0% found this document useful (0 votes)
22 views11 pages

4 100593163merged

This document discusses the use of deep learning for image classification, highlighting its advantages over conventional methods plagued by accuracy issues. It examines various methodologies, including convolutional neural networks (CNNs), and explores applications in multiple fields. The authors present experimental results demonstrating the effectiveness of deep learning techniques in improving image classification accuracy.

Uploaded by

mohdsuhail00021
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
22 views11 pages

4 100593163merged

This document discusses the use of deep learning for image classification, highlighting its advantages over conventional methods plagued by accuracy issues. It examines various methodologies, including convolutional neural networks (CNNs), and explores applications in multiple fields. The authors present experimental results demonstrating the effectiveness of deep learning techniques in improving image classification accuracy.

Uploaded by

mohdsuhail00021
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 11

Title: Image classi cation using deep learning

Manuscript ID: IJST-2025-90


Type: Abstract
Keywords: Abstract,Introduction,A SIMPLE RvNNARCHITECTURE
Journal: Indian Journal of Science and Technology

Authors

1. Mohd Suhail (Primary author)


2. Shivam Kumar (Co-author)
3. Vaibhav Bansal (Corresponding author)

y
Abstract

l og
Image classi cation is just a way that will balance the visual dissimilarity between machines and humans, which will help the
computer to interpret an image in a way as humans perceive. Despite its rampant application in practice, the conventional

no
methodology has been plagued by numerous problems. Its accurate classi cation precision is highly and arti cially limited
while unsatisfactory results are yielded. Thus, deep learning has been put forward as a possible improvement to the

h
accuracy of the solution to challenges involving image classi cation. This article addresses fundamental principles related to

ec
picture classi cation employing deep learning, examines different methodologies for image classi cation, highlights the

T
bene ts associated with deep learning, and explores the diverse applications that utilize deep learning in the context of
image classi cation. Arti cial neural networks, computational learning, deep learning techniques, and visual categorization.

nd
ea
nc
cie
fS
lo
na
ur
n Jo
dia
In
Ind
ian
Jo
urn
al
of
Sc
ien
ce
an
dT
ec
hn
olo
gy
Image Classification Using Deep Learning

Mohd. Suhail , Shivam , Vaibhav Bansal


Student of M.C.A.GalgotiasUniversity

y
l og
Dr. Shambu Kumar Jha

no
Assistant Professor, Galgotias University

h
Plot No.-2, Sector-17A, Yamuna Expressway, Gautam Buddha

ec
Nagar,

T
Greater Noida, Uttar Pradesh, India

nd
ea
Abstract: Image classification is just a way Introduction:- As reported by the Internet
nc
that will balance the visual dissimilarity Data Center (IDC), the entirety of global data
between machines and humans, which will help It will add up to 45ZB by 2020. Much of it,
cie

the computer to interpret an image in a way as some 70%, will seem like images and videos.
humans perceive. From computer vision, big data can now be
fS

Despite its rampant application in practice, the extracted from these pictures and videos.
conventional methodology has been plagued by Computer vision is getting more and more
lo

numerous problems. Its accurate classification common these days in the picture classification
precision is highly and artificially limited while space. Since its development in the late 1950s,
na

unsatisfactory results are yielded. Thus, deep image classification has been widely used in
learning has been put forward as a possible
ur

numerous engineering fields, the medical


improvement to the accuracy of the solution to profession, human-car monitoring, fingerprint
Jo

challenges involving image classification. technology, disaster management, security,


This article addresses fundamental principles and so on.
n

related to picture classification employing deep


dia

learning, examines different methodologies for Classification is the systematic structuring and
image classification, highlights the benefits grouping of items based on its attributes. In an
In

associated with deep learning, and explores the attempt to bridge the perceptual chasm between
diverse applications that utilize deep learning in man and machine, image categorization is used
the context of image classification. to provide data that enables machine learning.
Artificial neural networks, computational
learning, deep learning techniques, and visual
categorization.
images is based can be generalized into four and thousands of images in datasets are used to
categories. train

1. Image classification using statistical


methods: This well-known statistical method is
based on the error-minimizing principle and
includes Bayesian and Markov models.

2. Image classification based on textures,

y
geographical traits, and traditional color

l og
schemes.

no
3. Image classification using shallow
learning.

h
ec
4. Deep learning powered categorization by
images.Machine learning is the standard

T
technique for classifying images. A feature

nd
extraction module in machine learning extracts
significant features such as edges and ea
texturessuggestion for categorizing
nc
5. In this work image classification using
deep learning is covered. For this task, the
cie

convolutional neural network architecture


AlexNet is used. For the purpose of
fS

classification, four images are taken from the


ImageNet database. Different experiments were
lo

conducted where the images had their portions


cut out of different areas. The results
na

demonstrate the applicability of deep learning’s


image classification capabilities in AlexNet and
ur

show its reliability.


Jo

The first task in image recognition is capturing


n

the picture using some image obtaining devices,


dia

and thereafter the picture data is processed to


and a module that does the classification using
the features extracted. However, there are
In

significant restrictions regarding how machine


learning may be used for the purpose of photo
classification. The technique can only extract a
specific set of features from the photos and
cannot use features that are not those which the
trained data.
The problem led to the development of the deep
learning methodology. Deep learning is a subset
It has the propensity to learn in its own
computational approach. By using deep
learning, a computer can identify words, sounds,
and images. To enable this learning, thousands
remove undesired data, carry out feature
extraction and filtering, and eventually image
classification by a machine learning
discrimination. As the applications of machine
vision in a variety of sectors continue to
expand, people can now quickly perform tasks
like image processing methods such as noise
reduction and feature extraction.

y
l og
Owing to the data-driven nature of the
analysim of ever-growing volumes of varying
data, transfer, and semi-supervised learning, as

no
well as the automated construction and

h
assessment of deep learning models using AI-

ec
driven methods, it is sometimes difficult to
overemphasize the role and significance of

T
artificial intelligence in this regard. It is no

nd
secret that AI-powered technologies are
establishing themselves in numerous areas of ea
human activity, and most researchers or
entrepreneurs claim that Every technology
nc
sector has its own ‘big expectation’, so the
artificial intelligence’s ‘big hope’ rests many
cie

perception and notion. Artificial Intelligence


has experienced its fair share of ups and downs,
fS

yet it is still considered the most promising


technology of our time. It is still intricate how
lo

AI-powered software applications stand in


various industries and whether any AI system
na

would suit every business model, so AI


adaptation isn’t that widespread, however,
ur

perception in regards to AI is ever developing


Jo

ever since ai came into those ears. coversa vast


amount of previously unseen technologies
which piqued interest around AI.
n
dia

It then processes the pixel values of each image


into an internal representation that would help
In

the classifier recognize patterns in


the input photographs.
There are several deep learning networks,
including the following: Convolutional neural
networks feature among the most widely used
deep learning techniques for image
classification. Since CNNs learn directly from
input images, handcrafted feature extraction is
no longer required in this technique. This offers
three benefits: sparsity of interactions, equal
representations, and parameters shared.
Another well-liked deep learning technique, vectors. To generate a structured prediction
particularly in voice and natural language across a variable size input structure, the same
processing, is the recurrent neural network set of weights is applied recursively over a
(RNN). RNN makes use of the network's structured input.
sequential data. Consider an RNN as a short-
term memory unit with input, output, and hidden A SIMPLE RvNNARCHITECTURE
layers (layers x, y).
Recursive Neural Network (RvNN) RvNN can
categorize an item using compositional We will now examine the use of Convolutional

y
encoding and generate predictions in a Neural Networks (CNNs) for picture

l og
hierarchical structure. categorization.
A CNN consists of many layers.

no
The process begins with an input image. 1. The convolutional layer is responsible

h
for transmitting data to the following layer.

ec
This generates a feature map through the
application of several filters, subsequent

T
2. The pooling layer pools a group of neurons
application of ReLU functions to augment non-
to one neuron in the next level.

nd
linearity, implementation of pooling layers for
each feature map, and transforming the images ea
into a singular elongated vector. The vector then 3. A fully connected layer where each neuron
gets input in a fully connected artificial neural in one layer is connected to every neuron of the
nc
network after flattening. Train the network by another layers.
using both forward and backward propagation. CNN uses many hidden layers, sometimes
cie

Repeat this process until the network is well- hundreds of them, to enable feature recognition.
defined and has feature detectors and learned The characteristics learned are somewhat more
fS

weights. complex at each successive layer.


Various approaches to image identification
lo

using CNN
na
ur
n Jo
dia
In
Let's take a closer look at how CNN is used for
picture categorization.

The first step in image classification is accepting


the incoming image and making sure it adheres to
the class description. them can be easily classified
by humans, but computers see them differently.

What we see

y
l og
h no
T ec
nd
ea
nc
cie

The output of the first convolution layer becomes


fS

the input for the second layer as the picture passes


through it. Each and every convolution layer will
lo

experience it.
na

What a computer see


ur

Instead of seeing an image, a computer sees an The convolution layer is inserted before the
Jo

array of pixels; for example, if an image has 200 nonlinear layer. In the nonlinear layer, an
by 200 pixels, the array's size is 200 by 200 activation function is added, which provides with
n

pixels, with 200 being width, 200 for height, nonlinear properties; otherwise, without this
dia

and 2 for RGB values feature, a network cannot be intensive or describe


come next. The computer the response variable.
In

searches for base level characteristics, such as


borders or curvature, in order to solve these
problems. Next to the nonlinear layer comes the pooling
layer. Width and height of the image apply to the
The picture is initially sent into the convolution execution of down sampling, thus reducing the
layer. The program then chooses a smaller matrix volume of an image.
known as a filter. Next, the filter generates
convolution. Multiplying the filter's value by the
pixel value is its task. Next, the total of all these
multiplications is calculated.
Once the layers above are complete, a fully Plotting this result will allow us to see that it
connected layer is added to which produces an N- shows 96% accuracy, which is a good result.
dimensional vector, where N is the number of
classes for which the model can pick to perform
the classification task. Adding the fully connected Literature review
layer does this.
Nurul Hazirah Indra and Mohd Azlan Abu (2019)
[1] used the TensorFlow framework to classify
To form a model, however important, it should
images using deep neural networks. Because

y
pass through various stages:
Python comes with TensorFlow, it was employed

l og
in this manner. Approximately thousands of
Model building is actually started with the object flowers were gathered, and five different

no
model = Sequential(). varieties were present, each with hundreds of
compose layers based on their model types.add photos. All of these data sets are trained by the

h
the type_layer function. DNN until the system recognizes every image, at

ec
Once sufficient numbers of layers are included, which point each image is classified. Their
the model is compiled. In addition to specifying accuracy rate was about 90%. Ram, S., &

T
an optimization algorithm, a loss function will Chauhan, K. (2018)

nd
need to be defined. Once developed, the model is
[2]
applied to a previously untouched data set and its
ea
effectiveness is measured. They used, in the article, a deep learning
nc
convolutional network based on keras and
After the training of the model is complete and it tesnsorflow with Python for the picture
cie

produces the correct outcome, the model may be categorization. Four different CNN structures on
saved.save("file_name"). The model applies in CPU systems were tested, as well as four
fS

reality. This step is termed as model evaluation, different combinations of classifiers and
meaning that the data can be evaluated using the activation systems
lo

model. - softmax, sigmoid classifiers, and Relu, Tanh


The model's accuracy after testing was 96%; the activation functions. They therefore defined
na

only issue was that it took the model around 50 parameters for image classification in Python,
minutes to display the 60 epochs. then created a CNN with two convolutional
ur

layers, fitted the created CNN to the image


Jo

dataset, trained it, and tested it and obtained


satisfactory accuracy. They then prepared an
image dataset with 10,000 images of dogs and
n
dia

cats, of which 8,000 were used for training and


2000 for testing. Misbah Naimuddin Panchbhai
and Dr. Vinayak Bharadi (2017)
In

[3] have suggested deep learning approach


known as image classification, where the neural
network is used to classify the image.
One can use Python programming language to Their work makes a contribution by comparing
test how efficiently the system distinguishes the performance of several classification
between images on both the GPU and CPU. For algorithms with a deep learning approach for
this, the system will take a picture either through multi-class picture classification. Additionally, it
a digital camera or fetch one from a database. It contributes by demonstrating how easy it is to
will make adjustments to each picture in apply the deep learning method.
preparation for the next stage. Techniques for
dimensionality reduction include those of block .
transition coding and histograms among others, Feng-Ping An and Jun-e-Liu (2019) [6] Wrote

y
feature extraction techniques. The authors used the research called "Image Classification

l og
the CUDA library for the GPU and used Python Algorithm based on Deep Learning – Kernel
and TensorFlow for the CPU. Their Function". This way of computer vision includes

no
performance evaluation covered a range of two tasks - first, the exact identification of
aspects such as accuracy and the time taken to pictures and then the extraction of features from

h
execute both for CPU and GPU. M. Neelima them. The course of action is introduced by

ec
and M. Manoj Krishna (2018). utilizing the sparse representation of the deep
learning network architecture. The main

T
advantage of using the representation is that it is

nd
an effective way of solving the function
[4] They used the architecture of AlexNet and approximation problem, which can be very
ea
the convolutional neural network for complicated.
categorization in order to classify pictures in the
nc
proposed system. They selected four test photos Build an adaptive approximation capable model
from their database, resized the photos to
with deep learning.
cie

different sizes corresponding to their respective


section sizes and ran the test. They educated the
Vijay Anand and M. MuthukrishnanRamprasath
fS

data in the network by providing a test image


and told the network about the result of that (2018) [7] proposed the use of convolutional
neural networks in classifying images. Toward
lo

particular image. And from this experiment,


they saw that photos were rightly identified, computer vision objectives, the system uses the
na

even for the portion of test images it shows deep learning algorithm. The system through
how deep learning the autonomous classification of images, makes
ur

algorithm is effective in image classification. use of CNN. Using it as a benchmark, MNIST


Jo

dataset enables the classification of gray-scale


W.N.A.Ismail, W. A. Ezat, and M. M.Desouky images. They achieved a result of 98% by
(2020) [5] In their study, the PASCAL VOC
n

training using CNN network data. The classifier


dataset's pictures were classified using a CNN
dia

model that had been pre-trained on image-net. training consists of four primary steps:
The deep learning CNN model's performance preprocessing the data, feature extraction,
In

was enhanced by the application of the transfer normalization of the data set, and SVM image
learning technique, which allowed for more classification. Xin Mingyuan and Wang Yong
accurate classification even with shorter (2019).
computation times and less hardware. Results
from the SVM technique, the region ranking
SVM method, and the super vector coding of
the local image descriptor approach were
compared with the acquired results.
[8] proposed a research effort known as the fine-tuning, a hybrid, and the CNN model with
Deep Convolution Neural Network-Based Image pre-training. The CNN model was passed
Classification Model. The research into the through the network after pre-training and fine-
backpropagation method provided a tuning the model, whereas in the hybrid
foundational basis for the training of a deep approach, patch-based feature extraction is
neural network intended to reach the maximum used. These methods provide efficiency with
span of minimal classification error. For this high performance and speed as their prime
experiment, they explored three approaches: advantages.

y
l og
Published by Leonardo da Vinci and Sumanth Reference Advantages
Roychowdhary, a research paper on "Image Mohd Azlan 1- An accuracy

no
classification using deep learning and prior Abu, Nurul of 90% was
knowledge" was only present in their 2019 work. Hazirah found .

h
Indra(2019) [1]

ec
[9] In their work, they brought historical Karan Chauhan, 1- A good
ShrwanRam(2018) [2] accuracy was

T
knowledge into deep learning methods by
found in
simply using semantic-based regularization.

nd
result.
ea 2- Model took
This method can be utilized for group very small
classification or as part of a learning process. amount of
nc
The CIFAR-10 dataset, which consists of time
60,000 images, formed the basis of their fo
cie

exploratory study. The training set was r training.


employed to train the models, while the test set Dr. Vinayak Bharadi, 1- The system
fS

provided results for classification. The two Misbah can measure


primary benefits of their proposed approach NaimuddinPanchbhai( accuracy of
lo

were the very low costs associated with test 2017) [3] classifying
classification and the impressively quick images on
na

training of collective knowledge—taking less CPU and


ur

than 6 minutes. GPU.


M Manoj Krishna, M 1- Images were
Jo

Neelima(2018) [4] classified


correctly for
n

even portion
dia

The CNN model was passed through the


network after pre-training and fine-tuning the of test
images.
In

model, whereas in the hybrid approach, patch-


based feature extraction is used. These methods W. A. Ezat, M 1- It shows the
MDesouky and N A simplicity of
provide efficiency with high performance and
Ismail(2020) [5] implementing deep
speed as their prime advantages
learning algorithm.
2- Comparison were
shown on the basis
of performance.
Jun-e-Liu, Feng-Ping 1- Approximatio
An(2019) [6] N problem of
complex
function was References:
solved.

Muthukrishnan 1- Good
1. Mohd Azlan Abu, Nurul HazirahIndra(2019)
Ramprasath, M. Vijay accuracy of
[1]- Image classification using deep neural
Anand(2018) [7] almost 98%
network.
Mingyuan Xin 1- Better
2. Karan Chauhan, ShrwanRam(2018) [2]-

y
and Yong spee

l og
Wang(2019) [8] d and Image classification using deep learning
performance based on keras and tensorflow.
3. Dr. Vinayak Bharadi, Misbah

no
Michelangelo 1- Collective
Diligenti, classification NaimuddinPanchbhai(2017) [3]- Image

h
Soumal shows classification using deep learning.

ec
iRoychowdhary(2019) improvement 4. M Manoj Krishna, M Neelima(2018) [4]-
[9] over Image classification using deep neural

T
individual network.

nd
classification 5. W. A. Ezat, M MDesouky and N A
. ea Ismail(2020) [5]- Image
2- Cost of classification using convolutional neural
collective network.
nc
classification 6. Jun-e-Liu, Feng-Ping An(2019) [6] Image
was
cie

Classification Algorithm based on Deep


negligible.
3- Error Learning – Kernel Function.
fS

7. MuthukrishnanRamprasath, M. Vijay
reduction was
larger than Anand(2018) [7]Image Classification using
lo

2.7%. Convolutional Neural Network.


4- Time 8. Mingyuan Xin and Yong Wang(2019) [8]
na

consumption Image Classification Model based on Deep


Convolution Neural Network.
ur

was very less.


9. Michelangelo Diligenti,
Jo

SoumaliRoychowdhary(2019) [9] Image


classification using deep learning and prior
n

knowledge.
dia

Conclusion:
After examining several approaches, it can be said 10. https://in.mathworks.com/matlabcent
that each strategy may have a few benefits over ral/fileexchange/59133-neural- network-
In

the others. For example, some strategies toolbox-tm--model-for- alexnet-network


demonstrate more accuracy than others, while 11. H. Lee, R. Grosse, R. Ranganath, and
some are more cost-effective. While there have A.Y. Ng. Convolutional deep belief
been significant advancements in picture networks for scalable unsupervised
categorization recently, there is always room for learning of hierarchical representations.
improvement.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy