Image Classification using CNN

Presented by:

Student Name - Priya Mittal & Naveen Kumar

Roll No. – 2K16/EC/111 & 2K16/EP/035

Presented to: Dr. N. Jayanthi

 Introduction to CNN:
• In neural networks, Convolutional neural network (ConvNets or CNNs) is one of the main
categories to do images recognition, images classifications. Objects detections, recognition
faces etc., are some of the areas where CNNs are widely used.

• CNN image classifications takes an input image, process it and classify it under certain
categories (Eg., Dog, Cat, Tiger, Lion). Computers sees an input image as array of pixels
and it depends on the image resolution. Based on the image resolution, it will see h x w x d(
h = Height, w = Width, d = Dimension ). 

• Technically, deep learning CNN models to train and test, each input image will pass it
through a series of convolution layers with filters, Pooling, fully connected layers (FC) and
apply Softmax function to classify an object with probabilistic values between 0 and 1. The
below figure is a complete flow of CNN to process an input image and classifies the objects
based on values.
 Convolution Layer
• Convolution is the first layer to extract features from an input image. Convolution
preserves the relationship between pixels by learning image features using small
squares of input data. It is a mathematical operation that takes two inputs such as
image matrix and a filter or kernel.

• Consider a 5 x 5 whose image pixel values are 0, 1 and filter matrix 3 x 3 as shown in
below

• Then the convolution of 5 x 5 image matrix multiplies with 3 x 3 filter matrix which is
called “Feature Map” as output shown in below

• Convolution of an image with different filters can

perform operations such as edge detection, blur and
sharpen by applying filters. In this project what we
have done shows various convolution image after
applying different types of filters (Kernels).
 Problem Statement
 To build a model capable of classifying the images whether being of a cat or a
dog.

About the Dataset

 The 2,000 images used in this exercise are excerpted from the "Dogs vs. Cats"
dataset available on Kaggle, which contains 25,000 images. Here, we use a
subset of the full dataset to decrease training time for educational purposes. 
 Train folder = 1000 + 1000
Goal of Training data – To train the model
 Test  folder = 500 + 500
Goal of Test data – To verify the model

4
 Roadmap to the solution

Start Creating the CNN model

1 2
.
Extracting the dataset Preparing the data to be fitted to the
classifier model

4 3
Training the model and
checking the accuracy Plot the accuracy and loss graphs

5 6
If signs of over fitting, data
augmentation else go to step 6
 Understanding the code
1. Extracting the dataset

6
2. Importing the libraries

3. Creating the CNN model

4. Compiling the network

7
5. Preparing the data for the model

6. Training the network

8
7. Checking the results 

9
7. Improving the results by data augmentation

8. Model Summary
Results

10
2. Training, Validation Accuracy and Loss

11
 Applications in Real World
Facial recognition is broken down by a convolutional neural network into the following major components
-
Identifying every face in the picture
1 • Focusing on each face despite external factors, such as light, angle, pose, etc.
• Identifying unique features
• Comparing all the collected data with already existing data in the database to match a face with a
name
Convolutional neural networks can also be used for document analysis. This is not just useful for
2 handwriting
. analysis, but also has a major stake in recognizers. .

CNNs are also used for more complex purposes such as natural history collections. These collections act as
3 key players in documenting major parts of history such as biodiversity, evolution, habitat loss, biological
invasion, and climate change.

CNNs can be used to play a major role in the fight against climate change, especially in understanding the
4 reasons why we see such drastic changes and how we could experiment in curbing the effect.

Introduction of the grey area into CNNs is posed to provide a much more realistic picture of the real
5 world. Currently, CNNs largely function exactly like a machine, seeing a true and false value for every
question

12
 THANK YOU!

It is literally the case that learning

languages makes you smarter. The neural
networks in the brain strengthen as a result
of language learning.

~ Michael Gove
13