An approach to empirical Optical Character recognition paradigm using Multi-Layer Perceptorn Neural Network

An approach to empirical Optical
Character recognition paradigm
using Multi-Layer Perceptorn
Neural Network

OUTLINEOUTLINE
IntroductionIntroduction
What is Optical Character RecognitionWhat is Optical Character Recognition
OCR ModelOCR Model
Acquiring ImageAcquiring Image
Input PreprocessingInput Preprocessing
Input SegmentationInput Segmentation
Feature ExtractionFeature Extraction
Multi-Layer Perceptron Neural NetworkMulti-Layer Perceptron Neural Network
TrainingTraining
RecognitionRecognition
Experimental ResultExperimental Result
ConclusionsConclusions
ReferencesReferences
Dec 22, 2015 2An approach to empirical OCR paradigm using Multi-Layer Perceptorn Neural Network

 Representing the architecture of Optical Character
Recognition(OCR) that is designed using artificial
computational model same as biological neuron network.
Introduction

What isWhat is OOpticalptical CCharacterharacter RRecognitionecognition??
 OCR allow to convert mechanical or electronic
image base text into the machine encodes able text
through an optical mechanism.
 The ultimate objective of OCR is to simulate
the human reading capabilities so the computer
can read, understand, edit and do similar activities
it does with the text.

OCR ModelOCR Model
Figure 1:Figure 1: Optical Character Recognizer Model.

Acquiring ImageAcquiring Image
- Image is
acquisition from
any possible
source that can
be hardware
device like
camera, scanner
and so on.

Input PreprocessingInput Preprocessing
- Image processing is a signal processing that
convert either an image or a set of
characteristics or parameters related to the
image.
-It is achieve correction of distortion, noise
reduction, normalization, filtering the image
and so on.

- The RGB color space contains red, green,
blue that are added together in a variety of
ways to reproduce a array of color.
RGB to Gray scale Conversion
Input ImageRGB to Gray scale Conversion

- A binary image has only two possible color
value for each pixel is that black and white.
This color depth is 1-bit monochrome.
Gray scale to Binary Image Conversion
RGB to Gray scale ImageGray scale to Binary image

InputInput Segmentation
- By the Image segmentation simplify and/or
change the representation of an image into
something that is more meaningful and easier
to analyze.
-Image segmentation is used for object
recognition of an image; detect the boundary
estimation, image editing or image database
look-up.

- Enumeration of character lines in a
character image is essential in delimiting the
bounds within which the detection can
precede.
Determining Character Line
Figure-6: Boundary detection of character line.

- Detection of individual symbols involves
scanning character lines for orthogonally
separable images composed of black pixels.
Detecting Individual Character
Figure-7: Boundary detection of a character.

Feature ExtractionFeature Extraction
- Feature extraction extract set of feature to
produce the relevant information from the
original input set data that can be represent
in a lower dimensionality space.
-To implement the feature extraction process
we have used Image to matrix mapping
process.

Feature ExtractionFeature Extraction
- By the matrix mapping process the character
image is converted corresponding two
dimensional binary matrixes.
Image to Matrix Mapping
Image to
Matrix
Mapping
Image to
Matrix
Mapping
Binary
Represe
ntation
Binary
Represe
ntation

Multi-Layer Perceptron Neural NetworkMulti-Layer Perceptron Neural Network
Multi-Layer Perceptron Neural network has an input
layer, hidden layer and output layer. Input layer feed the
input data set that is came from feature extraction and
output layer produced the set of output vector.

TrainingTraining
 Appling the learning process algorithm within the
multilayer network architecture, the synaptic weights
and threshold are update in a way that the
classification/recognition task can be performing
efficiently.
 Presenting 600-602-6 three Layer Neural network
architecture to perform the Optical Character
Recognition Learning process.

Algorithm (sequential)
1. Apply an input vector and calculate all activations, a and u
2. Evaluate ∆k for all output units via:
(Note similarity to perceptron learning algorithm)
3. Backpropagate ∆ks to get error terms δ for hidden layers using:
4. Evaluate changes using:
))(('))()(()( tagtytdt iiii −=∆
∑∆=
k
kikii wttugt )())((')(δ
)()()()1(
)()()()1(
tzttwtw
txttvtv
jiijij
jiijij
∆+=+
+=+
η
ηδ
Dec 22, 2015 An approach to empirical OCR paradigm using Multi-Layer Perceptorn Neural Network 17

Once weight changes are computed for all units, weights are updated
at the same time (bias included as weights here). An example:
y1
y2
x1
x2
v11= -1
v21= 0
v12= 0
v22= 1
v10= 1
v20= 1
w11= 1
w21= -1
w12= 0
w22= 1
Use identity activation function (ie g(a) = a)

All biases set to 1. Will not draw them for clarity.
Learning rate η = 0.1
y1
y2
x1
x2
v11= -1
v21= 0
v12= 0
v22= 1
w11= 1
w21= -1
w12= 0
w22= 1
Have input [0 1] with target [1 0].
x1= 0
x2= 1

Forward pass. Calculate 1st
layer activations:
y1
y2
v11= -1
v21= 0
v12= 0
v22= 1
w11= 1
w21= -1
w12= 0
w22= 1
u2 = 2
u1 = 1
u1 = -1x0 + 0x1 +1 = 1
u2 = 0x0 + 1x1 +1 = 2
x1
x2

Calculate first layer outputs by passing activations thru activation
functions
y1
y2
x1
x2
v11= -1
v21= 0
v12= 0
v22= 1
w11= 1
w21= -1
w12= 0
w22= 1
z2 = 2
z1 = 1
z1 = g(u1) = 1
z2 = g(u2) = 2

Calculate 2nd
layer outputs (weighted sum thru activation functions):
y1= 2
y2= 2
x1
x2
v11= -1
v21= 0
v12= 0
v22= 1
w11= 1
w21= -1
w12= 0
w22= 1
y1 = a1 = 1x1 + 0x2 +1 = 2
y2 = a2 = -1x1 + 1x2 +1 = 2

Backward pass:
∆1= -1
∆2= -2
x1
x2
v11= -1
v21= 0
v12= 0
v22= 1
w11= 1
w21= -1
w12= 0
w22= 1
)())(('))()((
)()()()1(
tztagtytd
tzttwtw
jiii
jiijij
−=
∆=−+
η
η
Target =[1, 0] so d1 = 1 and d2 = 0
So:
∆1 = (d1 - y1 )= 1 – 2 = -1
∆2 = (d2 - y2 )= 0 – 2 = -2

Calculate weight changes for 1st
layer (cf perceptron learning):
∆1 z1 =-1x1
x2
v11= -1
v21= 0
v12= 0
v22= 1
w11= 1
w21= -1
w12= 0
w22= 1
)()()()1( tzttwtw jiijij ∆=−+ η
z2 = 2
z1 = 1
∆1 z2 =-2
∆2 z1 =-2
∆2 z2 =-4

Weight changes will be:
x1
x2
v11= -1
v21= 0
v12= 0
v22= 1
w11= 0.9
w21= -1.2
w12= -0.2
w22= 0.6
)()()()1( tzttwtw jiijij ∆=−+ η

But first must calculate δ’s:
∆1= -1
∆2= -2
x1
x2
v11= -1
v21= 0
v12= 0
v22= 1
∆1 w11= -1
∆2 w21= 2
∆1 w12= 0
∆2 w22= -2
∑∆=
k

∆’s propagate back:
∆1= -1
∆2= -2
x1
x2
v11= -1
v21= 0
v12= 0
v22= 1
δ1= 1
δ2 = -2
δ1 = - 1 + 2 = 1
δ2 = 0 – 2 = -2
∑∆=
k

And are multiplied by inputs:
∆1= -1
∆2= -2
v11= -1
v21= 0
v12= 0
v22= 1
δ1 x1 = 0
δ2 x2 = -2
)()()()1( txttvtv jiijij ηδ=−+
x2= 1
x1= 0
δ2 x1 = 0
δ1 x2 = 1

Finally change weights:
v11= -1
v21= 0
v12= 0.1
v22= 0.8
x2= 1
x1= 0 w11= 0.9
w21= -1.2
w12= -0.2
w22= 0.6
Note that the weights multiplied by the zero input are unchanged as they do
not contribute to the error
We have also changed biases (not shown)

Now go forward again (would normally use a new input vector):
v11= -1
v21= 0
v12= 0.1
v22= 0.8
x2= 1
x1= 0 w11= 0.9
w21= -1.2
w12= -0.2
w22= 0.6
z2 = 1.6
z1 = 1.2

Now go forward again (would normally use a new input vector):
v11= -1
v21= 0
v12= 0.1
v22= 0.8
x2= 1
x1= 0 w11= 0.9
w21= -1.2
w12= -0.2
w22= 0.6
y2 = 0.32
y1 = 1.66
Outputs now closer to target value [1, 0]

RecognitionRecognition
Feature data is feed to the network input layer and
produced an output vector and calculating the error
function.

Experimental ResultExperimental Result
Chart-1: Isolated Character Recognition
experiment result comparison.
62 English character (i.e, English
Capital Alphabets A to Z, English
Small Alphabets a to z, English
Numerical Digits 0 to 9) image
recognition.
So the average Success rate for the
Isolated Character Recognition is =
91.53%
Isolated Character Recognition

Experimental ResultExperimental Result
Chart-2: Sentential Case Character Recognition
experiment result comparison.
For the sentential case character we
have used the sentence is “A Quick
Brown Fox Jumps over the Lazy
Dog.” This experimental sentence
is written four different type of font
like Arial, Calibri (body), Segoe UI
and Times New Roman.
So the average Success rate for the
sentential case Character
Recognition is = 80.65%
Sentential Case Character Recognition
0
20
40
60
80
100
Correct
Recognition
Wrong
Recognition
Success(%)
Error(%)

ConclusionsConclusions
 In our proposed system are achieved 91.53%
accuracy for the isolated character and 80.65%
accuracy for the sentential case character.
 In future we try to be improved the accuracy of
the OCR model by better preprocessing method
and optimal ANN architecture.

An approach to empirical Optical Character recognition paradigm using Multi-Layer Perceptorn Neural Network

More Related Content

What's hot (20)

Viewers also liked (11)

Similar to An approach to empirical Optical Character recognition paradigm using Multi-Layer Perceptorn Neural Network (20)

More from Abdullah al Mamun (20)

Recently uploaded (20)

An approach to empirical Optical Character recognition paradigm using Multi-Layer Perceptorn Neural Network

Editor's Notes