Coke Can The predictions of net1 on the left compared to the predictions of net2.
  • 22. Results • To be generated – working on confusion matrix •
  • 23. Index: SVM • Support Vector Machine • Histogram of Oriented Gradients • Implementation • Results
  • 24. Support Vector Machine • Given a set of training examples, each marked for belonging to one of two categories, an SVM training algorithm builds a model that assigns new examples into one category or the other.
  • 25. What is the goal of the Support Vector Machine (SVM)? • The goal of a support vector machine is to find the optimal separating hyperplane which maximizes the margin of the training data.
  • 26. Histogram of Oriented Gradients • The technique counts occurrences of gradient orientation in localized portions of an image • The descriptor is made up of M*N cells covering the image window in a grid. • Each cell is represented by a histogram of edge orientations, where the number of discretized edge orientations is a parameter (usually 9). • The cell histogram is visualized by a 'star' showing the strength of the edge orientations in the histogram: the stronger a specific orientation, the longer it is relative to the others.
  • 27. • Note that there are various normalization schemes: • Local schemes, in which the cell in normalized with respect to neighboring cells only [Dalal-Triggs] • Global schemes, in which the orientation length is normalized by all the cells • Also note that some authors use multiple local normalizations per cell Histogram of Oriented Gradients The example below shows a model of a bike (from Felzenszwalb et al.) with HoG consisting of 7*11 cells, each with 8 orientations
  • 28. • (a) Test image • (b) Gradient image of the test image • (c) Orientation and magnitude of Gradient in each cell • (d) HoG of cells • (e) Average gradient image over the training example • (f) Weights of positive SVM in the block • (g) HoG descriptor weighted by the positive SVM weights Histogram of Oriented Gradients
  • 31. Results • To be generated – working on confusion matrix
  • 32. Conclusion • Cascading classifiers • Convolutional Neural Networks • Support Vector Machine