SlideShare a Scribd company logo
PRESENTED BY:-
GAURAV BISWAS
BIT MESRA
DEEP LEARNINGTECHNIQUES FOR
FALSE COLOURING OF SATELLITE IMAGES
 ABSTRACT
 INTRODUCTION
 USED DATASET
 PLATFORM AND LANGUAGE USED
 RESEARCH METHODOLOGY
 IMPLEMENTATION
 RESULT AND DISCUSSION
 CODES
 CONCLUSIONs
 FUTURE SCOPE
 REFERENCEs
CONTENTS
 Our intention is to use the technique of false colouring to
recolourize remote sensing images.
 Recolourizing an image is an extremely difficult task and an
acceptable recolourizing often not feasible without some prior
knowledge.
 For this we are using three techniques:-
(a) Convolutional Neural Network (CNN)
(b) Autoencoders and
(c) Variational Autoencoders (VAE)
ABSTRACT
 False colour refers to a group of colour rendering methods used to
display images in colour which were recorded in the visible or non-
visible parts.
INTRODUCTION
Satellite images are downloaded from Kaggle.
We used MNIST dataset as well as Cat-Dog dataset from Kaggle for
checking.
 Out of 25000 images we split the dataset into two parts i.e-
training and testing part.
All blurred and noisy image datasets are inputs for our different
techniques i.e- Autoencoders, Variational Autoencoders and
Convolutional Neural Network
USED DATASET
PLATFORMANDLANGUAGE USED
For this project we use Anaconda Navigator.
It is a desktop graphical user interface (GUI).
Under Anaconda Navigator we use-
Jupyter Notebook
Spyder
Language used is python programming.
 Using a Convolutional Neural Network (CNN) techniques for implementing
deep neural networks in remote sensing image and try to get the accuracy.
 Provide the satellite image dataset as an input.
 We have to use Autoencoders and Variational Autoencoders (VAE) to train the
Satellite images and check the accuracy of these approaches.
 Convert the Satellite Images (Black & White) into a false colour image using
these three approaches.
 Then train this images into a proper approach of deep learning techniques and
try to get more classified image as an output.
RESEARCH METHODOLOGY
(A) Convolutional Neural Network:
 In deep learning, a convolutional neural network is a class of deep neural
networks, most commonly applied to analyzing visual imagery.
 They are regularized versions of multilayer perceptrons. It usually mean fully
connected networks, that is, each neuron in one layer is connected to all
neurons in the next layer.
 Here’s an example of a convolutional neural network:
RESEARCH METHODOLOGY
output
ACCURACYOF CONVOLUTIONALNEURAL
NETWORK
It is clearly seen that the Accuracy for Convolutional Neural Network (CNN) is 92%.
In this model we train our dataset into 50 epoche and finally get this accuracy.
OUTPUTOFCONVOLUTIONALNEURAL
NETWORK
Figure - After performing False colouring using CNN technique
CODES
The code of the Convolutional Neural Network in jupyter notebook as below
First we have to select the model, here we are selecting sequential then we are
adding hidden layers to it and in the last layer we are using softmax as the
activation function.
Next, we add a 2D CNN layer to process the dataset input images. First argument passed to the 2D
layer function is the number of the output channels here we use 32 output channels.
Now we use flatten i.e. merge after pooling
CONTD…
Now we want to train our model and then getting the output after 50 epoch.
CONTD…
CONTD…
(B) Autoencoders:
 An autoencoder is a type of artificial neural network used to learn efficient
data in an unsupervised manner.
 The aim of an autoencoder is to learn a representation for a set of data,
typically for dimensionality reduction, by training the network to ignore
signal “noise”.
RESEARCH METHODOLOGY
IMPLEMENTATIONOFAUTOENCODERS
For implementing this technique we are using Sequential model in keras which is used most of
the time.
Next we have to split our dataset into our training and test data.
Added our first layer with 32 neurons and activation function ReLU.
In this case the input and output is same, we only care about the bottleneck part.
Add second layer with same configuration and from bottleneck we have to decode it to get the
proper output.
Added a fully connected Dense layer
Add an output layer that uses softmax activation for the no of classes.
ACCURACYOF AUTOENCODERS
Here we can clearly see that the variational loss is about 0.10 and the accuracy is 90%.
Here in this techniques we doesn’t care about the input it is just the replica of the output
we just care about the bottleneck part from that part we decode it and gets the proper
output.
OUTPUTOF AUTOENCODER
Figure - After performing False colouring using
Autoencoder technique
CODES
The code of the Autoencoder in jupyter notebook as below
CONTD…
Now let's train our autoencoder for 50 epochs
CONTD…
(C) Variational autoencoder:
 Just as a standard autoencoder, a variational autoencoder is an architecture
composed of both an encoder and a decoder and that is trained to
minimize the reconstruction error between the encoded-decoded data and
the initial data.
RESEARCH METHODOLOGY
ACCURACYOF VARIATIONAL
AUTOENCODERS (VAE)
It is clearly seen that the Accuracy for Variational Autoencoder is 92%.
In this case we have to take mean and variance and from that we have to decode it to
get the proper output. The VAE output is more clear compared to the Autoencoders.
IMPLEMENTATIONOF VARIATIONAL
AUTOENCODERS(VAE)
For implementing this technique we are using Sequential model in keras which is used most
of the time.
Next we have to split our dataset into our training and test data.
Added our first layer with 32 neurons and activation function ReLU.
In this case also the input and output is same, but after bottleneck part we have to take the
mean and variance and from that we to decode it to get the output.
Add second layer with same configuration
Added a fully connected Dense layer.
Add an output layer that uses softmax activation for the no of classes.
OUTPUTOF VARIATIONALAUTOENCODER(VAE)
Figure -After performing False colouring using Variational Autoencoder (VAE) technique
CODES
We perform the Variational Autoencoders means we run the VAE code in the Google Colab
platform the code is as below. Firstly here is our encoder network
Then we can use the parameters to the sample new similar points
CONTD…
We train our dataset
Our latent space is of two dimensional so there are few cool visualizations which have to be
done at this point.
CONTD…
As we all know that the VAE is a generative model we also use it for generating new dataset
CONTD…
 Using CNN to train Satellite Images for False Colouring.
 But due to large size of the image the neural network may not gives the
proper output for this we have to use net graph.
 We also use metrics to check whether the colouring is proper or not.
 In our project the accuracy for Autoencoder is near about 90% and for
Variational Autoencoder it is coming 92%.
CONCLUSIONS
FUTURE SCOPE
Any deep learning application that we are using has big scope in
future and in our project we have trained our satellite image dataset
with three different approaches.
To get more accuracy we need to train our satellite images in
Hybridization approach so that our images can create more
uniformality to the colours found in images.
[1] NASA’s Earth Observatory. How to interpret a Satellite Image. K. Aardal, S. van
Hoesel, A. Koster, C. Mannino, Models and solution techniques.
[2] S. Alouf, J. Galtier, C. Touati, MFTDMA satellites, in INFOCOM 2005, 24th
Annual Joint Conference of the IEEE, in Proceedings IEEE, 2005
[3] D. Kingma, Auto-Encoding Variational Bayes of the IEEE, ICLR, 2014
[4] Xinchen Yan, Jimei Yang, Kihyuk Sohn, Honglak Lee, Attribute2Image:
Conditional Image Generation from Visual Attributes IEEE, ECCV, 2016
[5] http://earthobservatory.nasa.gov/Features/FalseColor/page6.php
[6] https://ieeexplore.ieee.org/document/861379/keywords#keywords
REFERENCES
False colouring

More Related Content

What's hot

160205 NeuralArt - Understanding Neural Representation
160205 NeuralArt - Understanding Neural Representation160205 NeuralArt - Understanding Neural Representation
160205 NeuralArt - Understanding Neural Representation
Junho Cho
 
A ROBUST CHAOTIC AND FAST WALSH TRANSFORM ENCRYPTION FOR GRAY SCALE BIOMEDICA...
A ROBUST CHAOTIC AND FAST WALSH TRANSFORM ENCRYPTION FOR GRAY SCALE BIOMEDICA...A ROBUST CHAOTIC AND FAST WALSH TRANSFORM ENCRYPTION FOR GRAY SCALE BIOMEDICA...
A ROBUST CHAOTIC AND FAST WALSH TRANSFORM ENCRYPTION FOR GRAY SCALE BIOMEDICA...
sipij
 
Hf2513081311
Hf2513081311Hf2513081311
Hf2513081311
IJERA Editor
 
Deep learning in Computer Vision
Deep learning in Computer VisionDeep learning in Computer Vision
Deep learning in Computer Vision
David Dao
 
Learning spatiotemporal features with 3 d convolutional networks
Learning spatiotemporal features with 3 d convolutional networksLearning spatiotemporal features with 3 d convolutional networks
Learning spatiotemporal features with 3 d convolutional networks
SungminYou
 
Image captioning
Image captioningImage captioning
Image captioning
Muhammad Zbeedat
 
IRJET- Study of SVM and CNN in Semantic Concept Detection
IRJET- Study of SVM and CNN in Semantic Concept DetectionIRJET- Study of SVM and CNN in Semantic Concept Detection
IRJET- Study of SVM and CNN in Semantic Concept Detection
IRJET Journal
 
Biometric presentation attack detection
Biometric presentation attack detectionBiometric presentation attack detection
Biometric presentation attack detection
Gautam Saxena
 
Automated Speech Recognition
Automated Speech Recognition Automated Speech Recognition
Automated Speech Recognition
Pruthvij Thakar
 
Deep Learning for Structure-from-Motion (SfM)
Deep Learning for Structure-from-Motion (SfM)Deep Learning for Structure-from-Motion (SfM)
Deep Learning for Structure-from-Motion (SfM)
PetteriTeikariPhD
 
Accurate and Energy-Efficient Range-Free Localization for Mobile Sensor Networks
Accurate and Energy-Efficient Range-Free Localization for Mobile Sensor NetworksAccurate and Energy-Efficient Range-Free Localization for Mobile Sensor Networks
Accurate and Energy-Efficient Range-Free Localization for Mobile Sensor Networks
ambitlick
 
101: Convolutional Neural Networks
101: Convolutional Neural Networks 101: Convolutional Neural Networks
101: Convolutional Neural Networks
Mad Scientists
 
“Case Study: Facial Detection and Recognition for Always-On Applications,” a ...
“Case Study: Facial Detection and Recognition for Always-On Applications,” a ...“Case Study: Facial Detection and Recognition for Always-On Applications,” a ...
“Case Study: Facial Detection and Recognition for Always-On Applications,” a ...
Edge AI and Vision Alliance
 
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
Seonho Park
 
Multimodal Sequential Learning for Video QA
Multimodal Sequential Learning for Video QAMultimodal Sequential Learning for Video QA
Multimodal Sequential Learning for Video QA
NAVER Engineering
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
Junaid Bhat
 
Optimization of image compression and ciphering based on EZW techniques
Optimization of image compression and ciphering based on EZW techniquesOptimization of image compression and ciphering based on EZW techniques
Optimization of image compression and ciphering based on EZW techniques
TELKOMNIKA JOURNAL
 
Hardware software co simulation of edge detection for image processing system...
Hardware software co simulation of edge detection for image processing system...Hardware software co simulation of edge detection for image processing system...
Hardware software co simulation of edge detection for image processing system...
eSAT Publishing House
 
H43044145
H43044145H43044145
H43044145
IJERA Editor
 

What's hot (20)

160205 NeuralArt - Understanding Neural Representation
160205 NeuralArt - Understanding Neural Representation160205 NeuralArt - Understanding Neural Representation
160205 NeuralArt - Understanding Neural Representation
 
A ROBUST CHAOTIC AND FAST WALSH TRANSFORM ENCRYPTION FOR GRAY SCALE BIOMEDICA...
A ROBUST CHAOTIC AND FAST WALSH TRANSFORM ENCRYPTION FOR GRAY SCALE BIOMEDICA...A ROBUST CHAOTIC AND FAST WALSH TRANSFORM ENCRYPTION FOR GRAY SCALE BIOMEDICA...
A ROBUST CHAOTIC AND FAST WALSH TRANSFORM ENCRYPTION FOR GRAY SCALE BIOMEDICA...
 
Hf2513081311
Hf2513081311Hf2513081311
Hf2513081311
 
Deep learning in Computer Vision
Deep learning in Computer VisionDeep learning in Computer Vision
Deep learning in Computer Vision
 
Learning spatiotemporal features with 3 d convolutional networks
Learning spatiotemporal features with 3 d convolutional networksLearning spatiotemporal features with 3 d convolutional networks
Learning spatiotemporal features with 3 d convolutional networks
 
Mangesh_kothule_resume
Mangesh_kothule_resumeMangesh_kothule_resume
Mangesh_kothule_resume
 
Image captioning
Image captioningImage captioning
Image captioning
 
IRJET- Study of SVM and CNN in Semantic Concept Detection
IRJET- Study of SVM and CNN in Semantic Concept DetectionIRJET- Study of SVM and CNN in Semantic Concept Detection
IRJET- Study of SVM and CNN in Semantic Concept Detection
 
Biometric presentation attack detection
Biometric presentation attack detectionBiometric presentation attack detection
Biometric presentation attack detection
 
Automated Speech Recognition
Automated Speech Recognition Automated Speech Recognition
Automated Speech Recognition
 
Deep Learning for Structure-from-Motion (SfM)
Deep Learning for Structure-from-Motion (SfM)Deep Learning for Structure-from-Motion (SfM)
Deep Learning for Structure-from-Motion (SfM)
 
Accurate and Energy-Efficient Range-Free Localization for Mobile Sensor Networks
Accurate and Energy-Efficient Range-Free Localization for Mobile Sensor NetworksAccurate and Energy-Efficient Range-Free Localization for Mobile Sensor Networks
Accurate and Energy-Efficient Range-Free Localization for Mobile Sensor Networks
 
101: Convolutional Neural Networks
101: Convolutional Neural Networks 101: Convolutional Neural Networks
101: Convolutional Neural Networks
 
“Case Study: Facial Detection and Recognition for Always-On Applications,” a ...
“Case Study: Facial Detection and Recognition for Always-On Applications,” a ...“Case Study: Facial Detection and Recognition for Always-On Applications,” a ...
“Case Study: Facial Detection and Recognition for Always-On Applications,” a ...
 
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroim...
 
Multimodal Sequential Learning for Video QA
Multimodal Sequential Learning for Video QAMultimodal Sequential Learning for Video QA
Multimodal Sequential Learning for Video QA
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Optimization of image compression and ciphering based on EZW techniques
Optimization of image compression and ciphering based on EZW techniquesOptimization of image compression and ciphering based on EZW techniques
Optimization of image compression and ciphering based on EZW techniques
 
Hardware software co simulation of edge detection for image processing system...
Hardware software co simulation of edge detection for image processing system...Hardware software co simulation of edge detection for image processing system...
Hardware software co simulation of edge detection for image processing system...
 
H43044145
H43044145H43044145
H43044145
 

Similar to False colouring

Denoising autoencoder by Harish.R
Denoising autoencoder by Harish.RDenoising autoencoder by Harish.R
Denoising autoencoder by Harish.R
HARISH R
 
Color Detection & Segmentation based Invisible Cloak
Color Detection & Segmentation based Invisible CloakColor Detection & Segmentation based Invisible Cloak
Color Detection & Segmentation based Invisible Cloak
Aviral Chaurasia
 
Hand gestures recognition seminar_ppt.pptx.pdf
Hand gestures recognition seminar_ppt.pptx.pdfHand gestures recognition seminar_ppt.pptx.pdf
Hand gestures recognition seminar_ppt.pptx.pdf
SwathiSoman5
 
Evolving Comprehensible Neural Network Trees
Evolving Comprehensible Neural Network TreesEvolving Comprehensible Neural Network Trees
Evolving Comprehensible Neural Network Trees
Amr Kamel Deklel
 
Image De-Noising Using Deep Neural Network
Image De-Noising Using Deep Neural NetworkImage De-Noising Using Deep Neural Network
Image De-Noising Using Deep Neural Network
aciijournal
 
Hand Written Digit Classification
Hand Written Digit ClassificationHand Written Digit Classification
Hand Written Digit Classification
ijtsrd
 
Sign Detection from Hearing Impaired
Sign Detection from Hearing ImpairedSign Detection from Hearing Impaired
Sign Detection from Hearing Impaired
IRJET Journal
 
AI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
AI Class Topic 6: Easy Way to Learn Deep Learning AI TechnologiesAI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
AI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
Value Amplify Consulting
 
Plant Disease Detection using Convolution Neural Network (CNN)
Plant Disease Detection using Convolution Neural Network (CNN)Plant Disease Detection using Convolution Neural Network (CNN)
Plant Disease Detection using Convolution Neural Network (CNN)
IRJET Journal
 
IRJET-Multiclass Classification Method Based On Deep Learning For Leaf Identi...
IRJET-Multiclass Classification Method Based On Deep Learning For Leaf Identi...IRJET-Multiclass Classification Method Based On Deep Learning For Leaf Identi...
IRJET-Multiclass Classification Method Based On Deep Learning For Leaf Identi...
IRJET Journal
 
Devanagari Digit and Character Recognition Using Convolutional Neural Network
Devanagari Digit and Character Recognition Using Convolutional Neural NetworkDevanagari Digit and Character Recognition Using Convolutional Neural Network
Devanagari Digit and Character Recognition Using Convolutional Neural Network
IRJET Journal
 
Lab 6 Neural Network
Lab 6 Neural NetworkLab 6 Neural Network
Lab 6 Neural NetworkKyle Villano
 
Image De-Noising Using Deep Neural Network
Image De-Noising Using Deep Neural NetworkImage De-Noising Using Deep Neural Network
Image De-Noising Using Deep Neural Network
aciijournal
 
IMAGE DE-NOISING USING DEEP NEURAL NETWORK
IMAGE DE-NOISING USING DEEP NEURAL NETWORKIMAGE DE-NOISING USING DEEP NEURAL NETWORK
IMAGE DE-NOISING USING DEEP NEURAL NETWORK
aciijournal
 
Corrosion Detection Using A.I : A Comparison of Standard Computer Vision Tech...
Corrosion Detection Using A.I : A Comparison of Standard Computer Vision Tech...Corrosion Detection Using A.I : A Comparison of Standard Computer Vision Tech...
Corrosion Detection Using A.I : A Comparison of Standard Computer Vision Tech...
csandit
 
CORROSION DETECTION USING A.I. : A COMPARISON OF STANDARD COMPUTER VISION TEC...
CORROSION DETECTION USING A.I. : A COMPARISON OF STANDARD COMPUTER VISION TEC...CORROSION DETECTION USING A.I. : A COMPARISON OF STANDARD COMPUTER VISION TEC...
CORROSION DETECTION USING A.I. : A COMPARISON OF STANDARD COMPUTER VISION TEC...
cscpconf
 
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_ReportSaptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_ReportSitakanta Mishra
 
Ann model and its application
Ann model and its applicationAnn model and its application
Ann model and its application
milan107
 

Similar to False colouring (20)

Denoising autoencoder by Harish.R
Denoising autoencoder by Harish.RDenoising autoencoder by Harish.R
Denoising autoencoder by Harish.R
 
Color Detection & Segmentation based Invisible Cloak
Color Detection & Segmentation based Invisible CloakColor Detection & Segmentation based Invisible Cloak
Color Detection & Segmentation based Invisible Cloak
 
Hand gestures recognition seminar_ppt.pptx.pdf
Hand gestures recognition seminar_ppt.pptx.pdfHand gestures recognition seminar_ppt.pptx.pdf
Hand gestures recognition seminar_ppt.pptx.pdf
 
Evolving Comprehensible Neural Network Trees
Evolving Comprehensible Neural Network TreesEvolving Comprehensible Neural Network Trees
Evolving Comprehensible Neural Network Trees
 
Image De-Noising Using Deep Neural Network
Image De-Noising Using Deep Neural NetworkImage De-Noising Using Deep Neural Network
Image De-Noising Using Deep Neural Network
 
Hand Written Digit Classification
Hand Written Digit ClassificationHand Written Digit Classification
Hand Written Digit Classification
 
Som paper1.doc
Som paper1.docSom paper1.doc
Som paper1.doc
 
Sign Detection from Hearing Impaired
Sign Detection from Hearing ImpairedSign Detection from Hearing Impaired
Sign Detection from Hearing Impaired
 
neuralAC
neuralACneuralAC
neuralAC
 
AI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
AI Class Topic 6: Easy Way to Learn Deep Learning AI TechnologiesAI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
AI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
 
Plant Disease Detection using Convolution Neural Network (CNN)
Plant Disease Detection using Convolution Neural Network (CNN)Plant Disease Detection using Convolution Neural Network (CNN)
Plant Disease Detection using Convolution Neural Network (CNN)
 
IRJET-Multiclass Classification Method Based On Deep Learning For Leaf Identi...
IRJET-Multiclass Classification Method Based On Deep Learning For Leaf Identi...IRJET-Multiclass Classification Method Based On Deep Learning For Leaf Identi...
IRJET-Multiclass Classification Method Based On Deep Learning For Leaf Identi...
 
Devanagari Digit and Character Recognition Using Convolutional Neural Network
Devanagari Digit and Character Recognition Using Convolutional Neural NetworkDevanagari Digit and Character Recognition Using Convolutional Neural Network
Devanagari Digit and Character Recognition Using Convolutional Neural Network
 
Lab 6 Neural Network
Lab 6 Neural NetworkLab 6 Neural Network
Lab 6 Neural Network
 
Image De-Noising Using Deep Neural Network
Image De-Noising Using Deep Neural NetworkImage De-Noising Using Deep Neural Network
Image De-Noising Using Deep Neural Network
 
IMAGE DE-NOISING USING DEEP NEURAL NETWORK
IMAGE DE-NOISING USING DEEP NEURAL NETWORKIMAGE DE-NOISING USING DEEP NEURAL NETWORK
IMAGE DE-NOISING USING DEEP NEURAL NETWORK
 
Corrosion Detection Using A.I : A Comparison of Standard Computer Vision Tech...
Corrosion Detection Using A.I : A Comparison of Standard Computer Vision Tech...Corrosion Detection Using A.I : A Comparison of Standard Computer Vision Tech...
Corrosion Detection Using A.I : A Comparison of Standard Computer Vision Tech...
 
CORROSION DETECTION USING A.I. : A COMPARISON OF STANDARD COMPUTER VISION TEC...
CORROSION DETECTION USING A.I. : A COMPARISON OF STANDARD COMPUTER VISION TEC...CORROSION DETECTION USING A.I. : A COMPARISON OF STANDARD COMPUTER VISION TEC...
CORROSION DETECTION USING A.I. : A COMPARISON OF STANDARD COMPUTER VISION TEC...
 
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_ReportSaptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
 
Ann model and its application
Ann model and its applicationAnn model and its application
Ann model and its application
 

More from GauravBiswas9

SPARK ARCHITECTURE
SPARK ARCHITECTURESPARK ARCHITECTURE
SPARK ARCHITECTURE
GauravBiswas9
 
Spark architecture
Spark architectureSpark architecture
Spark architecture
GauravBiswas9
 
WCDMA
WCDMA WCDMA
Ofdm
OfdmOfdm
2.5G Cellular Standards
2.5G Cellular Standards2.5G Cellular Standards
2.5G Cellular Standards
GauravBiswas9
 
Map reduce in BIG DATA
Map reduce in BIG DATAMap reduce in BIG DATA
Map reduce in BIG DATA
GauravBiswas9
 
Iot in healthcare
Iot in healthcareIot in healthcare
Iot in healthcare
GauravBiswas9
 
Gsm vs gprs
Gsm vs gprsGsm vs gprs
Gsm vs gprs
GauravBiswas9
 
Circuit switch vs packet switch
Circuit switch vs packet switchCircuit switch vs packet switch
Circuit switch vs packet switch
GauravBiswas9
 
Channelization scheme in AMPS & GSM
Channelization scheme in AMPS & GSMChannelization scheme in AMPS & GSM
Channelization scheme in AMPS & GSM
GauravBiswas9
 
Big data analytics.
Big data analytics.Big data analytics.
Big data analytics.
GauravBiswas9
 

More from GauravBiswas9 (11)

SPARK ARCHITECTURE
SPARK ARCHITECTURESPARK ARCHITECTURE
SPARK ARCHITECTURE
 
Spark architecture
Spark architectureSpark architecture
Spark architecture
 
WCDMA
WCDMA WCDMA
WCDMA
 
Ofdm
OfdmOfdm
Ofdm
 
2.5G Cellular Standards
2.5G Cellular Standards2.5G Cellular Standards
2.5G Cellular Standards
 
Map reduce in BIG DATA
Map reduce in BIG DATAMap reduce in BIG DATA
Map reduce in BIG DATA
 
Iot in healthcare
Iot in healthcareIot in healthcare
Iot in healthcare
 
Gsm vs gprs
Gsm vs gprsGsm vs gprs
Gsm vs gprs
 
Circuit switch vs packet switch
Circuit switch vs packet switchCircuit switch vs packet switch
Circuit switch vs packet switch
 
Channelization scheme in AMPS & GSM
Channelization scheme in AMPS & GSMChannelization scheme in AMPS & GSM
Channelization scheme in AMPS & GSM
 
Big data analytics.
Big data analytics.Big data analytics.
Big data analytics.
 

Recently uploaded

Hybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdf
Hybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdfHybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdf
Hybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdf
fxintegritypublishin
 
Architectural Portfolio Sean Lockwood
Architectural Portfolio Sean LockwoodArchitectural Portfolio Sean Lockwood
Architectural Portfolio Sean Lockwood
seandesed
 
Forklift Classes Overview by Intella Parts
Forklift Classes Overview by Intella PartsForklift Classes Overview by Intella Parts
Forklift Classes Overview by Intella Parts
Intella Parts
 
DESIGN A COTTON SEED SEPARATION MACHINE.docx
DESIGN A COTTON SEED SEPARATION MACHINE.docxDESIGN A COTTON SEED SEPARATION MACHINE.docx
DESIGN A COTTON SEED SEPARATION MACHINE.docx
FluxPrime1
 
weather web application report.pdf
weather web application report.pdfweather web application report.pdf
weather web application report.pdf
Pratik Pawar
 
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)
MdTanvirMahtab2
 
Vaccine management system project report documentation..pdf
Vaccine management system project report documentation..pdfVaccine management system project report documentation..pdf
Vaccine management system project report documentation..pdf
Kamal Acharya
 
Water Industry Process Automation and Control Monthly - May 2024.pdf
Water Industry Process Automation and Control Monthly - May 2024.pdfWater Industry Process Automation and Control Monthly - May 2024.pdf
Water Industry Process Automation and Control Monthly - May 2024.pdf
Water Industry Process Automation & Control
 
TECHNICAL TRAINING MANUAL GENERAL FAMILIARIZATION COURSE
TECHNICAL TRAINING MANUAL   GENERAL FAMILIARIZATION COURSETECHNICAL TRAINING MANUAL   GENERAL FAMILIARIZATION COURSE
TECHNICAL TRAINING MANUAL GENERAL FAMILIARIZATION COURSE
DuvanRamosGarzon1
 
Standard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - NeometrixStandard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - Neometrix
Neometrix_Engineering_Pvt_Ltd
 
power quality voltage fluctuation UNIT - I.pptx
power quality voltage fluctuation UNIT - I.pptxpower quality voltage fluctuation UNIT - I.pptx
power quality voltage fluctuation UNIT - I.pptx
ViniHema
 
Automobile Management System Project Report.pdf
Automobile Management System Project Report.pdfAutomobile Management System Project Report.pdf
Automobile Management System Project Report.pdf
Kamal Acharya
 
addressing modes in computer architecture
addressing modes  in computer architectureaddressing modes  in computer architecture
addressing modes in computer architecture
ShahidSultan24
 
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
bakpo1
 
Quality defects in TMT Bars, Possible causes and Potential Solutions.
Quality defects in TMT Bars, Possible causes and Potential Solutions.Quality defects in TMT Bars, Possible causes and Potential Solutions.
Quality defects in TMT Bars, Possible causes and Potential Solutions.
PrashantGoswami42
 
Democratizing Fuzzing at Scale by Abhishek Arya
Democratizing Fuzzing at Scale by Abhishek AryaDemocratizing Fuzzing at Scale by Abhishek Arya
Democratizing Fuzzing at Scale by Abhishek Arya
abh.arya
 
Planning Of Procurement o different goods and services
Planning Of Procurement o different goods and servicesPlanning Of Procurement o different goods and services
Planning Of Procurement o different goods and services
JoytuBarua2
 
Top 10 Oil and Gas Projects in Saudi Arabia 2024.pdf
Top 10 Oil and Gas Projects in Saudi Arabia 2024.pdfTop 10 Oil and Gas Projects in Saudi Arabia 2024.pdf
Top 10 Oil and Gas Projects in Saudi Arabia 2024.pdf
Teleport Manpower Consultant
 
Student information management system project report ii.pdf
Student information management system project report ii.pdfStudent information management system project report ii.pdf
Student information management system project report ii.pdf
Kamal Acharya
 
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
 

Recently uploaded (20)

Hybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdf
Hybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdfHybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdf
Hybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdf
 
Architectural Portfolio Sean Lockwood
Architectural Portfolio Sean LockwoodArchitectural Portfolio Sean Lockwood
Architectural Portfolio Sean Lockwood
 
Forklift Classes Overview by Intella Parts
Forklift Classes Overview by Intella PartsForklift Classes Overview by Intella Parts
Forklift Classes Overview by Intella Parts
 
DESIGN A COTTON SEED SEPARATION MACHINE.docx
DESIGN A COTTON SEED SEPARATION MACHINE.docxDESIGN A COTTON SEED SEPARATION MACHINE.docx
DESIGN A COTTON SEED SEPARATION MACHINE.docx
 
weather web application report.pdf
weather web application report.pdfweather web application report.pdf
weather web application report.pdf
 
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)
 
Vaccine management system project report documentation..pdf
Vaccine management system project report documentation..pdfVaccine management system project report documentation..pdf
Vaccine management system project report documentation..pdf
 
Water Industry Process Automation and Control Monthly - May 2024.pdf
Water Industry Process Automation and Control Monthly - May 2024.pdfWater Industry Process Automation and Control Monthly - May 2024.pdf
Water Industry Process Automation and Control Monthly - May 2024.pdf
 
TECHNICAL TRAINING MANUAL GENERAL FAMILIARIZATION COURSE
TECHNICAL TRAINING MANUAL   GENERAL FAMILIARIZATION COURSETECHNICAL TRAINING MANUAL   GENERAL FAMILIARIZATION COURSE
TECHNICAL TRAINING MANUAL GENERAL FAMILIARIZATION COURSE
 
Standard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - NeometrixStandard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - Neometrix
 
power quality voltage fluctuation UNIT - I.pptx
power quality voltage fluctuation UNIT - I.pptxpower quality voltage fluctuation UNIT - I.pptx
power quality voltage fluctuation UNIT - I.pptx
 
Automobile Management System Project Report.pdf
Automobile Management System Project Report.pdfAutomobile Management System Project Report.pdf
Automobile Management System Project Report.pdf
 
addressing modes in computer architecture
addressing modes  in computer architectureaddressing modes  in computer architecture
addressing modes in computer architecture
 
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
 
Quality defects in TMT Bars, Possible causes and Potential Solutions.
Quality defects in TMT Bars, Possible causes and Potential Solutions.Quality defects in TMT Bars, Possible causes and Potential Solutions.
Quality defects in TMT Bars, Possible causes and Potential Solutions.
 
Democratizing Fuzzing at Scale by Abhishek Arya
Democratizing Fuzzing at Scale by Abhishek AryaDemocratizing Fuzzing at Scale by Abhishek Arya
Democratizing Fuzzing at Scale by Abhishek Arya
 
Planning Of Procurement o different goods and services
Planning Of Procurement o different goods and servicesPlanning Of Procurement o different goods and services
Planning Of Procurement o different goods and services
 
Top 10 Oil and Gas Projects in Saudi Arabia 2024.pdf
Top 10 Oil and Gas Projects in Saudi Arabia 2024.pdfTop 10 Oil and Gas Projects in Saudi Arabia 2024.pdf
Top 10 Oil and Gas Projects in Saudi Arabia 2024.pdf
 
Student information management system project report ii.pdf
Student information management system project report ii.pdfStudent information management system project report ii.pdf
Student information management system project report ii.pdf
 
Nuclear Power Economics and Structuring 2024
Nuclear Power Economics and Structuring 2024Nuclear Power Economics and Structuring 2024
Nuclear Power Economics and Structuring 2024
 

False colouring

  • 1. PRESENTED BY:- GAURAV BISWAS BIT MESRA DEEP LEARNINGTECHNIQUES FOR FALSE COLOURING OF SATELLITE IMAGES
  • 2.  ABSTRACT  INTRODUCTION  USED DATASET  PLATFORM AND LANGUAGE USED  RESEARCH METHODOLOGY  IMPLEMENTATION  RESULT AND DISCUSSION  CODES  CONCLUSIONs  FUTURE SCOPE  REFERENCEs CONTENTS
  • 3.  Our intention is to use the technique of false colouring to recolourize remote sensing images.  Recolourizing an image is an extremely difficult task and an acceptable recolourizing often not feasible without some prior knowledge.  For this we are using three techniques:- (a) Convolutional Neural Network (CNN) (b) Autoencoders and (c) Variational Autoencoders (VAE) ABSTRACT
  • 4.  False colour refers to a group of colour rendering methods used to display images in colour which were recorded in the visible or non- visible parts. INTRODUCTION
  • 5. Satellite images are downloaded from Kaggle. We used MNIST dataset as well as Cat-Dog dataset from Kaggle for checking.  Out of 25000 images we split the dataset into two parts i.e- training and testing part. All blurred and noisy image datasets are inputs for our different techniques i.e- Autoencoders, Variational Autoencoders and Convolutional Neural Network USED DATASET
  • 6. PLATFORMANDLANGUAGE USED For this project we use Anaconda Navigator. It is a desktop graphical user interface (GUI). Under Anaconda Navigator we use- Jupyter Notebook Spyder Language used is python programming.
  • 7.  Using a Convolutional Neural Network (CNN) techniques for implementing deep neural networks in remote sensing image and try to get the accuracy.  Provide the satellite image dataset as an input.  We have to use Autoencoders and Variational Autoencoders (VAE) to train the Satellite images and check the accuracy of these approaches.  Convert the Satellite Images (Black & White) into a false colour image using these three approaches.  Then train this images into a proper approach of deep learning techniques and try to get more classified image as an output. RESEARCH METHODOLOGY
  • 8. (A) Convolutional Neural Network:  In deep learning, a convolutional neural network is a class of deep neural networks, most commonly applied to analyzing visual imagery.  They are regularized versions of multilayer perceptrons. It usually mean fully connected networks, that is, each neuron in one layer is connected to all neurons in the next layer.  Here’s an example of a convolutional neural network: RESEARCH METHODOLOGY output
  • 9. ACCURACYOF CONVOLUTIONALNEURAL NETWORK It is clearly seen that the Accuracy for Convolutional Neural Network (CNN) is 92%. In this model we train our dataset into 50 epoche and finally get this accuracy.
  • 10. OUTPUTOFCONVOLUTIONALNEURAL NETWORK Figure - After performing False colouring using CNN technique
  • 11. CODES The code of the Convolutional Neural Network in jupyter notebook as below First we have to select the model, here we are selecting sequential then we are adding hidden layers to it and in the last layer we are using softmax as the activation function.
  • 12. Next, we add a 2D CNN layer to process the dataset input images. First argument passed to the 2D layer function is the number of the output channels here we use 32 output channels. Now we use flatten i.e. merge after pooling CONTD…
  • 13. Now we want to train our model and then getting the output after 50 epoch. CONTD…
  • 15. (B) Autoencoders:  An autoencoder is a type of artificial neural network used to learn efficient data in an unsupervised manner.  The aim of an autoencoder is to learn a representation for a set of data, typically for dimensionality reduction, by training the network to ignore signal “noise”. RESEARCH METHODOLOGY
  • 16. IMPLEMENTATIONOFAUTOENCODERS For implementing this technique we are using Sequential model in keras which is used most of the time. Next we have to split our dataset into our training and test data. Added our first layer with 32 neurons and activation function ReLU. In this case the input and output is same, we only care about the bottleneck part. Add second layer with same configuration and from bottleneck we have to decode it to get the proper output. Added a fully connected Dense layer Add an output layer that uses softmax activation for the no of classes.
  • 17. ACCURACYOF AUTOENCODERS Here we can clearly see that the variational loss is about 0.10 and the accuracy is 90%. Here in this techniques we doesn’t care about the input it is just the replica of the output we just care about the bottleneck part from that part we decode it and gets the proper output.
  • 18. OUTPUTOF AUTOENCODER Figure - After performing False colouring using Autoencoder technique
  • 19. CODES The code of the Autoencoder in jupyter notebook as below
  • 21. Now let's train our autoencoder for 50 epochs CONTD…
  • 22. (C) Variational autoencoder:  Just as a standard autoencoder, a variational autoencoder is an architecture composed of both an encoder and a decoder and that is trained to minimize the reconstruction error between the encoded-decoded data and the initial data. RESEARCH METHODOLOGY
  • 23. ACCURACYOF VARIATIONAL AUTOENCODERS (VAE) It is clearly seen that the Accuracy for Variational Autoencoder is 92%. In this case we have to take mean and variance and from that we have to decode it to get the proper output. The VAE output is more clear compared to the Autoencoders.
  • 24. IMPLEMENTATIONOF VARIATIONAL AUTOENCODERS(VAE) For implementing this technique we are using Sequential model in keras which is used most of the time. Next we have to split our dataset into our training and test data. Added our first layer with 32 neurons and activation function ReLU. In this case also the input and output is same, but after bottleneck part we have to take the mean and variance and from that we to decode it to get the output. Add second layer with same configuration Added a fully connected Dense layer. Add an output layer that uses softmax activation for the no of classes.
  • 25. OUTPUTOF VARIATIONALAUTOENCODER(VAE) Figure -After performing False colouring using Variational Autoencoder (VAE) technique
  • 26. CODES We perform the Variational Autoencoders means we run the VAE code in the Google Colab platform the code is as below. Firstly here is our encoder network Then we can use the parameters to the sample new similar points
  • 28. We train our dataset Our latent space is of two dimensional so there are few cool visualizations which have to be done at this point. CONTD…
  • 29. As we all know that the VAE is a generative model we also use it for generating new dataset CONTD…
  • 30.  Using CNN to train Satellite Images for False Colouring.  But due to large size of the image the neural network may not gives the proper output for this we have to use net graph.  We also use metrics to check whether the colouring is proper or not.  In our project the accuracy for Autoencoder is near about 90% and for Variational Autoencoder it is coming 92%. CONCLUSIONS
  • 31. FUTURE SCOPE Any deep learning application that we are using has big scope in future and in our project we have trained our satellite image dataset with three different approaches. To get more accuracy we need to train our satellite images in Hybridization approach so that our images can create more uniformality to the colours found in images.
  • 32. [1] NASA’s Earth Observatory. How to interpret a Satellite Image. K. Aardal, S. van Hoesel, A. Koster, C. Mannino, Models and solution techniques. [2] S. Alouf, J. Galtier, C. Touati, MFTDMA satellites, in INFOCOM 2005, 24th Annual Joint Conference of the IEEE, in Proceedings IEEE, 2005 [3] D. Kingma, Auto-Encoding Variational Bayes of the IEEE, ICLR, 2014 [4] Xinchen Yan, Jimei Yang, Kihyuk Sohn, Honglak Lee, Attribute2Image: Conditional Image Generation from Visual Attributes IEEE, ECCV, 2016 [5] http://earthobservatory.nasa.gov/Features/FalseColor/page6.php [6] https://ieeexplore.ieee.org/document/861379/keywords#keywords REFERENCES