SlideShare a Scribd company logo
HANDWRITTEN DIGIT RECOGNITION
Handwritten Digit Recognition Project
 PROBLEM STATMENT
The MNIST dataset of handwritten digits is widespread among
the data scientists and machine learning enthusiasts. It is an
amazing project to get started with the data science and
understand the processes involved in a project. The project is
implemented using the Convolutional Neural Networks and then
for real-time prediction we also build a nice graphical user
interface to draw digits on a canvas and then the model will
predict the digit."
OBJECTIVES:
MNIST data set :
It is a large data collection of handwritten digits used to train and
test various supervised machine learning algorithms.
Tenserflow :
TensorFlow is a free and open-source software library for machine
learning and artificial intelligence. It can be used across a range of tasks but has
a particular focus on training and inference of deep neural networks.
Convolutional Neural Networks(CNN) :
Convolutional Neural Networks are a type of Deep Learning Algorithm that
take the image as an input and learn the various features of the image through filters.
 PAPERS SURVEYED FROM SCIENCE DIRECT :
1. Hierarchical Convolutional Neural Network for Handwritten Digits Recognition
(https://www.sciencedirect.com/science/article/pii/S1877050920311881)
2. Hybrid CNN-SVM Classifier for Handwritten Digit
Recognition(https://www.sciencedirect.com/science/article/pii/S1877050920307754)
3. Handwritten Data Digitization Using an Anchor based Multi-Channel CNN (MCCNN)
Trained on a Hybrid Dataset (h-
EH).(https://www.sciencedirect.com/science/article/pii/S1877050921012187).
Hierarchical Convolutional Neural Network for Handwritten Digits
Recognition
 ABSTRACTION:
The application of a combination of convolutional neural networks for the
recognition of handwritten digits is considered. Recognition is carried out by
two sets of the networks following each other. The first neural network
selects two digits with maximum activation functions. Depending on the
winners, the next network is activated, which selects one digit from two. The
proposed algorithm is tested on the data from MNIST.
INTRODUCTION
 Handwritten digit recognition is mainly based on Neural networks. Neural
networks are widely used in science , technology and many other fields . One of
the main applications of networks is image processing. This includes various tasks
related to the classification, localization and recognition of objects. Similar tasks
are associated with the development of principles and the construction of systems
designed to determine whether an object belongs to one of the classes of objects.
 In present work, we consider the recognition of handwritten digits from the MNIST
database by a hierarchical convolutional neural network that interprets the image
sequentially and obtaining the correct answer
The first level. Digit recognition by convolutional neural network
 We consider the architecture of a six-layer convolution network, consisting of an
input layer containing 784 neurons (one image from the MNIST database has a
dimension of 28 by 28 pixels) and six layers:
 1. Convolutional layer, 11 cards of signs of dimension 24x24 (core bypass 5x5).
 2. Subsample layer, 11 cards of signs of dimension 12x12.
 3. Convolutional layer, 22 feature cards of dimension 8x8 (core bypass 5x5).
 4. Subsample layer. 22 cards of signs of dimension 4x4.
 5. Fully connected layer, 120 neurons.
 6. Fully connected layer, 10 neurons.
 We train the network using the backpropagation algorithm. Note that the network
parameters are established experimentally. For example, in this way the optimal
digit of matrices in the first convolutional layer was obtained, containing 11 24-
by-24 feature maps. The network was trained and tested on data representing 28
by 28 pixel handwritten digits from the MNIST database. The smallest error of the
convolutional neural network shown in the test sample from MNIST it amounted
to 0.82% 82 images from the test sample containing 10 thousand handwritten
images were incorrectly recognized. Note that we did not achieve maximum
accuracy at this stage. We write the digits of incorrectly recognized MNIST images:
115, 247, 259, 449, 582, 619, 659, 674, 740, 791, 900, 947, 1014, 1039, 1112,
The second level. Additional convolutional networks
 Additional networks are a set of convolutional neural networks trained to
recognize two digits. We have analyzed and found out that 31 such networks are
needed (equal to the digit of nonzero cells in the table). The recognition algorithm
using a combination of neural networks has the following two stages:
 1) Passage through the global network;
 2) Passage through the additional network if the difference between the maximum
values of the digits at the output does not exceed 0.7 at the first stage
KEY FINDINGS
 Convolutional Neural Networks
 Heirarical Convolutional Neural Networks
 Training And Testing MNIST datraset using Neural Nrtworks
REFERENCES
 https://www.sciencedirect.com/science/article/pii/S1877050920307754
 https://www.sciencedirect.com/science/article/pii/S1877050920311881
 https://www.sciencedirect.com/science/article/pii/S1877050921012187
 https://data-flair.training/blogs/python-deep-learning-project-handwritten-digit-
recognition/
 CONCLUSION: The hierarchical convolutional neural network is proposed for the
task of recognizing handwritten numbers. The similar task can be used for
handwriting recognition on tablet computers, recognition of postal codes for
sorting mail, processing bank checks, entering numerical entries in manually filled
forms, etc. The proposed algorithm is tested on data from MNIST.

More Related Content

What's hot

MNIST and machine learning - presentation
MNIST and machine learning - presentationMNIST and machine learning - presentation
MNIST and machine learning - presentation
Steve Dias da Cruz
 
Comparison of Learning Algorithms for Handwritten Digit Recognition
Comparison of Learning Algorithms for Handwritten Digit RecognitionComparison of Learning Algorithms for Handwritten Digit Recognition
Comparison of Learning Algorithms for Handwritten Digit Recognition
Safaa Alnabulsi
 
Deep Neural Networks (DNN)
Deep Neural Networks (DNN)Deep Neural Networks (DNN)
YOGA POSE DETECTION USING MACHINE LEARNING LIBRARIES
YOGA POSE DETECTION USING MACHINE LEARNING LIBRARIESYOGA POSE DETECTION USING MACHINE LEARNING LIBRARIES
YOGA POSE DETECTION USING MACHINE LEARNING LIBRARIES
IRJET Journal
 
Convolution Neural Network (CNN)
Convolution Neural Network (CNN)Convolution Neural Network (CNN)
Convolution Neural Network (CNN)
Basit Rafiq
 
Handwritten Digit Recognition using Convolutional Neural Networks
Handwritten Digit Recognition using Convolutional Neural  NetworksHandwritten Digit Recognition using Convolutional Neural  Networks
Handwritten Digit Recognition using Convolutional Neural Networks
IRJET Journal
 
Recurrent Neural Network (RNN) | RNN LSTM Tutorial | Deep Learning Course | S...
Recurrent Neural Network (RNN) | RNN LSTM Tutorial | Deep Learning Course | S...Recurrent Neural Network (RNN) | RNN LSTM Tutorial | Deep Learning Course | S...
Recurrent Neural Network (RNN) | RNN LSTM Tutorial | Deep Learning Course | S...
Simplilearn
 
Deep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural NetworksDeep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural Networks
Christian Perone
 
Handwritten bangla-digit-recognition-using-deep-learning
Handwritten bangla-digit-recognition-using-deep-learningHandwritten bangla-digit-recognition-using-deep-learning
Handwritten bangla-digit-recognition-using-deep-learning
Sharmin Rubi
 
What is Deep Learning?
What is Deep Learning?What is Deep Learning?
What is Deep Learning?
NVIDIA
 
Convolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningConvolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep Learning
Mohamed Loey
 
ResNet basics (Deep Residual Network for Image Recognition)
ResNet basics (Deep Residual Network for Image Recognition)ResNet basics (Deep Residual Network for Image Recognition)
ResNet basics (Deep Residual Network for Image Recognition)
Sanjay Saha
 
Image processing fundamentals
Image processing fundamentalsImage processing fundamentals
Image processing fundamentals
A B Shinde
 
Image recognition
Image recognitionImage recognition
Image recognition
Joel Jose
 
CNN Machine learning DeepLearning
CNN Machine learning DeepLearningCNN Machine learning DeepLearning
CNN Machine learning DeepLearning
Abhishek Sharma
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
Muhammad Ishaq
 
Handwritten digit recognition using image processing
Handwritten digit recognition using image processing Handwritten digit recognition using image processing
Handwritten digit recognition using image processing
anita maharjan
 
Introduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkIntroduction to Recurrent Neural Network
Introduction to Recurrent Neural Network
Knoldus Inc.
 
Overview of Convolutional Neural Networks
Overview of Convolutional Neural NetworksOverview of Convolutional Neural Networks
Overview of Convolutional Neural Networks
ananth
 
Digit recognition using neural network
Digit recognition using neural networkDigit recognition using neural network
Digit recognition using neural network
shachibattar
 

What's hot (20)

MNIST and machine learning - presentation
MNIST and machine learning - presentationMNIST and machine learning - presentation
MNIST and machine learning - presentation
 
Comparison of Learning Algorithms for Handwritten Digit Recognition
Comparison of Learning Algorithms for Handwritten Digit RecognitionComparison of Learning Algorithms for Handwritten Digit Recognition
Comparison of Learning Algorithms for Handwritten Digit Recognition
 
Deep Neural Networks (DNN)
Deep Neural Networks (DNN)Deep Neural Networks (DNN)
Deep Neural Networks (DNN)
 
YOGA POSE DETECTION USING MACHINE LEARNING LIBRARIES
YOGA POSE DETECTION USING MACHINE LEARNING LIBRARIESYOGA POSE DETECTION USING MACHINE LEARNING LIBRARIES
YOGA POSE DETECTION USING MACHINE LEARNING LIBRARIES
 
Convolution Neural Network (CNN)
Convolution Neural Network (CNN)Convolution Neural Network (CNN)
Convolution Neural Network (CNN)
 
Handwritten Digit Recognition using Convolutional Neural Networks
Handwritten Digit Recognition using Convolutional Neural  NetworksHandwritten Digit Recognition using Convolutional Neural  Networks
Handwritten Digit Recognition using Convolutional Neural Networks
 
Recurrent Neural Network (RNN) | RNN LSTM Tutorial | Deep Learning Course | S...
Recurrent Neural Network (RNN) | RNN LSTM Tutorial | Deep Learning Course | S...Recurrent Neural Network (RNN) | RNN LSTM Tutorial | Deep Learning Course | S...
Recurrent Neural Network (RNN) | RNN LSTM Tutorial | Deep Learning Course | S...
 
Deep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural NetworksDeep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural Networks
 
Handwritten bangla-digit-recognition-using-deep-learning
Handwritten bangla-digit-recognition-using-deep-learningHandwritten bangla-digit-recognition-using-deep-learning
Handwritten bangla-digit-recognition-using-deep-learning
 
What is Deep Learning?
What is Deep Learning?What is Deep Learning?
What is Deep Learning?
 
Convolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningConvolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep Learning
 
ResNet basics (Deep Residual Network for Image Recognition)
ResNet basics (Deep Residual Network for Image Recognition)ResNet basics (Deep Residual Network for Image Recognition)
ResNet basics (Deep Residual Network for Image Recognition)
 
Image processing fundamentals
Image processing fundamentalsImage processing fundamentals
Image processing fundamentals
 
Image recognition
Image recognitionImage recognition
Image recognition
 
CNN Machine learning DeepLearning
CNN Machine learning DeepLearningCNN Machine learning DeepLearning
CNN Machine learning DeepLearning
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
 
Handwritten digit recognition using image processing
Handwritten digit recognition using image processing Handwritten digit recognition using image processing
Handwritten digit recognition using image processing
 
Introduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkIntroduction to Recurrent Neural Network
Introduction to Recurrent Neural Network
 
Overview of Convolutional Neural Networks
Overview of Convolutional Neural NetworksOverview of Convolutional Neural Networks
Overview of Convolutional Neural Networks
 
Digit recognition using neural network
Digit recognition using neural networkDigit recognition using neural network
Digit recognition using neural network
 

Similar to HANDWRITTEN DIGIT RECOGNITIONppt1.pptx

Handwritten digits recognition report
Handwritten digits recognition reportHandwritten digits recognition report
Handwritten digits recognition report
Swayamdipta Saha
 
IRJET - Study on the Effects of Increase in the Depth of the Feature Extracto...
IRJET - Study on the Effects of Increase in the Depth of the Feature Extracto...IRJET - Study on the Effects of Increase in the Depth of the Feature Extracto...
IRJET - Study on the Effects of Increase in the Depth of the Feature Extracto...
IRJET Journal
 
Neural networks and deep learning
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learning
RADO7900
 
BATCH.pptx
BATCH.pptxBATCH.pptx
BATCH.pptx
NIRMALRAJSCSE20
 
Looking into the Black Box - A Theoretical Insight into Deep Learning Networks
Looking into the Black Box - A Theoretical Insight into Deep Learning NetworksLooking into the Black Box - A Theoretical Insight into Deep Learning Networks
Looking into the Black Box - A Theoretical Insight into Deep Learning Networks
Dinesh V
 
Cnn
CnnCnn
Hand Written Digit Classification
Hand Written Digit ClassificationHand Written Digit Classification
Hand Written Digit Classification
ijtsrd
 
Neural Network and Fuzzy logic ( NN &FL).pptx
Neural Network and Fuzzy logic ( NN &FL).pptxNeural Network and Fuzzy logic ( NN &FL).pptx
Neural Network and Fuzzy logic ( NN &FL).pptx
UsamaAli119043
 
Handwritten digit and symbol recognition using CNN.pptx
Handwritten digit and symbol recognition using CNN.pptxHandwritten digit and symbol recognition using CNN.pptx
Handwritten digit and symbol recognition using CNN.pptx
Yasmin297583
 
Artificial Neural Network for hand Gesture recognition
Artificial Neural Network for hand Gesture recognitionArtificial Neural Network for hand Gesture recognition
Artificial Neural Network for hand Gesture recognition
Vigneshwer Dhinakaran
 
Intelligent Handwritten Digit Recognition using Artificial Neural Network
Intelligent Handwritten Digit Recognition using Artificial Neural NetworkIntelligent Handwritten Digit Recognition using Artificial Neural Network
Intelligent Handwritten Digit Recognition using Artificial Neural Network
IJERA Editor
 
Build a simple image recognition system with tensor flow
Build a simple image recognition system with tensor flowBuild a simple image recognition system with tensor flow
Build a simple image recognition system with tensor flow
DebasisMohanty37
 
Neural Network
Neural NetworkNeural Network
Neural Network
Ashish Kumar
 
Eckovation machine learning project
Eckovation machine learning projectEckovation machine learning project
Eckovation machine learning project
Vinod Jatav
 
Teach a neural network to read handwriting
Teach a neural network to read handwritingTeach a neural network to read handwriting
Teach a neural network to read handwriting
Vipul Kaushal
 
Deep Learning - The Past, Present and Future of Artificial Intelligence
Deep Learning - The Past, Present and Future of Artificial IntelligenceDeep Learning - The Past, Present and Future of Artificial Intelligence
Deep Learning - The Past, Present and Future of Artificial Intelligence
Lukas Masuch
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)
IJERD Editor
 
Deep Learning Training at Intel
Deep Learning Training at IntelDeep Learning Training at Intel
Deep Learning Training at Intel
Atul Vaish
 
A new study of dss based on neural network and data mining
A new study of dss based on neural network and data miningA new study of dss based on neural network and data mining
A new study of dss based on neural network and data mining
Attaporn Ninsuwan
 
Machine Learning
Machine LearningMachine Learning
Machine Learning
Mahdi Hosseini Moghaddam
 

Similar to HANDWRITTEN DIGIT RECOGNITIONppt1.pptx (20)

Handwritten digits recognition report
Handwritten digits recognition reportHandwritten digits recognition report
Handwritten digits recognition report
 
IRJET - Study on the Effects of Increase in the Depth of the Feature Extracto...
IRJET - Study on the Effects of Increase in the Depth of the Feature Extracto...IRJET - Study on the Effects of Increase in the Depth of the Feature Extracto...
IRJET - Study on the Effects of Increase in the Depth of the Feature Extracto...
 
Neural networks and deep learning
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learning
 
BATCH.pptx
BATCH.pptxBATCH.pptx
BATCH.pptx
 
Looking into the Black Box - A Theoretical Insight into Deep Learning Networks
Looking into the Black Box - A Theoretical Insight into Deep Learning NetworksLooking into the Black Box - A Theoretical Insight into Deep Learning Networks
Looking into the Black Box - A Theoretical Insight into Deep Learning Networks
 
Cnn
CnnCnn
Cnn
 
Hand Written Digit Classification
Hand Written Digit ClassificationHand Written Digit Classification
Hand Written Digit Classification
 
Neural Network and Fuzzy logic ( NN &FL).pptx
Neural Network and Fuzzy logic ( NN &FL).pptxNeural Network and Fuzzy logic ( NN &FL).pptx
Neural Network and Fuzzy logic ( NN &FL).pptx
 
Handwritten digit and symbol recognition using CNN.pptx
Handwritten digit and symbol recognition using CNN.pptxHandwritten digit and symbol recognition using CNN.pptx
Handwritten digit and symbol recognition using CNN.pptx
 
Artificial Neural Network for hand Gesture recognition
Artificial Neural Network for hand Gesture recognitionArtificial Neural Network for hand Gesture recognition
Artificial Neural Network for hand Gesture recognition
 
Intelligent Handwritten Digit Recognition using Artificial Neural Network
Intelligent Handwritten Digit Recognition using Artificial Neural NetworkIntelligent Handwritten Digit Recognition using Artificial Neural Network
Intelligent Handwritten Digit Recognition using Artificial Neural Network
 
Build a simple image recognition system with tensor flow
Build a simple image recognition system with tensor flowBuild a simple image recognition system with tensor flow
Build a simple image recognition system with tensor flow
 
Neural Network
Neural NetworkNeural Network
Neural Network
 
Eckovation machine learning project
Eckovation machine learning projectEckovation machine learning project
Eckovation machine learning project
 
Teach a neural network to read handwriting
Teach a neural network to read handwritingTeach a neural network to read handwriting
Teach a neural network to read handwriting
 
Deep Learning - The Past, Present and Future of Artificial Intelligence
Deep Learning - The Past, Present and Future of Artificial IntelligenceDeep Learning - The Past, Present and Future of Artificial Intelligence
Deep Learning - The Past, Present and Future of Artificial Intelligence
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)
 
Deep Learning Training at Intel
Deep Learning Training at IntelDeep Learning Training at Intel
Deep Learning Training at Intel
 
A new study of dss based on neural network and data mining
A new study of dss based on neural network and data miningA new study of dss based on neural network and data mining
A new study of dss based on neural network and data mining
 
Machine Learning
Machine LearningMachine Learning
Machine Learning
 

Recently uploaded

办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
apvysm8
 
The Building Blocks of QuestDB, a Time Series Database
The Building Blocks of QuestDB, a Time Series DatabaseThe Building Blocks of QuestDB, a Time Series Database
The Building Blocks of QuestDB, a Time Series Database
javier ramirez
 
Learn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queriesLearn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queries
manishkhaire30
 
My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.
rwarrenll
 
Challenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more importantChallenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more important
Sm321
 
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
bopyb
 
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
Timothy Spann
 
University of New South Wales degree offer diploma Transcript
University of New South Wales degree offer diploma TranscriptUniversity of New South Wales degree offer diploma Transcript
University of New South Wales degree offer diploma Transcript
soxrziqu
 
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
74nqk8xf
 
State of Artificial intelligence Report 2023
State of Artificial intelligence Report 2023State of Artificial intelligence Report 2023
State of Artificial intelligence Report 2023
kuntobimo2016
 
DSSML24_tspann_CodelessGenerativeAIPipelines
DSSML24_tspann_CodelessGenerativeAIPipelinesDSSML24_tspann_CodelessGenerativeAIPipelines
DSSML24_tspann_CodelessGenerativeAIPipelines
Timothy Spann
 
一比一原版(Chester毕业证书)切斯特大学毕业证如何办理
一比一原版(Chester毕业证书)切斯特大学毕业证如何办理一比一原版(Chester毕业证书)切斯特大学毕业证如何办理
一比一原版(Chester毕业证书)切斯特大学毕业证如何办理
74nqk8xf
 
Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......
Sachin Paul
 
Everything you wanted to know about LIHTC
Everything you wanted to know about LIHTCEverything you wanted to know about LIHTC
Everything you wanted to know about LIHTC
Roger Valdez
 
一比一原版(Glasgow毕业证书)格拉斯哥大学毕业证如何办理
一比一原版(Glasgow毕业证书)格拉斯哥大学毕业证如何办理一比一原版(Glasgow毕业证书)格拉斯哥大学毕业证如何办理
一比一原版(Glasgow毕业证书)格拉斯哥大学毕业证如何办理
g4dpvqap0
 
Analysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performanceAnalysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performance
roli9797
 
Influence of Marketing Strategy and Market Competition on Business Plan
Influence of Marketing Strategy and Market Competition on Business PlanInfluence of Marketing Strategy and Market Competition on Business Plan
Influence of Marketing Strategy and Market Competition on Business Plan
jerlynmaetalle
 
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
nuttdpt
 
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
sameer shah
 
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
g4dpvqap0
 

Recently uploaded (20)

办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
 
The Building Blocks of QuestDB, a Time Series Database
The Building Blocks of QuestDB, a Time Series DatabaseThe Building Blocks of QuestDB, a Time Series Database
The Building Blocks of QuestDB, a Time Series Database
 
Learn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queriesLearn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queries
 
My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.
 
Challenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more importantChallenges of Nation Building-1.pptx with more important
Challenges of Nation Building-1.pptx with more important
 
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
 
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
 
University of New South Wales degree offer diploma Transcript
University of New South Wales degree offer diploma TranscriptUniversity of New South Wales degree offer diploma Transcript
University of New South Wales degree offer diploma Transcript
 
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
 
State of Artificial intelligence Report 2023
State of Artificial intelligence Report 2023State of Artificial intelligence Report 2023
State of Artificial intelligence Report 2023
 
DSSML24_tspann_CodelessGenerativeAIPipelines
DSSML24_tspann_CodelessGenerativeAIPipelinesDSSML24_tspann_CodelessGenerativeAIPipelines
DSSML24_tspann_CodelessGenerativeAIPipelines
 
一比一原版(Chester毕业证书)切斯特大学毕业证如何办理
一比一原版(Chester毕业证书)切斯特大学毕业证如何办理一比一原版(Chester毕业证书)切斯特大学毕业证如何办理
一比一原版(Chester毕业证书)切斯特大学毕业证如何办理
 
Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......
 
Everything you wanted to know about LIHTC
Everything you wanted to know about LIHTCEverything you wanted to know about LIHTC
Everything you wanted to know about LIHTC
 
一比一原版(Glasgow毕业证书)格拉斯哥大学毕业证如何办理
一比一原版(Glasgow毕业证书)格拉斯哥大学毕业证如何办理一比一原版(Glasgow毕业证书)格拉斯哥大学毕业证如何办理
一比一原版(Glasgow毕业证书)格拉斯哥大学毕业证如何办理
 
Analysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performanceAnalysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performance
 
Influence of Marketing Strategy and Market Competition on Business Plan
Influence of Marketing Strategy and Market Competition on Business PlanInfluence of Marketing Strategy and Market Competition on Business Plan
Influence of Marketing Strategy and Market Competition on Business Plan
 
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
 
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
 
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
 

HANDWRITTEN DIGIT RECOGNITIONppt1.pptx

  • 2. Handwritten Digit Recognition Project  PROBLEM STATMENT The MNIST dataset of handwritten digits is widespread among the data scientists and machine learning enthusiasts. It is an amazing project to get started with the data science and understand the processes involved in a project. The project is implemented using the Convolutional Neural Networks and then for real-time prediction we also build a nice graphical user interface to draw digits on a canvas and then the model will predict the digit."
  • 3. OBJECTIVES: MNIST data set : It is a large data collection of handwritten digits used to train and test various supervised machine learning algorithms. Tenserflow : TensorFlow is a free and open-source software library for machine learning and artificial intelligence. It can be used across a range of tasks but has a particular focus on training and inference of deep neural networks. Convolutional Neural Networks(CNN) : Convolutional Neural Networks are a type of Deep Learning Algorithm that take the image as an input and learn the various features of the image through filters.
  • 4.  PAPERS SURVEYED FROM SCIENCE DIRECT : 1. Hierarchical Convolutional Neural Network for Handwritten Digits Recognition (https://www.sciencedirect.com/science/article/pii/S1877050920311881) 2. Hybrid CNN-SVM Classifier for Handwritten Digit Recognition(https://www.sciencedirect.com/science/article/pii/S1877050920307754) 3. Handwritten Data Digitization Using an Anchor based Multi-Channel CNN (MCCNN) Trained on a Hybrid Dataset (h- EH).(https://www.sciencedirect.com/science/article/pii/S1877050921012187).
  • 5. Hierarchical Convolutional Neural Network for Handwritten Digits Recognition  ABSTRACTION: The application of a combination of convolutional neural networks for the recognition of handwritten digits is considered. Recognition is carried out by two sets of the networks following each other. The first neural network selects two digits with maximum activation functions. Depending on the winners, the next network is activated, which selects one digit from two. The proposed algorithm is tested on the data from MNIST.
  • 6. INTRODUCTION  Handwritten digit recognition is mainly based on Neural networks. Neural networks are widely used in science , technology and many other fields . One of the main applications of networks is image processing. This includes various tasks related to the classification, localization and recognition of objects. Similar tasks are associated with the development of principles and the construction of systems designed to determine whether an object belongs to one of the classes of objects.  In present work, we consider the recognition of handwritten digits from the MNIST database by a hierarchical convolutional neural network that interprets the image sequentially and obtaining the correct answer
  • 7. The first level. Digit recognition by convolutional neural network  We consider the architecture of a six-layer convolution network, consisting of an input layer containing 784 neurons (one image from the MNIST database has a dimension of 28 by 28 pixels) and six layers:  1. Convolutional layer, 11 cards of signs of dimension 24x24 (core bypass 5x5).  2. Subsample layer, 11 cards of signs of dimension 12x12.  3. Convolutional layer, 22 feature cards of dimension 8x8 (core bypass 5x5).  4. Subsample layer. 22 cards of signs of dimension 4x4.  5. Fully connected layer, 120 neurons.
  • 8.  6. Fully connected layer, 10 neurons.  We train the network using the backpropagation algorithm. Note that the network parameters are established experimentally. For example, in this way the optimal digit of matrices in the first convolutional layer was obtained, containing 11 24- by-24 feature maps. The network was trained and tested on data representing 28 by 28 pixel handwritten digits from the MNIST database. The smallest error of the convolutional neural network shown in the test sample from MNIST it amounted to 0.82% 82 images from the test sample containing 10 thousand handwritten images were incorrectly recognized. Note that we did not achieve maximum accuracy at this stage. We write the digits of incorrectly recognized MNIST images: 115, 247, 259, 449, 582, 619, 659, 674, 740, 791, 900, 947, 1014, 1039, 1112,
  • 9. The second level. Additional convolutional networks  Additional networks are a set of convolutional neural networks trained to recognize two digits. We have analyzed and found out that 31 such networks are needed (equal to the digit of nonzero cells in the table). The recognition algorithm using a combination of neural networks has the following two stages:  1) Passage through the global network;  2) Passage through the additional network if the difference between the maximum values of the digits at the output does not exceed 0.7 at the first stage
  • 10. KEY FINDINGS  Convolutional Neural Networks  Heirarical Convolutional Neural Networks  Training And Testing MNIST datraset using Neural Nrtworks
  • 11. REFERENCES  https://www.sciencedirect.com/science/article/pii/S1877050920307754  https://www.sciencedirect.com/science/article/pii/S1877050920311881  https://www.sciencedirect.com/science/article/pii/S1877050921012187  https://data-flair.training/blogs/python-deep-learning-project-handwritten-digit- recognition/  CONCLUSION: The hierarchical convolutional neural network is proposed for the task of recognizing handwritten numbers. The similar task can be used for handwriting recognition on tablet computers, recognition of postal codes for sorting mail, processing bank checks, entering numerical entries in manually filled forms, etc. The proposed algorithm is tested on data from MNIST.