SlideShare a Scribd company logo
A Framework for Scene Recognition Using
Convolutional Neural Network as Feature
Extractor and Machine Learning Kernels as
Classifier
Tahmid Abtahi, Aniket Badhan and Sri Harsha
Department of Computer Science & Electrical Engineering
University of Maryland, Baltimore County
{abtahi1,yh02299,ksrihar1}@umbc.edu
Frame work
Why?
-Scene recognition is
valuable in computer vision
-Autonomous navigation
-DataSet ?
- VGG set
-Three category
-High way
-Open Country
-Streets
-678 Images
Convolutional Neural Network (CNN) –
Feature Extractor
Why Feature Extraction ?
-Data Dimensionality Reduction
10 x times in propsed case
--Key Feature Extraction
Algorithm :Convolution
Pseudo Code Convolution:
for Patch_x_axis_movement{
initialize sum =0;
for Patch_y_axis_movement{
calculate dot product (Patch, Filter);
}
result_convolution (x,y) = Dot product;
}
Convolution Operation calculation
Data size Filter size Stri
de
Number of Patch Addition op
per patch
Multiplicati
on op. per
patch
Total op Order
nxn mxm 1 (n-m+1)x (n-m+1) m-1 m m(m-1) (n-
m+1)2
O(n3)
64x64 9x9 1 56x56 = 3136 8 9 2,25,792
Algorithm : Max Pool, ReLU
Pseudo Code Maxpool:
for Patch_x_axis_movement{
for Patch_y_axis_movement{
calculate Max (Patch);
}
result_maxpool (x,y) = Dot product;
}
Pseudo Code ReLU:
update F = max(0, x)
Maxpool Operation calculation
Data size Patch size Factor Number of Patch Comparision op per
patch
Total op Order
nxn mxm m (n/m)x (n/m) m-1 (m-1) (n/m)2 O(n2)
56x56 7x7 7 8x8=64 6 384
Linear Rectification Operation calculation
Data size op per element Total op Order
nxn 1 n2 O(n2)
8x8 1 64
1x Convolution
1/588x Maxpool
1/3528x times ReLU
Implementation and Result
Communication dominating computation
10x dimensionality Reduction
Pre Work
- Training CNN in MatConvNet
--Creating matlab Prototype for
cross checking checking results
Perceptron
• Algorithm for supervised learning of binary classifiers
• Function that maps its inputs x to an output value f(x)
• w is the vector of real valued weights
• f(x) is the output
• m is the no. of inputs to the perceptron
• b is the bias
Pseudo code
Parallel Implementation
• In the training phase, One vs All is implemented for each
output class. This process can be done in parallel, with each
processor handling divided output classes.
• While testing , the test data is divided amongst the processors,
and each processor will report its local accuracy to the Master
node. In the Master node, it will use MPI Reduce to sum the
received local accuracy value and return the final accuracy and
the accuracy percentage.
Results
Results
Results
Varying the Training and keeping the Testing Data size as constant and Processor count as 4
SVM Classifier
• Support Vector Machines (also popularly known as SVM or Support Vector
Networks) are supervised learning models with associated learning algorithms that
analyze data used for classification.
• Used for binary Classification
SVM One versus All
• From the above discussion on SVM, it’s clear that the above model of
SVM can be used for binary classification only, i.e., it can separate
only two classes.
• So, for classification of data points with more than 2 possible outputs,
the above model would fail.
• Hence, to overcome this, there is an enhancement in SVM which is
SVM OVA (One versus All).
• In this model, one output class is separated from the other output
classes and hence, the name One Versus All.
Parallel Implementation
• The training phase will be implementation of OVA for each output class.
This process can be done in parallel, with each processor handling
divided output classes.
• For the testing phase, the number of test data points can be divided
amongst the processor, and each processor can report its local accuracy
to the Master node.
• The Master node will use MPI Reduce to sum the received local accuracy
and report the final accuracy and the accuracy percentage.
• In the implementation, all the processors do work, including the master
node, which ensures load balancing as the tasks are the same.
Results
Results
Increasing the Training Data size and keeping the Testing Data
size and Number of Processors as constant
Comparison Between SVM and Perceptron
• SVM includes the factor (1/input number) in weight calculation.
• This helps in getting better accuracy as any input which has noise can
not have much impact on the weight values.
• Also, Lambda is used as an hyper-parameter in weight calculation,
which takes care of the over-fitting and under-fitting.
• Accuracy obtained using Perceptron is comparatively lesser than SVM,
taking almost the same time for computation
Training Data Size Testing Data Size Number of Processors Time Required for SVM
Time
Required for
Perceptron Accuracy for SVM Accuracy for Perceptron
4000 1000 1 0.658 0.617 75.5 72.19
4000 1000 2 1.255 1.283 75.5 72.19
4000 1000 3 1.772 1.955 75.5 72.19
4000 1000 4 2.408 2.366 75.5 72.19
4000 1000 5 2.966 3.035 75.5 72.19
4000 1000 6 3.769 4.11 75.5 72.19
4000 1000 7 5.567 6.987 75.5 72.19
4000 1000 8 8.016 8.037 75.5 72.19
Future Scope
• Task Level Parallel Implementation of SVM and Perceptron
• Increasing the Data Size and Output Classes and use the prepared
framework for advanced scene recognition
• Comparing the results of PCA (Principal Component Analysis) with
CNN and compare which gives the better accuracy.
• Implementing other ML Kernels such as Logistic Regression, k-NN,
etc.
• CNN – GO DEEP
Questions?

More Related Content

What's hot

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
 
Neural Network as a function
Neural Network as a functionNeural Network as a function
Neural Network as a function
Taisuke Oe
 
Deep Learning - RNN and CNN
Deep Learning - RNN and CNNDeep Learning - RNN and CNN
Deep Learning - RNN and CNN
Pradnya Saval
 
HardNet: Convolutional Network for Local Image Description
HardNet: Convolutional Network for Local Image DescriptionHardNet: Convolutional Network for Local Image Description
HardNet: Convolutional Network for Local Image Description
Dmytro Mishkin
 
Convolutional Neural Networks
Convolutional Neural NetworksConvolutional Neural Networks
Convolutional Neural Networks
Tianxiang Xiong
 
Convolutional neural networks
Convolutional neural networks Convolutional neural networks
Convolutional neural networks
Roozbeh Sanaei
 
Tutorial on convolutional neural networks
Tutorial on convolutional neural networksTutorial on convolutional neural networks
Tutorial on convolutional neural networks
Hojin Yang
 
Machine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural NetworkMachine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural Network
Richard Kuo
 
Neuroevolution and deep learing
Neuroevolution and deep learing Neuroevolution and deep learing
Neuroevolution and deep learing
Accenture
 
Review on cs231 part-2
Review on cs231 part-2Review on cs231 part-2
Review on cs231 part-2
Jeong Choi
 
Cnn
CnnCnn
Introduction to Convolutional Neural Networks
Introduction to Convolutional Neural NetworksIntroduction to Convolutional Neural Networks
Introduction to Convolutional Neural Networks
Hannes Hapke
 
Introduction to CNN
Introduction to CNNIntroduction to CNN
Introduction to CNN
Shuai Zhang
 
convolutional neural network (CNN, or ConvNet)
convolutional neural network (CNN, or ConvNet)convolutional neural network (CNN, or ConvNet)
convolutional neural network (CNN, or ConvNet)
RakeshSaran5
 
PR095: Modularity Matters: Learning Invariant Relational Reasoning Tasks
PR095: Modularity Matters: Learning Invariant Relational Reasoning TasksPR095: Modularity Matters: Learning Invariant Relational Reasoning Tasks
PR095: Modularity Matters: Learning Invariant Relational Reasoning Tasks
Jinwon Lee
 
Convolutional Neural Networks
Convolutional Neural NetworksConvolutional Neural Networks
Convolutional Neural Networks
Ashray Bhandare
 
Convolutional neural network from VGG to DenseNet
Convolutional neural network from VGG to DenseNetConvolutional neural network from VGG to DenseNet
Convolutional neural network from VGG to DenseNet
SungminYou
 
Convolutional neural network
Convolutional neural networkConvolutional neural network
Convolutional neural network
MojammilHusain
 
Convolutional neural networks deepa
Convolutional neural networks deepaConvolutional neural networks deepa
Convolutional neural networks deepa
deepa4466
 
Modern Convolutional Neural Network techniques for image segmentation
Modern Convolutional Neural Network techniques for image segmentationModern Convolutional Neural Network techniques for image segmentation
Modern Convolutional Neural Network techniques for image segmentation
Gioele Ciaparrone
 

What's hot (20)

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
 
Neural Network as a function
Neural Network as a functionNeural Network as a function
Neural Network as a function
 
Deep Learning - RNN and CNN
Deep Learning - RNN and CNNDeep Learning - RNN and CNN
Deep Learning - RNN and CNN
 
HardNet: Convolutional Network for Local Image Description
HardNet: Convolutional Network for Local Image DescriptionHardNet: Convolutional Network for Local Image Description
HardNet: Convolutional Network for Local Image Description
 
Convolutional Neural Networks
Convolutional Neural NetworksConvolutional Neural Networks
Convolutional Neural Networks
 
Convolutional neural networks
Convolutional neural networks Convolutional neural networks
Convolutional neural networks
 
Tutorial on convolutional neural networks
Tutorial on convolutional neural networksTutorial on convolutional neural networks
Tutorial on convolutional neural networks
 
Machine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural NetworkMachine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural Network
 
Neuroevolution and deep learing
Neuroevolution and deep learing Neuroevolution and deep learing
Neuroevolution and deep learing
 
Review on cs231 part-2
Review on cs231 part-2Review on cs231 part-2
Review on cs231 part-2
 
Cnn
CnnCnn
Cnn
 
Introduction to Convolutional Neural Networks
Introduction to Convolutional Neural NetworksIntroduction to Convolutional Neural Networks
Introduction to Convolutional Neural Networks
 
Introduction to CNN
Introduction to CNNIntroduction to CNN
Introduction to CNN
 
convolutional neural network (CNN, or ConvNet)
convolutional neural network (CNN, or ConvNet)convolutional neural network (CNN, or ConvNet)
convolutional neural network (CNN, or ConvNet)
 
PR095: Modularity Matters: Learning Invariant Relational Reasoning Tasks
PR095: Modularity Matters: Learning Invariant Relational Reasoning TasksPR095: Modularity Matters: Learning Invariant Relational Reasoning Tasks
PR095: Modularity Matters: Learning Invariant Relational Reasoning Tasks
 
Convolutional Neural Networks
Convolutional Neural NetworksConvolutional Neural Networks
Convolutional Neural Networks
 
Convolutional neural network from VGG to DenseNet
Convolutional neural network from VGG to DenseNetConvolutional neural network from VGG to DenseNet
Convolutional neural network from VGG to DenseNet
 
Convolutional neural network
Convolutional neural networkConvolutional neural network
Convolutional neural network
 
Convolutional neural networks deepa
Convolutional neural networks deepaConvolutional neural networks deepa
Convolutional neural networks deepa
 
Modern Convolutional Neural Network techniques for image segmentation
Modern Convolutional Neural Network techniques for image segmentationModern Convolutional Neural Network techniques for image segmentation
Modern Convolutional Neural Network techniques for image segmentation
 

Similar to A Framework for Scene Recognition Using Convolutional Neural Network as Feature Extractor and Machine Learning Kernels as Classifier

GPU Parallel Computing of Support Vector Machines as applied to Intrusion Det...
GPU Parallel Computing of Support Vector Machines as applied to Intrusion Det...GPU Parallel Computing of Support Vector Machines as applied to Intrusion Det...
GPU Parallel Computing of Support Vector Machines as applied to Intrusion Det...
IJCSIS Research Publications
 
iterativealgorithms.ppsx
iterativealgorithms.ppsxiterativealgorithms.ppsx
iterativealgorithms.ppsx
Bharathi Lakshmi Pon
 
Iterative Algorithms.ppsx
Iterative Algorithms.ppsxIterative Algorithms.ppsx
Iterative Algorithms.ppsx
BharathiLakshmiAAssi
 
AIRLINE FARE PRICE PREDICTION
AIRLINE FARE PRICE PREDICTIONAIRLINE FARE PRICE PREDICTION
AIRLINE FARE PRICE PREDICTION
IRJET Journal
 
Performance comparison of row per slave and rows set
Performance comparison of row per slave and rows setPerformance comparison of row per slave and rows set
Performance comparison of row per slave and rows set
eSAT Publishing House
 
Random Forest Decision Tree.pptx
Random Forest Decision Tree.pptxRandom Forest Decision Tree.pptx
Random Forest Decision Tree.pptx
Ramakrishna Reddy Bijjam
 
Build Deep Learning model to identify santader bank's dissatisfied customers
Build Deep Learning model to identify santader bank's dissatisfied customersBuild Deep Learning model to identify santader bank's dissatisfied customers
Build Deep Learning model to identify santader bank's dissatisfied customerssriram30691
 
Apache Spark Based Hyper-Parameter Selection and Adaptive Model Tuning for De...
Apache Spark Based Hyper-Parameter Selection and Adaptive Model Tuning for De...Apache Spark Based Hyper-Parameter Selection and Adaptive Model Tuning for De...
Apache Spark Based Hyper-Parameter Selection and Adaptive Model Tuning for De...
Databricks
 
NLP Classifier Models & Metrics
NLP Classifier Models & MetricsNLP Classifier Models & Metrics
NLP Classifier Models & Metrics
Sanghamitra Deb
 
Performance comparison of row per slave and rows set per slave method in pvm ...
Performance comparison of row per slave and rows set per slave method in pvm ...Performance comparison of row per slave and rows set per slave method in pvm ...
Performance comparison of row per slave and rows set per slave method in pvm ...
eSAT Journals
 
Nimrita deep learning
Nimrita deep learningNimrita deep learning
Nimrita deep learning
Nimrita Koul
 
NEURAL Network Design Training
NEURAL Network Design  TrainingNEURAL Network Design  Training
NEURAL Network Design TrainingESCOM
 
Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...
Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...
Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...
Universitat Politècnica de Catalunya
 
Rapid Miner
Rapid MinerRapid Miner
Rapid Miner
SrushtiSuvarna
 
Understand and Harness the Capabilities of Intel® Xeon Phi™ Processors
Understand and Harness the Capabilities of Intel® Xeon Phi™ ProcessorsUnderstand and Harness the Capabilities of Intel® Xeon Phi™ Processors
Understand and Harness the Capabilities of Intel® Xeon Phi™ Processors
Intel® Software
 
Comprehensive Performance Evaluation on Multiplication of Matrices using MPI
Comprehensive Performance Evaluation on Multiplication of Matrices using MPIComprehensive Performance Evaluation on Multiplication of Matrices using MPI
Comprehensive Performance Evaluation on Multiplication of Matrices using MPI
ijtsrd
 
Support Vector machine(SVM) and Random Forest
Support Vector machine(SVM) and Random ForestSupport Vector machine(SVM) and Random Forest
Support Vector machine(SVM) and Random Forest
umarcybermind
 
C3 w1
C3 w1C3 w1

Similar to A Framework for Scene Recognition Using Convolutional Neural Network as Feature Extractor and Machine Learning Kernels as Classifier (20)

GPU Parallel Computing of Support Vector Machines as applied to Intrusion Det...
GPU Parallel Computing of Support Vector Machines as applied to Intrusion Det...GPU Parallel Computing of Support Vector Machines as applied to Intrusion Det...
GPU Parallel Computing of Support Vector Machines as applied to Intrusion Det...
 
iterativealgorithms.ppsx
iterativealgorithms.ppsxiterativealgorithms.ppsx
iterativealgorithms.ppsx
 
Iterative Algorithms.ppsx
Iterative Algorithms.ppsxIterative Algorithms.ppsx
Iterative Algorithms.ppsx
 
AIRLINE FARE PRICE PREDICTION
AIRLINE FARE PRICE PREDICTIONAIRLINE FARE PRICE PREDICTION
AIRLINE FARE PRICE PREDICTION
 
eam2
eam2eam2
eam2
 
Performance comparison of row per slave and rows set
Performance comparison of row per slave and rows setPerformance comparison of row per slave and rows set
Performance comparison of row per slave and rows set
 
Random Forest Decision Tree.pptx
Random Forest Decision Tree.pptxRandom Forest Decision Tree.pptx
Random Forest Decision Tree.pptx
 
Build Deep Learning model to identify santader bank's dissatisfied customers
Build Deep Learning model to identify santader bank's dissatisfied customersBuild Deep Learning model to identify santader bank's dissatisfied customers
Build Deep Learning model to identify santader bank's dissatisfied customers
 
Apache Spark Based Hyper-Parameter Selection and Adaptive Model Tuning for De...
Apache Spark Based Hyper-Parameter Selection and Adaptive Model Tuning for De...Apache Spark Based Hyper-Parameter Selection and Adaptive Model Tuning for De...
Apache Spark Based Hyper-Parameter Selection and Adaptive Model Tuning for De...
 
NLP Classifier Models & Metrics
NLP Classifier Models & MetricsNLP Classifier Models & Metrics
NLP Classifier Models & Metrics
 
Performance comparison of row per slave and rows set per slave method in pvm ...
Performance comparison of row per slave and rows set per slave method in pvm ...Performance comparison of row per slave and rows set per slave method in pvm ...
Performance comparison of row per slave and rows set per slave method in pvm ...
 
Nimrita deep learning
Nimrita deep learningNimrita deep learning
Nimrita deep learning
 
NEURAL Network Design Training
NEURAL Network Design  TrainingNEURAL Network Design  Training
NEURAL Network Design Training
 
Svm on cloud (presntation)
Svm on cloud  (presntation)Svm on cloud  (presntation)
Svm on cloud (presntation)
 
Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...
Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...
Training Deep Networks with Backprop (D1L4 Insight@DCU Machine Learning Works...
 
Rapid Miner
Rapid MinerRapid Miner
Rapid Miner
 
Understand and Harness the Capabilities of Intel® Xeon Phi™ Processors
Understand and Harness the Capabilities of Intel® Xeon Phi™ ProcessorsUnderstand and Harness the Capabilities of Intel® Xeon Phi™ Processors
Understand and Harness the Capabilities of Intel® Xeon Phi™ Processors
 
Comprehensive Performance Evaluation on Multiplication of Matrices using MPI
Comprehensive Performance Evaluation on Multiplication of Matrices using MPIComprehensive Performance Evaluation on Multiplication of Matrices using MPI
Comprehensive Performance Evaluation on Multiplication of Matrices using MPI
 
Support Vector machine(SVM) and Random Forest
Support Vector machine(SVM) and Random ForestSupport Vector machine(SVM) and Random Forest
Support Vector machine(SVM) and Random Forest
 
C3 w1
C3 w1C3 w1
C3 w1
 

Recently uploaded

bank management system in java and mysql report1.pdf
bank management system in java and mysql report1.pdfbank management system in java and mysql report1.pdf
bank management system in java and mysql report1.pdf
Divyam548318
 
Hierarchical Digital Twin of a Naval Power System
Hierarchical Digital Twin of a Naval Power SystemHierarchical Digital Twin of a Naval Power System
Hierarchical Digital Twin of a Naval Power System
Kerry Sado
 
[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf
[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf
[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf
awadeshbabu
 
14 Template Contractual Notice - EOT Application
14 Template Contractual Notice - EOT Application14 Template Contractual Notice - EOT Application
14 Template Contractual Notice - EOT Application
SyedAbiiAzazi1
 
PROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.ppt
PROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.pptPROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.ppt
PROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.ppt
bhadouriyakaku
 
Unbalanced Three Phase Systems and circuits.pptx
Unbalanced Three Phase Systems and circuits.pptxUnbalanced Three Phase Systems and circuits.pptx
Unbalanced Three Phase Systems and circuits.pptx
ChristineTorrepenida1
 
一比一原版(Otago毕业证)奥塔哥大学毕业证成绩单如何办理
一比一原版(Otago毕业证)奥塔哥大学毕业证成绩单如何办理一比一原版(Otago毕业证)奥塔哥大学毕业证成绩单如何办理
一比一原版(Otago毕业证)奥塔哥大学毕业证成绩单如何办理
dxobcob
 
Water billing management system project report.pdf
Water billing management system project report.pdfWater billing management system project report.pdf
Water billing management system project report.pdf
Kamal Acharya
 
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressions
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressionsKuberTENes Birthday Bash Guadalajara - K8sGPT first impressions
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressions
Victor Morales
 
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming PipelinesHarnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
Christina Lin
 
AIR POLLUTION lecture EnE203 updated.pdf
AIR POLLUTION lecture EnE203 updated.pdfAIR POLLUTION lecture EnE203 updated.pdf
AIR POLLUTION lecture EnE203 updated.pdf
RicletoEspinosa1
 
ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024
Rahul
 
Nuclear Power Economics and Structuring 2024
Nuclear Power Economics and Structuring 2024Nuclear Power Economics and Structuring 2024
Nuclear Power Economics and Structuring 2024
Massimo Talia
 
sieving analysis and results interpretation
sieving analysis and results interpretationsieving analysis and results interpretation
sieving analysis and results interpretation
ssuser36d3051
 
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
obonagu
 
Tutorial for 16S rRNA Gene Analysis with QIIME2.pdf
Tutorial for 16S rRNA Gene Analysis with QIIME2.pdfTutorial for 16S rRNA Gene Analysis with QIIME2.pdf
Tutorial for 16S rRNA Gene Analysis with QIIME2.pdf
aqil azizi
 
Modelagem de um CSTR com reação endotermica.pdf
Modelagem de um CSTR com reação endotermica.pdfModelagem de um CSTR com reação endotermica.pdf
Modelagem de um CSTR com reação endotermica.pdf
camseq
 
Recycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part IIIRecycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part III
Aditya Rajan Patra
 
在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样
在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样
在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样
obonagu
 
Technical Drawings introduction to drawing of prisms
Technical Drawings introduction to drawing of prismsTechnical Drawings introduction to drawing of prisms
Technical Drawings introduction to drawing of prisms
heavyhaig
 

Recently uploaded (20)

bank management system in java and mysql report1.pdf
bank management system in java and mysql report1.pdfbank management system in java and mysql report1.pdf
bank management system in java and mysql report1.pdf
 
Hierarchical Digital Twin of a Naval Power System
Hierarchical Digital Twin of a Naval Power SystemHierarchical Digital Twin of a Naval Power System
Hierarchical Digital Twin of a Naval Power System
 
[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf
[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf
[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf
 
14 Template Contractual Notice - EOT Application
14 Template Contractual Notice - EOT Application14 Template Contractual Notice - EOT Application
14 Template Contractual Notice - EOT Application
 
PROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.ppt
PROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.pptPROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.ppt
PROJECT FORMAT FOR EVS AMITY UNIVERSITY GWALIOR.ppt
 
Unbalanced Three Phase Systems and circuits.pptx
Unbalanced Three Phase Systems and circuits.pptxUnbalanced Three Phase Systems and circuits.pptx
Unbalanced Three Phase Systems and circuits.pptx
 
一比一原版(Otago毕业证)奥塔哥大学毕业证成绩单如何办理
一比一原版(Otago毕业证)奥塔哥大学毕业证成绩单如何办理一比一原版(Otago毕业证)奥塔哥大学毕业证成绩单如何办理
一比一原版(Otago毕业证)奥塔哥大学毕业证成绩单如何办理
 
Water billing management system project report.pdf
Water billing management system project report.pdfWater billing management system project report.pdf
Water billing management system project report.pdf
 
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressions
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressionsKuberTENes Birthday Bash Guadalajara - K8sGPT first impressions
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressions
 
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming PipelinesHarnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
 
AIR POLLUTION lecture EnE203 updated.pdf
AIR POLLUTION lecture EnE203 updated.pdfAIR POLLUTION lecture EnE203 updated.pdf
AIR POLLUTION lecture EnE203 updated.pdf
 
ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024
 
Nuclear Power Economics and Structuring 2024
Nuclear Power Economics and Structuring 2024Nuclear Power Economics and Structuring 2024
Nuclear Power Economics and Structuring 2024
 
sieving analysis and results interpretation
sieving analysis and results interpretationsieving analysis and results interpretation
sieving analysis and results interpretation
 
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
 
Tutorial for 16S rRNA Gene Analysis with QIIME2.pdf
Tutorial for 16S rRNA Gene Analysis with QIIME2.pdfTutorial for 16S rRNA Gene Analysis with QIIME2.pdf
Tutorial for 16S rRNA Gene Analysis with QIIME2.pdf
 
Modelagem de um CSTR com reação endotermica.pdf
Modelagem de um CSTR com reação endotermica.pdfModelagem de um CSTR com reação endotermica.pdf
Modelagem de um CSTR com reação endotermica.pdf
 
Recycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part IIIRecycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part III
 
在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样
在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样
在线办理(ANU毕业证书)澳洲国立大学毕业证录取通知书一模一样
 
Technical Drawings introduction to drawing of prisms
Technical Drawings introduction to drawing of prismsTechnical Drawings introduction to drawing of prisms
Technical Drawings introduction to drawing of prisms
 

A Framework for Scene Recognition Using Convolutional Neural Network as Feature Extractor and Machine Learning Kernels as Classifier

  • 1. A Framework for Scene Recognition Using Convolutional Neural Network as Feature Extractor and Machine Learning Kernels as Classifier Tahmid Abtahi, Aniket Badhan and Sri Harsha Department of Computer Science & Electrical Engineering University of Maryland, Baltimore County {abtahi1,yh02299,ksrihar1}@umbc.edu
  • 2. Frame work Why? -Scene recognition is valuable in computer vision -Autonomous navigation -DataSet ? - VGG set -Three category -High way -Open Country -Streets -678 Images
  • 3. Convolutional Neural Network (CNN) – Feature Extractor Why Feature Extraction ? -Data Dimensionality Reduction 10 x times in propsed case --Key Feature Extraction
  • 4. Algorithm :Convolution Pseudo Code Convolution: for Patch_x_axis_movement{ initialize sum =0; for Patch_y_axis_movement{ calculate dot product (Patch, Filter); } result_convolution (x,y) = Dot product; } Convolution Operation calculation Data size Filter size Stri de Number of Patch Addition op per patch Multiplicati on op. per patch Total op Order nxn mxm 1 (n-m+1)x (n-m+1) m-1 m m(m-1) (n- m+1)2 O(n3) 64x64 9x9 1 56x56 = 3136 8 9 2,25,792
  • 5. Algorithm : Max Pool, ReLU Pseudo Code Maxpool: for Patch_x_axis_movement{ for Patch_y_axis_movement{ calculate Max (Patch); } result_maxpool (x,y) = Dot product; } Pseudo Code ReLU: update F = max(0, x) Maxpool Operation calculation Data size Patch size Factor Number of Patch Comparision op per patch Total op Order nxn mxm m (n/m)x (n/m) m-1 (m-1) (n/m)2 O(n2) 56x56 7x7 7 8x8=64 6 384 Linear Rectification Operation calculation Data size op per element Total op Order nxn 1 n2 O(n2) 8x8 1 64 1x Convolution 1/588x Maxpool 1/3528x times ReLU
  • 6. Implementation and Result Communication dominating computation 10x dimensionality Reduction Pre Work - Training CNN in MatConvNet --Creating matlab Prototype for cross checking checking results
  • 7. Perceptron • Algorithm for supervised learning of binary classifiers • Function that maps its inputs x to an output value f(x) • w is the vector of real valued weights • f(x) is the output • m is the no. of inputs to the perceptron • b is the bias
  • 9. Parallel Implementation • In the training phase, One vs All is implemented for each output class. This process can be done in parallel, with each processor handling divided output classes. • While testing , the test data is divided amongst the processors, and each processor will report its local accuracy to the Master node. In the Master node, it will use MPI Reduce to sum the received local accuracy value and return the final accuracy and the accuracy percentage.
  • 12. Results Varying the Training and keeping the Testing Data size as constant and Processor count as 4
  • 13. SVM Classifier • Support Vector Machines (also popularly known as SVM or Support Vector Networks) are supervised learning models with associated learning algorithms that analyze data used for classification. • Used for binary Classification
  • 14. SVM One versus All • From the above discussion on SVM, it’s clear that the above model of SVM can be used for binary classification only, i.e., it can separate only two classes. • So, for classification of data points with more than 2 possible outputs, the above model would fail. • Hence, to overcome this, there is an enhancement in SVM which is SVM OVA (One versus All). • In this model, one output class is separated from the other output classes and hence, the name One Versus All.
  • 15.
  • 16.
  • 17. Parallel Implementation • The training phase will be implementation of OVA for each output class. This process can be done in parallel, with each processor handling divided output classes. • For the testing phase, the number of test data points can be divided amongst the processor, and each processor can report its local accuracy to the Master node. • The Master node will use MPI Reduce to sum the received local accuracy and report the final accuracy and the accuracy percentage. • In the implementation, all the processors do work, including the master node, which ensures load balancing as the tasks are the same.
  • 20. Increasing the Training Data size and keeping the Testing Data size and Number of Processors as constant
  • 21. Comparison Between SVM and Perceptron • SVM includes the factor (1/input number) in weight calculation. • This helps in getting better accuracy as any input which has noise can not have much impact on the weight values. • Also, Lambda is used as an hyper-parameter in weight calculation, which takes care of the over-fitting and under-fitting. • Accuracy obtained using Perceptron is comparatively lesser than SVM, taking almost the same time for computation Training Data Size Testing Data Size Number of Processors Time Required for SVM Time Required for Perceptron Accuracy for SVM Accuracy for Perceptron 4000 1000 1 0.658 0.617 75.5 72.19 4000 1000 2 1.255 1.283 75.5 72.19 4000 1000 3 1.772 1.955 75.5 72.19 4000 1000 4 2.408 2.366 75.5 72.19 4000 1000 5 2.966 3.035 75.5 72.19 4000 1000 6 3.769 4.11 75.5 72.19 4000 1000 7 5.567 6.987 75.5 72.19 4000 1000 8 8.016 8.037 75.5 72.19
  • 22. Future Scope • Task Level Parallel Implementation of SVM and Perceptron • Increasing the Data Size and Output Classes and use the prepared framework for advanced scene recognition • Comparing the results of PCA (Principal Component Analysis) with CNN and compare which gives the better accuracy. • Implementing other ML Kernels such as Logistic Regression, k-NN, etc. • CNN – GO DEEP

Editor's Notes

  1. Temporary output file of convolution Id Result 4 -71.435791 4 -76.951523 4 -78.251266 4 -85.814285 0 -88.926094 0 -92.253456