SlideShare a Scribd company logo
Image Classification
using deep learning
Done By :
Asma Hawari - Qamar AL-Zaman Hafez - Amena Samra - Nader Pervis
CIFR10
It’s mini-images dataset
Consists of 60000 images
Split into 50000 training and
10000 testing
2
CIFR 10 Dataset
3
“ There are thousands of solutions
for this problem and we tried many
to increase the test accuracy .”
4
Preprocessing Data &
Normalization
1. Convert from uint8 to float32
2. Scale the images values to range 0-1
3. Apply OneHotEncoding to the Labels
Train Neural Network from scratch
First we try AlexNet Neural Network
7
AlexNet Architecture
 11*11 kernel size
 5 convolutional layers
 3 fully connected layers
CNN
Convolutional Neural Network
But why CNN Not MLP ?
8
9
CNN Architecture
10
Convolution Operation with kernel size 3*3
11
CNNs learn Hierarchical features
As we go deeper into the network , the neurons get
information from larger parts of the image and from various
other neurons
The neurons at the later layers can learn more complicated
features like eyes / legs
12
Max Pooling :
Pooling layers is mostly used immediately after the
convolutional layer to reduce the spatial size (only width and
height , not depth ) .
This reduces the number of parameters to avoid Overfitting
13
Dropout Layer :
avoid Overfitting by putting Dropout Layer after each Max-
Pooling Layer
14
ReLu ( Rectified Linear Unit ) as Activation Function :
ReLu function is zero when z is less than zero and f(z) is
equal to z when z is above or equal to zero
15
Visualize The Model
What is the CNN result ?
▫ This solution return 78% accuracy which is not bad but
there was Overfitting
16
What is Data Augmentation ?
▫ Rotation of the image , shifting left/right/top/bottom
by some amount , flip the image horizontally or
vertically , zoom ..etc.
17
What is the CNN result ?
▫ To solve the Overfitting Problem we did
DATA AUGMENTATION and it solved the problem !!!
Accuracy is 79.57%
18
Transfer
Learning
What is transfer learning ?
19
To use already trained models on very large amounts of data for
difficult tasks with thousands of classes that research group share in
the competitions like ILSVRC and ImageNet
Transfer Learning
20
Pre-trained Models on :
ImageNet
It contains more than 14 million
images belong to more than
20,000 classes
ILSVRC
ImageNet Large Scale Visual
Recognition Challenge to
evaluate their computer vision
algorithms
The training data subset of
ImageNet 1.2 million images
belong to 1000 class
21
Why Use Pre-trained
Models ?
22
Why Use Pre-trained Models ?
23
20XX
We need powerful GPUs
20XX
It takes a large amount of time
to train the network
20XX
To finding all the unknown
parameters we need a lot of data
20XX
Deep networks have large
number of unknown parameters.
This network is characterized by its simplicity , using only 3*3
convolutional layers stacked on top of each other in increasing depth
VGG16 -VGG19
24
GoogleNet Or InceptionV3
25
The goal of the inception module is to act as a “multi-level feature
extractor “ by computing 1*1 , 3*3 and 5*5 convolutions within the
same module of the network .
The output of these filters are then stacked along the channel
dimensions and before being fed into the next layer in the network
GoogleNet Or InceptionV3
26
What is Vanishing Gradient Problem ?
27
This problem makes it really hard to learn and tune the parameters
of the earlier layers in the network , and it’s becomes worse as the
number of layers in the architectures increase .
ResNet
28
This architecture solved Vanishing gradient problem by identity
mapping
OUR PROCESS IS
29
STEP 3
compare the results
STEP 1
Extract features from The
pre-trained models (VGG16 &
VGG19 & InceptionV3 &
ResNet)
STEP 2
Fine-tuning the parameters
By trying to build LinearSVC
classifier with many possible C
Extract Features
30
Visualze our Features by PCA
31
Fine Tuning The SVM Parameters
32
The Result is
33
91,58
Whoa! That’s a big number, aren’t you proud?
34
83,45
KNN
100%
Total success!
90,37
Logistic Regression
35
36
THANKS!
Any questions?

More Related Content

PPTX
Deep learning presentation
PPTX
Pulse Modulation ppt
PPTX
Image classification using CNN
PPTX
Convolution Neural Network (CNN)
PPTX
Introduction to CNN
PPTX
Data Augmentation
PPTX
Noise
PPTX
Image classification using convolutional neural network
Deep learning presentation
Pulse Modulation ppt
Image classification using CNN
Convolution Neural Network (CNN)
Introduction to CNN
Data Augmentation
Noise
Image classification using convolutional neural network

What's hot (20)

PPTX
Image classification with Deep Neural Networks
PDF
An introduction to Deep Learning
PDF
Convolutional Neural Network Models - Deep Learning
PPTX
CNN Machine learning DeepLearning
PPTX
Convolutional neural network
PPTX
Introduction to Deep Learning
PDF
Generative adversarial networks
PDF
Deep learning for image video processing
PPTX
Convolutional Neural Network
PPTX
CNN Tutorial
PPTX
Convolutional Neural Network (CNN)
PPTX
cnn ppt.pptx
PPTX
Image classification using cnn
PPTX
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...
PDF
Neural Networks: Multilayer Perceptron
PDF
Convolutional Neural Networks (CNN)
PPT
Neural Networks
PPT
Deep learning ppt
PPTX
Convolutional Neural Network and Its Applications
PPTX
Lecture 29 Convolutional Neural Networks - Computer Vision Spring2015
Image classification with Deep Neural Networks
An introduction to Deep Learning
Convolutional Neural Network Models - Deep Learning
CNN Machine learning DeepLearning
Convolutional neural network
Introduction to Deep Learning
Generative adversarial networks
Deep learning for image video processing
Convolutional Neural Network
CNN Tutorial
Convolutional Neural Network (CNN)
cnn ppt.pptx
Image classification using cnn
Convolutional Neural Network - CNN | How CNN Works | Deep Learning Course | S...
Neural Networks: Multilayer Perceptron
Convolutional Neural Networks (CNN)
Neural Networks
Deep learning ppt
Convolutional Neural Network and Its Applications
Lecture 29 Convolutional Neural Networks - Computer Vision Spring2015
Ad

Similar to Image Classification using deep learning (20)

PDF
ImageNet Classification with Deep Convolutional Neural Networks
PPT
lec6a.ppt
PPTX
adlkchiuabcndjhvkajnfdkjhcfatgcbajkbcyudfctauygb
PPTX
Tìm hiểu về CNN và ResNet | Computer Vision
PPTX
Introduction to Convolutional Neural Networks
PPTX
Deep Learning for Image Processing on 16 June 2025 MITS.pptx
PPTX
Introduction to Convolutional Neural Networks (CNNs).pptx
PPTX
Convolutional neural networks 이론과 응용
PPTX
IMAGE CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORK.P.pptx
PPTX
DL-CO2-Session6-VGGNet_GoogLeNet_ResNet_DenseNet_RCNN.pptx
PDF
Deep learning-practical
PDF
Unit 5: Convolutional Neural Networks - CNN
PDF
Modern Convolutional Neural Network techniques for image segmentation
PDF
深度學習在AOI的應用
PPTX
Computer Vision for Beginners
PPTX
Waste Classification System using Convolutional Neural Networks.pptx
PPTX
Mnist report ppt
PDF
Mnist report
PDF
cnn.pdf
ImageNet Classification with Deep Convolutional Neural Networks
lec6a.ppt
adlkchiuabcndjhvkajnfdkjhcfatgcbajkbcyudfctauygb
Tìm hiểu về CNN và ResNet | Computer Vision
Introduction to Convolutional Neural Networks
Deep Learning for Image Processing on 16 June 2025 MITS.pptx
Introduction to Convolutional Neural Networks (CNNs).pptx
Convolutional neural networks 이론과 응용
IMAGE CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORK.P.pptx
DL-CO2-Session6-VGGNet_GoogLeNet_ResNet_DenseNet_RCNN.pptx
Deep learning-practical
Unit 5: Convolutional Neural Networks - CNN
Modern Convolutional Neural Network techniques for image segmentation
深度學習在AOI的應用
Computer Vision for Beginners
Waste Classification System using Convolutional Neural Networks.pptx
Mnist report ppt
Mnist report
cnn.pdf
Ad

Recently uploaded (20)

PPTX
20250228 LYD VKU AI Blended-Learning.pptx
PPTX
MYSQL Presentation for SQL database connectivity
PDF
Encapsulation_ Review paper, used for researhc scholars
PDF
Machine learning based COVID-19 study performance prediction
PDF
Advanced methodologies resolving dimensionality complications for autism neur...
PDF
Unlocking AI with Model Context Protocol (MCP)
PDF
Video forgery: An extensive analysis of inter-and intra-frame manipulation al...
PDF
Network Security Unit 5.pdf for BCA BBA.
PDF
Optimiser vos workloads AI/ML sur Amazon EC2 et AWS Graviton
PDF
Spectral efficient network and resource selection model in 5G networks
PPT
Teaching material agriculture food technology
PDF
Build a system with the filesystem maintained by OSTree @ COSCUP 2025
PDF
Architecting across the Boundaries of two Complex Domains - Healthcare & Tech...
PDF
Agricultural_Statistics_at_a_Glance_2022_0.pdf
PDF
Mobile App Security Testing_ A Comprehensive Guide.pdf
PDF
Profit Center Accounting in SAP S/4HANA, S4F28 Col11
PDF
Approach and Philosophy of On baking technology
PPTX
Group 1 Presentation -Planning and Decision Making .pptx
PPTX
KOM of Painting work and Equipment Insulation REV00 update 25-dec.pptx
PPTX
Spectroscopy.pptx food analysis technology
20250228 LYD VKU AI Blended-Learning.pptx
MYSQL Presentation for SQL database connectivity
Encapsulation_ Review paper, used for researhc scholars
Machine learning based COVID-19 study performance prediction
Advanced methodologies resolving dimensionality complications for autism neur...
Unlocking AI with Model Context Protocol (MCP)
Video forgery: An extensive analysis of inter-and intra-frame manipulation al...
Network Security Unit 5.pdf for BCA BBA.
Optimiser vos workloads AI/ML sur Amazon EC2 et AWS Graviton
Spectral efficient network and resource selection model in 5G networks
Teaching material agriculture food technology
Build a system with the filesystem maintained by OSTree @ COSCUP 2025
Architecting across the Boundaries of two Complex Domains - Healthcare & Tech...
Agricultural_Statistics_at_a_Glance_2022_0.pdf
Mobile App Security Testing_ A Comprehensive Guide.pdf
Profit Center Accounting in SAP S/4HANA, S4F28 Col11
Approach and Philosophy of On baking technology
Group 1 Presentation -Planning and Decision Making .pptx
KOM of Painting work and Equipment Insulation REV00 update 25-dec.pptx
Spectroscopy.pptx food analysis technology

Image Classification using deep learning