SlideShare a Scribd company logo
1 of 37
Deep Learning
Presented By:
Srishty Saha
IIIT-DELHI
Shallow Learning
• SVM
• Linear & Kernel Regression
• Hidden Markov Models (HMM)
• Gaussian Mixture Models (GMM)
• Single hidden layer MLP
Limitations
Cannot make use of unlabeled data
Supervised vs Unsupervised Learning
• Supervised Learning
1.Output has to be produced according to target vector.
2.Input + Target vector = Training Pair
3.Labelled Data
• Unsupervised Learning ( self Organising)
1.Network receives input patterns to form clusters.
2.When a new input pattern is applied , output gives the class the input pattern
belongs to
3.Unlabelled Data
Neural Networks
• Machine Learning
• Knowledge from high dimensional data
• Classification
• Input: features of data
• supervised vs unsupervised
• labeled data
• Neurons
What is it used for?
• Classification
• Regression
---- Prediction
---- Fitting Curve
Multi Layer Perceptron
• Multiple Layers
• Feed Forward
• Connected Weights
• 1-of-N Output
hidden
output
Back Propagation
• Minimize error of
calculated output
• Adjust weights
• Gradient Descent
• Procedure
• Forward Phase
• Backpropagation
of errors
• For each sample,
multiple epochs
Problems with Backpropagation
• Multiple hidden Layers
• Get stuck in local optima
• start weights from random positions
• Only use labeled data
• most data is unlabeled
Deep Learning Means Feature Learning
• Deep Learning is about Learning Hierarchical Features.
Convolutional Neural Network
Feature extraction layer
Convolution layer
Shift and distortion invariance or
Subsampling layer
CNN contd.
• Detect the same feature at different positions in the
input image in C Layer.
features
CNN Contd.
Shared weights: all neurons in a feature share the
same weights (but not the biases).
In this way all neurons detect the same feature at
different positions in the input image.
Reduce the number of free parameters.
If a neuron in the feature map fires, this corresponds to a match with
the template
CNN Contd.
S Layer
The subsampling layers reduce the spatial resolution of each feature
map
By reducing the spatial resolution of the feature map, a certain degree
of shift and distortion invariance is achieved
Contd. S layer
The weight sharing is also applied in subsampling layers
Reduce the effect of noises and shift or distortion.
Applications
Speech Recognition.
Object Detection ( Computer Vision).
Web search – Text Analysis.
Few Insights Gathered From Papers.
• Used CBIR method to do feature extractions in Convolutional Layer.
• Applied filters to feature extraction.
• Used Definite size of patch to work upon.
• CNN method was used throughout.
• 3D convolution – time added as third factor .
• Feature Extraction so far observed was:
1. Gradient Filter in X and Y directions.
Object Detection
Architecture:
Dataset : MIT Face dataset 1104 faces.
Training – 200 images.
Test - 200 images.
The Convolutional Neural Network consists of two parts
1) the convolution layers and max-pooling layers
2) the fully connection layers and the output layers.
The Input Layer consists of 72x72 size histogram equalized images an
output is the set of different face images each of size 18x18.
The networks used for face detection and face recognition contains two
convolutional layer and two sub-sampling layer.
Output Layer
72 x 72 72x72 :5no 36x36: 5no
36X36
18 x 18:
12no
Output Layer
20 faces
Feature Maps :5no Feature Maps :5no
Input Layer Conv Layer-1
Kernels of 3x3
Conv Layer-2Samp Layer-1 Samp Layer-2
Convolutional Layer
Total of 5 kernels of size 3x3 is used to convolutional operation.
5 different feature maps :
• gray
• gradient –x
• gradient-y
• last two kernels gives the information below the eyes area.
Sampling Layer
• Mean filter of 2x2 is applied on image
• Alternate rows and alternate columns of image is sampled out.
72 x 72 72x72 :5no 36x36: 5no
36X36
18 x 18:
12no
Fully
connected
layer20 faces
Feature Maps :5no Feature Maps :5no
Input Layer Conv Layer-1
Kernels of 3x3
Conv Layer-2Samp Layer-1 Samp Layer-2
Fully Connected And Output Layer
• Output layer : 70 images.
72 x 72 72x72 :5no 36x36: 5no
36X36
18 x 18:
12no
Fully
connected
layer20 faces
Feature Maps :5no Feature Maps :5no
Input Layer Conv Layer-1
Kernels of 3x3
Conv Layer-2Samp Layer-1 Samp Layer-2
Error Propagation.
• Error Matrix e is obtained by finding difference between values of
neurons in output layer and fully connected layer.
• As there are 5 kernels in convolutional layers so each face will have 5
different feature maps. So in fully connected layer of Object
Recognition CNN,total neurons are 18 X 18 X 5(feature maps).
• So, Mean error M(i=1:5) of each Map is calculated.
• EM is Mean of M(i=1:5) is calculated.
• Error {M( i=1 :5) } is used for back-propagation.
• {EM} is used as a threshold such that any value below the threshold
is considered success or face match.
Implementation
1) Input of 200 images each of size 72X72 is presented to network one
by one for training.
2) In First Layer, Convolutional operation is performed using
aforementioned kernels of size 3X3 .The resultant output is of size
7 2 X 72 X 5.
3) In first S Layer, Sampling of image using mean filter of size 2X2
and sampling alternate rows and columns.The output of this of size
36 X 36 X 5.
4) In Second C layer,after convolution operation we get output
of size 36 X 36 X 5 .
5) In Second S layer, after sampling operation we get image of size
200 X 18 X 18 X 5.
6) The Fully connected layer is obtained after S layer and it is of
size 18 X 18 X 5 and each of neuron is connected to output layer.
7) Error Propagated using above method mentioned in
Back Propagation section of Object Recognition.
8) Error propagation takes place for fixed number of epochs in during
trainning.
9) For testing, {EM} obtained in equation is used as threshold to find face
match.
Results – Error vs Epochs
Results – Accuracy vs epochs
Object Detection.
• Input – Face images of size 72 x 72
Non Face images of size 72 x 72
• Output – 1 or 0
Error Propagation
• Error Matrix e is obtained by finding difference between values of
neurons in output layer and fully connected layer.
• Error of each neuron is propagated backwards and thus weight up-
dation is done.
• The backpropagation comes to hault when error <0.0003 or number
of epochs is 64 for training.
Object Detection ( Face/Non face)
1) Input of 50 (30 faces +20 non face) images each of size 72X72 is
presented to network one by one for training.
2) In First Layer, Convolutional operation is performed using
aforementioned kernels of size 3X3 .The resultant output is of size
7 2 X 72 X 5.
3) In first S Layer, Sampling of image using mean filter of size 2X2
and sampling alternate rows and columns.The output of this of size
36 X 36 X 5.
4) In Second C layer,after convolution operation we get output
of size 36 X 36 X 5 .
5) In Second S layer, after sampling operation we get image of size
18 X 18 X 5.
6) The Fully connected layer is obtained after S layer and it is of
size 18 X 18 X 5 and each of neuron is connected to output layer.
7) Error Propagated using above method mentioned in
Back Propagation section of Object Recognition.
8) Error propagation takes place for fixed number of epochs in during
trainning.
9) For testing, 200 images were used 125 faces and 75 non face.
Result:
Confusion Matrix Face Non face
Face (test) 100 25
Non Face (test) 32 43
Accuracy : 80% approx. for faces.
Accuracy : 57.33 % approx. for non faces.
Time to detect a face : 25.35 secs approx.
Object Recognition in an image.
Implementation iterative search
1) Input is an image is presented to network .
2) 72 X 72 patch is created and presented to network.
3) In First Layer, Convolutional operation is performed using
aforementioned kernels of size 3X3 .The resultant output is of size
7 2 X 72 X 5.
4) In first S Layer, Sampling of image using mean filter of size 2X2
and sampling alternate rows and columns.The output of this of size
36 X 36 X 5.
4) In Second C layer,after convolution operation we get output
of size 36 X 36 X 5 .
5) In Second S layer, after sampling operation we get image of size
200 X 18 X 18 X 5.
6) The Fully connected layer is obtained after S layer and it is of
size 18 X 18 X 5 and each of neuron is connected to output layer.
7) Error Propagated using above method mentioned in
Back Propagation section of Object Recognition.
8) Error propagation takes place for fixed number of epochs in during
trainning.
9) As an image is found Count = count+1.
Results: Error vs ith iteration face found.
Result : Accuracy
To do.
• Face detection using in set of images.
• Improve the accuracy.
• Implement it for videos.

More Related Content

What's hot

Electricity price forecasting with Recurrent Neural Networks
Electricity price forecasting with Recurrent Neural NetworksElectricity price forecasting with Recurrent Neural Networks
Electricity price forecasting with Recurrent Neural NetworksTaegyun Jeon
 
ISCAS'18: A Deep Neural Network on the Nested RNS (NRNS) on an FPGA: Applied ...
ISCAS'18: A Deep Neural Network on the Nested RNS (NRNS) on an FPGA: Applied ...ISCAS'18: A Deep Neural Network on the Nested RNS (NRNS) on an FPGA: Applied ...
ISCAS'18: A Deep Neural Network on the Nested RNS (NRNS) on an FPGA: Applied ...Hiroki Nakahara
 
Deep Learning - RNN and CNN
Deep Learning - RNN and CNNDeep Learning - RNN and CNN
Deep Learning - RNN and CNNPradnya Saval
 
Optimized Network-coded Scalable Video Multicasting over eMBMS Networks
Optimized Network-coded Scalable Video Multicasting over eMBMS NetworksOptimized Network-coded Scalable Video Multicasting over eMBMS Networks
Optimized Network-coded Scalable Video Multicasting over eMBMS NetworksAndrea Tassi
 
Bio-inspired Algorithms for Evolving the Architecture of Convolutional Neural...
Bio-inspired Algorithms for Evolving the Architecture of Convolutional Neural...Bio-inspired Algorithms for Evolving the Architecture of Convolutional Neural...
Bio-inspired Algorithms for Evolving the Architecture of Convolutional Neural...Ashray Bhandare
 
Applied Deep Learning 11/03 Convolutional Neural Networks
Applied Deep Learning 11/03 Convolutional Neural NetworksApplied Deep Learning 11/03 Convolutional Neural Networks
Applied Deep Learning 11/03 Convolutional Neural NetworksMark Chang
 
ISMVL2018: A Ternary Weight Binary Input Convolutional Neural Network
ISMVL2018: A Ternary Weight Binary Input Convolutional Neural NetworkISMVL2018: A Ternary Weight Binary Input Convolutional Neural Network
ISMVL2018: A Ternary Weight Binary Input Convolutional Neural NetworkHiroki Nakahara
 
Optimizing Parallel Reduction in CUDA : NOTES
Optimizing Parallel Reduction in CUDA : NOTESOptimizing Parallel Reduction in CUDA : NOTES
Optimizing Parallel Reduction in CUDA : NOTESSubhajit Sahu
 
Batch normalization
Batch normalizationBatch normalization
Batch normalizationYuichiro Iio
 
Introduction to Neural Network
Introduction to Neural NetworkIntroduction to Neural Network
Introduction to Neural NetworkOmer Korech
 
Video Analysis with Recurrent Neural Networks (Master Computer Vision Barcelo...
Video Analysis with Recurrent Neural Networks (Master Computer Vision Barcelo...Video Analysis with Recurrent Neural Networks (Master Computer Vision Barcelo...
Video Analysis with Recurrent Neural Networks (Master Computer Vision Barcelo...Universitat Politècnica de Catalunya
 
Why Batch Normalization Works so Well
Why Batch Normalization Works so WellWhy Batch Normalization Works so Well
Why Batch Normalization Works so WellChun-Ming Chang
 
Pixel RNN to Pixel CNN++
Pixel RNN to Pixel CNN++Pixel RNN to Pixel CNN++
Pixel RNN to Pixel CNN++Dongheon Lee
 
FPL15 talk: Deep Convolutional Neural Network on FPGA
FPL15 talk: Deep Convolutional Neural Network on FPGAFPL15 talk: Deep Convolutional Neural Network on FPGA
FPL15 talk: Deep Convolutional Neural Network on FPGAHiroki Nakahara
 
ujava.org Deep Learning with Convolutional Neural Network
ujava.org Deep Learning with Convolutional Neural Network ujava.org Deep Learning with Convolutional Neural Network
ujava.org Deep Learning with Convolutional Neural Network 신동 강
 

What's hot (20)

Gh2411361141
Gh2411361141Gh2411361141
Gh2411361141
 
Electricity price forecasting with Recurrent Neural Networks
Electricity price forecasting with Recurrent Neural NetworksElectricity price forecasting with Recurrent Neural Networks
Electricity price forecasting with Recurrent Neural Networks
 
ISCAS'18: A Deep Neural Network on the Nested RNS (NRNS) on an FPGA: Applied ...
ISCAS'18: A Deep Neural Network on the Nested RNS (NRNS) on an FPGA: Applied ...ISCAS'18: A Deep Neural Network on the Nested RNS (NRNS) on an FPGA: Applied ...
ISCAS'18: A Deep Neural Network on the Nested RNS (NRNS) on an FPGA: Applied ...
 
Deep Learning - RNN and CNN
Deep Learning - RNN and CNNDeep Learning - RNN and CNN
Deep Learning - RNN and CNN
 
Optimized Network-coded Scalable Video Multicasting over eMBMS Networks
Optimized Network-coded Scalable Video Multicasting over eMBMS NetworksOptimized Network-coded Scalable Video Multicasting over eMBMS Networks
Optimized Network-coded Scalable Video Multicasting over eMBMS Networks
 
Bio-inspired Algorithms for Evolving the Architecture of Convolutional Neural...
Bio-inspired Algorithms for Evolving the Architecture of Convolutional Neural...Bio-inspired Algorithms for Evolving the Architecture of Convolutional Neural...
Bio-inspired Algorithms for Evolving the Architecture of Convolutional Neural...
 
Applied Deep Learning 11/03 Convolutional Neural Networks
Applied Deep Learning 11/03 Convolutional Neural NetworksApplied Deep Learning 11/03 Convolutional Neural Networks
Applied Deep Learning 11/03 Convolutional Neural Networks
 
nn network
nn networknn network
nn network
 
Slide tesi
Slide tesiSlide tesi
Slide tesi
 
ISMVL2018: A Ternary Weight Binary Input Convolutional Neural Network
ISMVL2018: A Ternary Weight Binary Input Convolutional Neural NetworkISMVL2018: A Ternary Weight Binary Input Convolutional Neural Network
ISMVL2018: A Ternary Weight Binary Input Convolutional Neural Network
 
Optimizing Parallel Reduction in CUDA : NOTES
Optimizing Parallel Reduction in CUDA : NOTESOptimizing Parallel Reduction in CUDA : NOTES
Optimizing Parallel Reduction in CUDA : NOTES
 
Batch normalization
Batch normalizationBatch normalization
Batch normalization
 
Introduction to Neural Network
Introduction to Neural NetworkIntroduction to Neural Network
Introduction to Neural Network
 
Video Analysis with Recurrent Neural Networks (Master Computer Vision Barcelo...
Video Analysis with Recurrent Neural Networks (Master Computer Vision Barcelo...Video Analysis with Recurrent Neural Networks (Master Computer Vision Barcelo...
Video Analysis with Recurrent Neural Networks (Master Computer Vision Barcelo...
 
Why Batch Normalization Works so Well
Why Batch Normalization Works so WellWhy Batch Normalization Works so Well
Why Batch Normalization Works so Well
 
Pixel RNN to Pixel CNN++
Pixel RNN to Pixel CNN++Pixel RNN to Pixel CNN++
Pixel RNN to Pixel CNN++
 
The Perceptron (D1L1 Insight@DCU Machine Learning Workshop 2017)
The Perceptron (D1L1 Insight@DCU Machine Learning Workshop 2017)The Perceptron (D1L1 Insight@DCU Machine Learning Workshop 2017)
The Perceptron (D1L1 Insight@DCU Machine Learning Workshop 2017)
 
FPL15 talk: Deep Convolutional Neural Network on FPGA
FPL15 talk: Deep Convolutional Neural Network on FPGAFPL15 talk: Deep Convolutional Neural Network on FPGA
FPL15 talk: Deep Convolutional Neural Network on FPGA
 
Back propagation method
Back propagation methodBack propagation method
Back propagation method
 
ujava.org Deep Learning with Convolutional Neural Network
ujava.org Deep Learning with Convolutional Neural Network ujava.org Deep Learning with Convolutional Neural Network
ujava.org Deep Learning with Convolutional Neural Network
 

Similar to Deep Learning for Image Classification and Object Detection

Designed by Identity MLP
Designed by Identity MLP Designed by Identity MLP
Designed by Identity MLP butest
 
Image Classification using deep learning
Image Classification using deep learning Image Classification using deep learning
Image Classification using deep learning Asma-AH
 
Waste Classification System using Convolutional Neural Networks.pptx
Waste Classification System using Convolutional Neural Networks.pptxWaste Classification System using Convolutional Neural Networks.pptx
Waste Classification System using Convolutional Neural Networks.pptxJohnPrasad14
 
IRJET - Hand Gesture Recognition to Perform System Operations
IRJET -  	  Hand Gesture Recognition to Perform System OperationsIRJET -  	  Hand Gesture Recognition to Perform System Operations
IRJET - Hand Gesture Recognition to Perform System OperationsIRJET Journal
 
Skin Lesion Detection from Dermoscopic Images using Convolutional Neural Netw...
Skin Lesion Detection from Dermoscopic Images using Convolutional Neural Netw...Skin Lesion Detection from Dermoscopic Images using Convolutional Neural Netw...
Skin Lesion Detection from Dermoscopic Images using Convolutional Neural Netw...Universitat Politècnica de Catalunya
 
Back propagation network
Back propagation networkBack propagation network
Back propagation networkHIRA Zaidi
 
Trackster Pruning at the CMS High-Granularity Calorimeter
Trackster Pruning at the CMS High-Granularity CalorimeterTrackster Pruning at the CMS High-Granularity Calorimeter
Trackster Pruning at the CMS High-Granularity CalorimeterYousef Fadila
 
Coin recognition using matlab
Coin recognition using matlabCoin recognition using matlab
Coin recognition using matlabslmnsvn
 
Improving face recognition by artificial neural network using principal compo...
Improving face recognition by artificial neural network using principal compo...Improving face recognition by artificial neural network using principal compo...
Improving face recognition by artificial neural network using principal compo...TELKOMNIKA JOURNAL
 
Handwritten Digit Recognition and performance of various modelsation[autosaved]
Handwritten Digit Recognition and performance of various modelsation[autosaved]Handwritten Digit Recognition and performance of various modelsation[autosaved]
Handwritten Digit Recognition and performance of various modelsation[autosaved]SubhradeepMaji
 
Dh3211231128
Dh3211231128Dh3211231128
Dh3211231128IJMER
 
SLIC Superpixel Based Self Organizing Maps Algorithm for Segmentation of Micr...
SLIC Superpixel Based Self Organizing Maps Algorithm for Segmentation of Micr...SLIC Superpixel Based Self Organizing Maps Algorithm for Segmentation of Micr...
SLIC Superpixel Based Self Organizing Maps Algorithm for Segmentation of Micr...IJAAS Team
 
phase 2 ppt.pptx
phase 2 ppt.pptxphase 2 ppt.pptx
phase 2 ppt.pptxbharatt7
 
Deep learning in Computer Vision
Deep learning in Computer VisionDeep learning in Computer Vision
Deep learning in Computer VisionDavid Dao
 

Similar to Deep Learning for Image Classification and Object Detection (20)

Neural networks
Neural networksNeural networks
Neural networks
 
Designed by Identity MLP
Designed by Identity MLP Designed by Identity MLP
Designed by Identity MLP
 
Image Classification using deep learning
Image Classification using deep learning Image Classification using deep learning
Image Classification using deep learning
 
Deep learning
Deep learningDeep learning
Deep learning
 
Waste Classification System using Convolutional Neural Networks.pptx
Waste Classification System using Convolutional Neural Networks.pptxWaste Classification System using Convolutional Neural Networks.pptx
Waste Classification System using Convolutional Neural Networks.pptx
 
IRJET - Hand Gesture Recognition to Perform System Operations
IRJET -  	  Hand Gesture Recognition to Perform System OperationsIRJET -  	  Hand Gesture Recognition to Perform System Operations
IRJET - Hand Gesture Recognition to Perform System Operations
 
lec6a.ppt
lec6a.pptlec6a.ppt
lec6a.ppt
 
Skin Lesion Detection from Dermoscopic Images using Convolutional Neural Netw...
Skin Lesion Detection from Dermoscopic Images using Convolutional Neural Netw...Skin Lesion Detection from Dermoscopic Images using Convolutional Neural Netw...
Skin Lesion Detection from Dermoscopic Images using Convolutional Neural Netw...
 
Back propagation network
Back propagation networkBack propagation network
Back propagation network
 
Trackster Pruning at the CMS High-Granularity Calorimeter
Trackster Pruning at the CMS High-Granularity CalorimeterTrackster Pruning at the CMS High-Granularity Calorimeter
Trackster Pruning at the CMS High-Granularity Calorimeter
 
Coin recognition using matlab
Coin recognition using matlabCoin recognition using matlab
Coin recognition using matlab
 
Improving face recognition by artificial neural network using principal compo...
Improving face recognition by artificial neural network using principal compo...Improving face recognition by artificial neural network using principal compo...
Improving face recognition by artificial neural network using principal compo...
 
RNN-LSTM.pptx
RNN-LSTM.pptxRNN-LSTM.pptx
RNN-LSTM.pptx
 
Handwritten Digit Recognition and performance of various modelsation[autosaved]
Handwritten Digit Recognition and performance of various modelsation[autosaved]Handwritten Digit Recognition and performance of various modelsation[autosaved]
Handwritten Digit Recognition and performance of various modelsation[autosaved]
 
Dh3211231128
Dh3211231128Dh3211231128
Dh3211231128
 
SLIC Superpixel Based Self Organizing Maps Algorithm for Segmentation of Micr...
SLIC Superpixel Based Self Organizing Maps Algorithm for Segmentation of Micr...SLIC Superpixel Based Self Organizing Maps Algorithm for Segmentation of Micr...
SLIC Superpixel Based Self Organizing Maps Algorithm for Segmentation of Micr...
 
phase 2 ppt.pptx
phase 2 ppt.pptxphase 2 ppt.pptx
phase 2 ppt.pptx
 
Deep learning in Computer Vision
Deep learning in Computer VisionDeep learning in Computer Vision
Deep learning in Computer Vision
 
28 01-2021-05
28 01-2021-0528 01-2021-05
28 01-2021-05
 
All projects
All projectsAll projects
All projects
 

Recently uploaded

Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...VICTOR MAESTRE RAMIREZ
 
An experimental study in using natural admixture as an alternative for chemic...
An experimental study in using natural admixture as an alternative for chemic...An experimental study in using natural admixture as an alternative for chemic...
An experimental study in using natural admixture as an alternative for chemic...Chandu841456
 
HARMONY IN THE NATURE AND EXISTENCE - Unit-IV
HARMONY IN THE NATURE AND EXISTENCE - Unit-IVHARMONY IN THE NATURE AND EXISTENCE - Unit-IV
HARMONY IN THE NATURE AND EXISTENCE - Unit-IVRajaP95
 
Churning of Butter, Factors affecting .
Churning of Butter, Factors affecting  .Churning of Butter, Factors affecting  .
Churning of Butter, Factors affecting .Satyam Kumar
 
Introduction to Machine Learning Unit-3 for II MECH
Introduction to Machine Learning Unit-3 for II MECHIntroduction to Machine Learning Unit-3 for II MECH
Introduction to Machine Learning Unit-3 for II MECHC Sai Kiran
 
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdf
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdfCCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdf
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdfAsst.prof M.Gokilavani
 
Artificial-Intelligence-in-Electronics (K).pptx
Artificial-Intelligence-in-Electronics (K).pptxArtificial-Intelligence-in-Electronics (K).pptx
Artificial-Intelligence-in-Electronics (K).pptxbritheesh05
 
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxDecoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxJoão Esperancinha
 
Effects of rheological properties on mixing
Effects of rheological properties on mixingEffects of rheological properties on mixing
Effects of rheological properties on mixingviprabot1
 
pipeline in computer architecture design
pipeline in computer architecture  designpipeline in computer architecture  design
pipeline in computer architecture designssuser87fa0c1
 
DATA ANALYTICS PPT definition usage example
DATA ANALYTICS PPT definition usage exampleDATA ANALYTICS PPT definition usage example
DATA ANALYTICS PPT definition usage examplePragyanshuParadkar1
 
Internship report on mechanical engineering
Internship report on mechanical engineeringInternship report on mechanical engineering
Internship report on mechanical engineeringmalavadedarshan25
 
VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...
VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...
VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...VICTOR MAESTRE RAMIREZ
 
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETEINFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETEroselinkalist12
 
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfCCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfAsst.prof M.Gokilavani
 
Call Girls Narol 7397865700 Independent Call Girls
Call Girls Narol 7397865700 Independent Call GirlsCall Girls Narol 7397865700 Independent Call Girls
Call Girls Narol 7397865700 Independent Call Girlsssuser7cb4ff
 

Recently uploaded (20)

young call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Service
young call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Serviceyoung call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Service
young call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Service
 
Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...
 
An experimental study in using natural admixture as an alternative for chemic...
An experimental study in using natural admixture as an alternative for chemic...An experimental study in using natural admixture as an alternative for chemic...
An experimental study in using natural admixture as an alternative for chemic...
 
HARMONY IN THE NATURE AND EXISTENCE - Unit-IV
HARMONY IN THE NATURE AND EXISTENCE - Unit-IVHARMONY IN THE NATURE AND EXISTENCE - Unit-IV
HARMONY IN THE NATURE AND EXISTENCE - Unit-IV
 
🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
 
Churning of Butter, Factors affecting .
Churning of Butter, Factors affecting  .Churning of Butter, Factors affecting  .
Churning of Butter, Factors affecting .
 
Introduction to Machine Learning Unit-3 for II MECH
Introduction to Machine Learning Unit-3 for II MECHIntroduction to Machine Learning Unit-3 for II MECH
Introduction to Machine Learning Unit-3 for II MECH
 
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdf
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdfCCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdf
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdf
 
Artificial-Intelligence-in-Electronics (K).pptx
Artificial-Intelligence-in-Electronics (K).pptxArtificial-Intelligence-in-Electronics (K).pptx
Artificial-Intelligence-in-Electronics (K).pptx
 
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxDecoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
 
Effects of rheological properties on mixing
Effects of rheological properties on mixingEffects of rheological properties on mixing
Effects of rheological properties on mixing
 
pipeline in computer architecture design
pipeline in computer architecture  designpipeline in computer architecture  design
pipeline in computer architecture design
 
DATA ANALYTICS PPT definition usage example
DATA ANALYTICS PPT definition usage exampleDATA ANALYTICS PPT definition usage example
DATA ANALYTICS PPT definition usage example
 
Internship report on mechanical engineering
Internship report on mechanical engineeringInternship report on mechanical engineering
Internship report on mechanical engineering
 
VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...
VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...
VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...
 
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETEINFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
 
young call girls in Green Park🔝 9953056974 🔝 escort Service
young call girls in Green Park🔝 9953056974 🔝 escort Serviceyoung call girls in Green Park🔝 9953056974 🔝 escort Service
young call girls in Green Park🔝 9953056974 🔝 escort Service
 
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfCCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
 
9953056974 Call Girls In South Ex, Escorts (Delhi) NCR.pdf
9953056974 Call Girls In South Ex, Escorts (Delhi) NCR.pdf9953056974 Call Girls In South Ex, Escorts (Delhi) NCR.pdf
9953056974 Call Girls In South Ex, Escorts (Delhi) NCR.pdf
 
Call Girls Narol 7397865700 Independent Call Girls
Call Girls Narol 7397865700 Independent Call GirlsCall Girls Narol 7397865700 Independent Call Girls
Call Girls Narol 7397865700 Independent Call Girls
 

Deep Learning for Image Classification and Object Detection

  • 2. Shallow Learning • SVM • Linear & Kernel Regression • Hidden Markov Models (HMM) • Gaussian Mixture Models (GMM) • Single hidden layer MLP Limitations Cannot make use of unlabeled data
  • 3. Supervised vs Unsupervised Learning • Supervised Learning 1.Output has to be produced according to target vector. 2.Input + Target vector = Training Pair 3.Labelled Data • Unsupervised Learning ( self Organising) 1.Network receives input patterns to form clusters. 2.When a new input pattern is applied , output gives the class the input pattern belongs to 3.Unlabelled Data
  • 4. Neural Networks • Machine Learning • Knowledge from high dimensional data • Classification • Input: features of data • supervised vs unsupervised • labeled data • Neurons
  • 5. What is it used for? • Classification • Regression ---- Prediction ---- Fitting Curve
  • 6. Multi Layer Perceptron • Multiple Layers • Feed Forward • Connected Weights • 1-of-N Output hidden output
  • 7. Back Propagation • Minimize error of calculated output • Adjust weights • Gradient Descent • Procedure • Forward Phase • Backpropagation of errors • For each sample, multiple epochs
  • 8. Problems with Backpropagation • Multiple hidden Layers • Get stuck in local optima • start weights from random positions • Only use labeled data • most data is unlabeled
  • 9. Deep Learning Means Feature Learning • Deep Learning is about Learning Hierarchical Features.
  • 10. Convolutional Neural Network Feature extraction layer Convolution layer Shift and distortion invariance or Subsampling layer
  • 11. CNN contd. • Detect the same feature at different positions in the input image in C Layer. features
  • 12. CNN Contd. Shared weights: all neurons in a feature share the same weights (but not the biases). In this way all neurons detect the same feature at different positions in the input image. Reduce the number of free parameters. If a neuron in the feature map fires, this corresponds to a match with the template
  • 13. CNN Contd. S Layer The subsampling layers reduce the spatial resolution of each feature map By reducing the spatial resolution of the feature map, a certain degree of shift and distortion invariance is achieved
  • 14. Contd. S layer The weight sharing is also applied in subsampling layers Reduce the effect of noises and shift or distortion.
  • 15. Applications Speech Recognition. Object Detection ( Computer Vision). Web search – Text Analysis.
  • 16. Few Insights Gathered From Papers. • Used CBIR method to do feature extractions in Convolutional Layer. • Applied filters to feature extraction. • Used Definite size of patch to work upon. • CNN method was used throughout. • 3D convolution – time added as third factor . • Feature Extraction so far observed was: 1. Gradient Filter in X and Y directions.
  • 17. Object Detection Architecture: Dataset : MIT Face dataset 1104 faces. Training – 200 images. Test - 200 images. The Convolutional Neural Network consists of two parts 1) the convolution layers and max-pooling layers 2) the fully connection layers and the output layers. The Input Layer consists of 72x72 size histogram equalized images an output is the set of different face images each of size 18x18. The networks used for face detection and face recognition contains two convolutional layer and two sub-sampling layer.
  • 18. Output Layer 72 x 72 72x72 :5no 36x36: 5no 36X36 18 x 18: 12no Output Layer 20 faces Feature Maps :5no Feature Maps :5no Input Layer Conv Layer-1 Kernels of 3x3 Conv Layer-2Samp Layer-1 Samp Layer-2
  • 19. Convolutional Layer Total of 5 kernels of size 3x3 is used to convolutional operation. 5 different feature maps : • gray • gradient –x • gradient-y • last two kernels gives the information below the eyes area.
  • 20. Sampling Layer • Mean filter of 2x2 is applied on image • Alternate rows and alternate columns of image is sampled out. 72 x 72 72x72 :5no 36x36: 5no 36X36 18 x 18: 12no Fully connected layer20 faces Feature Maps :5no Feature Maps :5no Input Layer Conv Layer-1 Kernels of 3x3 Conv Layer-2Samp Layer-1 Samp Layer-2
  • 21. Fully Connected And Output Layer • Output layer : 70 images. 72 x 72 72x72 :5no 36x36: 5no 36X36 18 x 18: 12no Fully connected layer20 faces Feature Maps :5no Feature Maps :5no Input Layer Conv Layer-1 Kernels of 3x3 Conv Layer-2Samp Layer-1 Samp Layer-2
  • 22. Error Propagation. • Error Matrix e is obtained by finding difference between values of neurons in output layer and fully connected layer. • As there are 5 kernels in convolutional layers so each face will have 5 different feature maps. So in fully connected layer of Object Recognition CNN,total neurons are 18 X 18 X 5(feature maps). • So, Mean error M(i=1:5) of each Map is calculated. • EM is Mean of M(i=1:5) is calculated. • Error {M( i=1 :5) } is used for back-propagation. • {EM} is used as a threshold such that any value below the threshold is considered success or face match.
  • 23. Implementation 1) Input of 200 images each of size 72X72 is presented to network one by one for training. 2) In First Layer, Convolutional operation is performed using aforementioned kernels of size 3X3 .The resultant output is of size 7 2 X 72 X 5. 3) In first S Layer, Sampling of image using mean filter of size 2X2 and sampling alternate rows and columns.The output of this of size 36 X 36 X 5.
  • 24. 4) In Second C layer,after convolution operation we get output of size 36 X 36 X 5 . 5) In Second S layer, after sampling operation we get image of size 200 X 18 X 18 X 5. 6) The Fully connected layer is obtained after S layer and it is of size 18 X 18 X 5 and each of neuron is connected to output layer. 7) Error Propagated using above method mentioned in Back Propagation section of Object Recognition. 8) Error propagation takes place for fixed number of epochs in during trainning. 9) For testing, {EM} obtained in equation is used as threshold to find face match.
  • 25. Results – Error vs Epochs
  • 26. Results – Accuracy vs epochs
  • 27. Object Detection. • Input – Face images of size 72 x 72 Non Face images of size 72 x 72 • Output – 1 or 0
  • 28. Error Propagation • Error Matrix e is obtained by finding difference between values of neurons in output layer and fully connected layer. • Error of each neuron is propagated backwards and thus weight up- dation is done. • The backpropagation comes to hault when error <0.0003 or number of epochs is 64 for training.
  • 29. Object Detection ( Face/Non face) 1) Input of 50 (30 faces +20 non face) images each of size 72X72 is presented to network one by one for training. 2) In First Layer, Convolutional operation is performed using aforementioned kernels of size 3X3 .The resultant output is of size 7 2 X 72 X 5. 3) In first S Layer, Sampling of image using mean filter of size 2X2 and sampling alternate rows and columns.The output of this of size 36 X 36 X 5.
  • 30. 4) In Second C layer,after convolution operation we get output of size 36 X 36 X 5 . 5) In Second S layer, after sampling operation we get image of size 18 X 18 X 5. 6) The Fully connected layer is obtained after S layer and it is of size 18 X 18 X 5 and each of neuron is connected to output layer. 7) Error Propagated using above method mentioned in Back Propagation section of Object Recognition. 8) Error propagation takes place for fixed number of epochs in during trainning. 9) For testing, 200 images were used 125 faces and 75 non face.
  • 31. Result: Confusion Matrix Face Non face Face (test) 100 25 Non Face (test) 32 43 Accuracy : 80% approx. for faces. Accuracy : 57.33 % approx. for non faces. Time to detect a face : 25.35 secs approx.
  • 33. Implementation iterative search 1) Input is an image is presented to network . 2) 72 X 72 patch is created and presented to network. 3) In First Layer, Convolutional operation is performed using aforementioned kernels of size 3X3 .The resultant output is of size 7 2 X 72 X 5. 4) In first S Layer, Sampling of image using mean filter of size 2X2 and sampling alternate rows and columns.The output of this of size 36 X 36 X 5.
  • 34. 4) In Second C layer,after convolution operation we get output of size 36 X 36 X 5 . 5) In Second S layer, after sampling operation we get image of size 200 X 18 X 18 X 5. 6) The Fully connected layer is obtained after S layer and it is of size 18 X 18 X 5 and each of neuron is connected to output layer. 7) Error Propagated using above method mentioned in Back Propagation section of Object Recognition. 8) Error propagation takes place for fixed number of epochs in during trainning. 9) As an image is found Count = count+1.
  • 35. Results: Error vs ith iteration face found.
  • 37. To do. • Face detection using in set of images. • Improve the accuracy. • Implement it for videos.