You are on page 1of 2

RecognizingHandwrittenEnglishLettersUsing

SupportVectorMachine

HodaAlhameidyandNaflaAlDarei
CollegeofInformationTechnology,UAEU
Email:[20012554;200812303]@uaeu.ac.ae

1. Introduction
It is common for children to have the problem of
mixing up letters such asbandd,pandq,mandn,
and other letters. The principle that children learn
lettersbymemorizingthelettersshapesturnedout
tobenotaccurate.Mostlyaletterisrecognizedby
its sequence of features, not as a whole shape.
Therefore, the best way to teach children how to
writelettersisthroughasequenceoffeatureswhich
reflect the printing practice of letters. It is highly
desired to develop a method which will enable
children to write English letters and the system
automatically checks for the correctness and the
readabilityoftheletter.Tothisend,severalsystems
wheredevelopedinthepastforrecognizingletters.
Oneofthewidelyusedtechniqueswhichwasableto
recognize characters successfully is the chain code
[1].Themainadvantageofusingchaincodeoverthe
traditional representation of a binary object is that
the chain code is a complete representation of an
objectorcurve(letterinthiscase).Thismeansthat
wecancomputeanyshapesfeaturesfromthechain
codes.

Combining chain code with a powerful machine


learning technique such as Support Vector Machine
(SVM) will surely be an accurate letter recognizing
method. Therefore, in this paper we propose a
machine learning based method and in particular
SVM to learn from an initial training set of
handwrittenEnglishlettersanddetecthandwritten
letters.Thismethodwillbeofgreathelpinteaching
childrenletters.

2. Method
TheoverviewofthemethodisshowninFigure1.

Figure1:AnOverviewoftheproposedmethodfor
recognizingEnglishletters.

Themethodstartsbyextractingthefeaturesofeach
letter using the Chain codes. Chain codes use to
represent a boundary by a connected sequence of
straight line segments of specified length and
direction.Thisrepresentationinthiscaseisbasedon
8connectivity of the segments [2]. The direction of
eachsegmentiscodedbyusinganumberingscheme
as shown in Figure 2. Chain codes based from this
schemeareknownasFreemanchaincodes.

Figure2:Thedirectionrepresentation.

Following the feature extraction step, the trained


SVMisusedtomaketheletteridentificationsbased

To evaluate the method, 10 volunteers were asked


towriteallthe26Englishlettersusingdrawingpad
resulted in 260 samples. The Freeman chain codes
were then used to determine the combination of
directions of all letters. A java program was written
to detect the movement of the child's hand and
generateasequencebasedonFreemanChaincode.
The attributes in this case are the 8connectivity of
the segments by tracking the mouse movements.
Once the data is created SVM was used to
distinguishbetweenthe26letters.

Following the preparations of the dataset, our


proposed method was applied (using 5fold cross
validation)andtheTruepositives(TP),falsepositives
(FP), true negatives (TN) and false negatives (FN)
werecalculated.Theclassificationaccuracyinterms
TP
TP
of Precision
), Recall (
and Accuracy
TP TN

TP FP

TP FN

(
where n in this case is the total number of
the samples. The receiver operating characteristic
(ROC) was also calculated to show the tradeoff
betweenthehitrateandfalsealarmrateovernoisy
channel. Several machine learning techniques were
comparedasshowninFigure3.ItisclearthatSVM
performance (Precision = 0.33, Recall = 0.25, ROC =
0.84) is superior to many machine learning
techniques such as Decision tree (J48), Neural
Network (1NN and 10NN). However, the
performance of the Nave Bayes technique is
equivalenttoSVM.

Precision
Accuracy

on features extracted using Freeman Chain codes.


SVM [3] has been used in many fields and showed
accurate classification performances [46]. In this
case each SVM uniquely learns the properties that
differentiate training handwritten English letters. It
thenlooksforsimilarpropertiesinthetargetletters
tobeidentified.

3. Experimentalwork

Recall

ROC

1
0.8
0.6
0.4
0.2
0
J48

1NN 10NN SVM Nave


bayes

MachineLearningMethod

Figure3:Comparemachinelearningmethods.

4. Conclusion
In this paper, a method for recognizing English
letterswasproposedandevaluated.Themethodhas
a direct application in teaching children letters and
the proper handwriting. The overall accuracy is
considered well enough for such a multiple
classificationtaskof26differentclasses.

References

[1]Jahne,B.(2005).DigitalImageProcessing.6thEd.New
York:Springer.
[2]Gonzales,R.C.andWoods,R.E.(2002).DigitalImage
Processing.2ndEd.UpperSaddleRiver,N.J.:Prentice
Hall,Inc.
[3]NazarZaki,SafaaiDerisandChinK.K.(2003).A
comparisonofquadraticprogrammingsolversinsupport
vectormachinestraining.JurnalTeknologi.Vol.39,pp:
4556.
[4]NazarZaki,SafaaiDerisandRosliIllias(2005).
Applicationofstringkernelsinproteinsequence
classification.AppliedBioinformatics.Vol.4,pp:4552.
[5]NazarZaki,SanjaLazarovaMolnar,WassimElHajj,
PiersCampbell,(2009).Proteinproteininteractionbased
onpairwisesimilarity.BMCBioinformatics.10:150.
[6]NazarZaki,StefanWolfsheimer,GregoryNueland
SawsanKhuri(2011)."ConotoxinProteinClassification
UsingFreeScoresofWordsandSupportVector
Machines",BMCBioinformatics,12:217.

You might also like