Fake currency detection using image processing
- 1. JAVAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTA PUR ANANTA PURAMU -5 15002, AP,INDIA Project On Recognition of fake currency using image processing Presented by: 8.Anivinder Reddy M.K.Harik:I B.V.Suma1hl • 18001A0<03 - 18001A0410 • 1900SA0<03 Under the guidanceof Sri . M.Sreedhar Asslst<intPioressor Adhoc o e rtmentof E C E
- 2. Contents: I.Airn orThc Project 2.lntroduction 3.Scopc of 'ork nnd ldcn 4.0vcrvicv of "fhe Project S.f lo'v chan 6.Steps involved 7.fe111urcs involved S.Block diagrnnt 9.RcsultS I O.Novchy of project I I.Advnnu1g<.'-S I 2.Lin1i1ation.. 13.Application.s 14.Conclusions I S.Fu1urc scope 16.Jtcfercnccs
- 3. Aim of tl1e project : ,,. l11e ICChnology of currency rL'tOgniti()n b11sicully '1i1ns ror identifying 11nd CXln1c1ing visible nnd invisible tCatures of cu1TCncy notes. Until no,v,n1any 1echniqucs have been 1>roposed 10 iden1ify 1hc currency nolc. Bui the best vny is 10 use the visible features of the nolc for cxantplc,color and size.
- 4. Introduction: ,. F11kc Currency Note is n 1crnl lhat refers to 1hc counterfeit currency notes thnl rapidly citcula1cd in the econon1y .1l1esc days technology is been groving very fas1. Conscquenlly the bank ing sector is also gcning n1odcm dny by dny. Currency duplic.ot ion nlso knovn as coun1crfcit currencyis a vulnerable 1hrca1on cconon1y. ,. In 1hc proposed n1odcl • acquired image of currency note is checked Vhcthcr it is fake or real on the basis of couJtting the nuntl>cr or intcrn1ptions in the security thread. The can1cra pic1urcs nrc noted and nrudysctlby MATLAB progn1minstalle<Ion computer.
- 5. Problem statement: , ·rhc coun1crfcitcrs novadays, c1n evade Lhe chen1ical propeny & physical t'Ca1ure based counterfeit paper currency dc1ec1ion system due 10 technological advancc1nent. ,. The circulu1ion of u lru'};c t1111ounl of fake cum:ncy i11cn.-:1se.s 1hc :1. 111ounl of money in circula1ion. vhich ntay lead 10 high dc1nond for goods and co1nn1oditics. l11e rise in demand in tum Crt'.Ul<'.S a scarci1y of goods, leading to 1.1 rise in 1hc price of 1hc goods. This leads 10currency devaluation
- 6. Scope of work a1 1d idea: ,. This projccl proposes an app«>•lch that Jill dc1ec1 f;ake currency note being circulatc<I in our cou111ry by using Iheir irnage.Our project viii provide required mobili1y and con,pn1ibi li1y 10 n1os1of the people ond provides credible accurocy for the fnke currency dc1cc1ion. Ve arc using 111nchinc learning to nmkc it portable :ind efficient.
- 7. Overview of tl1e project: , The fnkc currency de1ec1ion using lllachinc lcan1ing '''as in1plenlen1ed on MATLAB. Fc11urcs of currency no1c like serial nu111bcr. security 1hld. ldc111ific-a1ion mnrk. Mnha1n1u Gaodhi ponrJit were CXlntcted. The process suui.;.; rro1n i1nagc ac:quisilion 10 cnlcula1ioll or intensity of each extracted fcuturc.
- 8. Flow chart : lmoge Ac<1uisi1ion l Initial Scgmcn1:uion Gray Scale Con•ersion f(. llurc ex111u::1ion Resuh F•kc"' Real
- 9. Steps involved : ln111ge Acquisition :It is the action of retrieving <lJl irnage fron1source. II goes through Lhe in1agc •bich i.. given as o palh as ;1 in1>ul. II also checks 1hc over rill image vhich is given 11s input. II selects 1hc n.".<lUin.:d fcnturcs 10 proceed for the furlhcr processing. Pre Processing : Pre proc ing i u fon1ili11r nttntc for Opt.:n11ions 'ith in1oges :ti the IO'Ct level of 11bstmction -both input and output arc intensity iinagcs.111c aim of Pre·processing is an iinprovemcnt of the i1nage duta 1ha1 supprcss un,,11n1cd dis1ortions or enhances sonic i1nage fea1urcs: cssentiRI for further processing. , Initial Segn1en1n1ion :In 1his, s1cp VC divide an ilttagc into '31'iou.s p-irts thru have si1nilar auributcs vhich urc called os inuagc objc.-.cts.It is the first stc-1> for inn1gc analysis
- 10. Continuation.. ros1 Proccs'iing :rdjusting c:<po!-urc. contr.Li,I and brighlnt.'$:.. and also udjus1ing colors. hues. loncl), S3turation and light levels. II alsochecks the true and fake pixels of the image. ... Gray Scale Conversion :This i.tep is used 10 enhance 1hc gray i1nilg,C 10e1nphasize di.lrk lin1. ill liglucr background and also helps in checkin the bl11ck strips of the rcnl note • It nlso dc1cc1s cx11c1 ft.-.ntures of the note afler convcrting the itna,gc iruo gray scaling. r feature E'1r:icrion ; Extrncti,. the feature 1h:it nrc nt-.cdcxl 10 be con1p.;1rcd and 10 conclude •hcthcr 1hc note is f{lkc or real . Jn the over all processing each step is ha'ing the unique ·ay of cxtmcting the fca1urcs of the rc-111and fukc note.
- 11. Features involved: ,. Coni rust ; The difference in brighlncss bct'c<:"n light and dark 11rcas of irnngc. Conlrast dctcnnincs the nun1ber of shade$ in 1he i1n11gc. ,. Energy : It is the dist1.1nccs of so111c qu.ality bClVt.-.en the pixels of so1ne locality ,.. l-lu1nogcnci1·: It expresses ho"•' similar ccr1nin clen1cnts(pixcls) of 1h1.; imngc: nrc. Generally on irnngc is hon1ogcnous if each pixel in the in1age hos 1he snn1ccolor . , lenn :Mean value is the sun1of pixel values divided by the total number of 1>ixel values. ,. En1ropy : Entropy is a rncasurc of inu1ge infom1;11ion con1en1. Vhich is in1erpre1ed ns the avemge unccnainity of infom1a1ion source. It is defined as corresponding stales of intcnsily level Vhich individua l pixelsc-an nd:tJ>L
- 12. Block Diagra1 n: .... , _ EXTRACTIN O FEATURE S ln 1 ng c User DISPlA Y RESUL TS Oata SCI SVM INPUT Pn. Processing Grey Scale Conversion Edge Dc1cc1ion Scg.111cnlntio n
- 13. Co1 1tinuation: , RlIS : To gc1 an cs1in1n1c of the sin1ilarity bctvccn source in1agc nnd the scgmcnlcd i1nagc, VC use rool n1can square error.Using 1his the da1a can be divided by best lil 10 find ou1 hov conccrunucd nn image is. , S1:i11durd d('!i:ltion : Standard deviation or the irnngc implies a l_;T'OS!; lllCJISUrc or 1hc irnprt'Cision or vari111ion :1bout the target value of liglu in1cnsi1y ut c.1tch such data point ,. f:1rinncl' :The variance gi ves an idea hOY 1111:pixel volues arc spread. , Srnoocbncss:Smoo1hncss 111casurcs the relative !'n1001h11ess of intensity in a region. II is high for a region of co11s:u1n1iruen!'ity and IO' for regions 'ilh lorgcexcursions in the >alucs of i1.s in1cns:i1y levels. , I OJ1: Inverse Difference Mon1cnt is usually called hon1ogcnci1y lhat n1casurcs the local hon1ogcnchy ornn i1nage
- 14. Technique used: Sup1>or1 V ctor Machine , Support f<".ClOr Machine or SVM is one or1he n1ost popul11r Supervised Le.urning algori1hn1s. 'vhich is t•S<'.<I for Classificotion os VCll as Regression problcn,is. ,. Slpport ve<:tor nu1chinC$ (SVf1s) urc a set of supervised le.urni ngn1cthods us(.-.d for cl11ssifica1ion,regressio11aod outliers: det(."(;t ioo. - The advantag<'.S of support vcc lor machines arc:6ffcc1ivc in high dimensional SJN CC$. S1ill cff<. tivc in cases ''here nun1bcr ordintcnsions ls greater thnn the number of sru11plcs.
- 15. Results: Genuine note: - I r.. . I " I - • • • figure. OriginiL Iin1 ag.c Figure. IISV image --" ' . . ./ " r . I ' , ' Figure. 13' in1 :1 g._, Figure. Genuine in1 :1 ge
- 16. Fnkc note: Figu . 1 - ISV image .... Ftgun:. fake im.igc
- 17. Novelty of project: ... De1ec1ion of ahc f.1ke currency note i.s done by couoting the nun1ber of in1crru1nioni.> in the thrc.ad line. , Predicts 1hcther the note isreal or f'.lkc on the basb of number of in1crru1>tions. , I I'the number of intcm.iplion is 1.cro. 1hcn it is real note othcn'isc it is fake note. And :also we calculate the cn1ro1>Y of the currency no1es ror the cnicicn1 detection of Cake currency note. ,. MATLAB sofh•nrcis usc'.d to detect the fake currcnc}'note.
- 18. Advantages: ,. Simplicity , Rcmov;i1 I orunncocss.uryda1 n in imngc
- 19. Limitations: , lnpul lirniltuion ... Accuracy ... Lighting limi1 ation
- 20. Applications: , Fake currency dc1 cc1on systcrn can be ut lized in shops. b:1 nk cou1ltcrs und in co1 npu1crized 1 cllcr 1 nachinc. auto n1 crchan11 11nchines and soon. , l l1c systenis nrc created utilizing diverse techniques and ulgorithrns.
- 21. Conclusion : , l11e survival of 1he financial sy111111etry n1ay be affected Yit h its value, rapidity.ou 1pul and •cllbcing by counterfeiting of b;1nk notes. ,. Vhh improvcmcn1 of rcccn1 banking scl'•iccs. au1on1n1ic methods for paper currency recognition bl!COnH!vital in nu1ny upplica1ions such a.,.:; in ATI and tn1101nn 1ic goods seller 111t1chines. ,. TI1c sys-tc111 hos a best pcrfon1u•ncc for both agreeing valid banknotes and deleting invalid duta. h nlso shOVS 1he techniques lOr currency rccog.ni1ion us ng in1agc processing. , 111eIndian c.urrency no1es have been identif ed and c-0un 1erfeit 1101cs ha...:; been found.ll1isVUtkis done by using various filters. This n1cthod is very rosy 10 in1plcn1cn1 in rcnl 1in1c Vorld. Al las1 VC have concluded 1hn 1 if 'c propose son1c eflicient preprocessing and feature cx1mc1ion n1cthod 1hcn 'c can inlprovc 1hc accuracy of idcntificotion system..Ve con nlsodevelop ap1> for detcetion of f1.-k c currency.
- 22. Futt1re scope: Many difl'crcnl :idnptations.1csts and innovations have been kepi for the future due 10 1he lack of ti11lc. As fu1·ure'1ork concen s deeper nnalysis or panicular nlechaoisntS. ne'v proposals 10 1ry <lifTerc111 methods or sirnplc curiosity. ,. I . In fut ure VC VOu ld be including u 1n001.1lc for currency conversion. ,. 2.'ecan iinplc111en1the sys1e1n for foreign currencies. ,. 3.Tn:1cking of device's loc.ation through Vh ich the currency is scanned and maintaining the san1c in 1hcd.atabasc.
- 23. References ,.. Megha· 1 1uLkur andAn1 ri1 Kaur, "V t1rious Fake C"11rro11t 1 ,• /)ett!ttlo1 1lt!t·/1 1 1iq11(s" ,lrucma1onal Journal for T echnologicnl Research In Engint::cring. vol. 1.no. 11,July 2014.. , B R Knvy• •nd B Dc,<endnm , "IND/AN CURRENCYDETECTION1 IND DENOMINATION USING SIFT', ln1cma1ionalJoumnl of Science EngineeringandTechnology Jtcscarch. vol. 4, no. 6. June 2015. ,,. V , K. El Said, *F akeEg,• 1 11 1 '< 11 1C 'urr enc)'D(•1e c1io1 1S J· ste1 1 11 1 si11 g T erture < 11 1 1 / SJ1 1 1 pe Clu1r1 1tterisric s", huema1ional Journal of Coolputcl' 1 - pplicatioos (0975 - 8887), vol. 143. no. 2, JuJle 201 6•• ,.. Binod Prasad yadav.C.S patil,R.lt Karhc,P .H patii - " HSI' Tecl1 1 1iq11cb)1 using 1 1 .1 11'1.AB'"The fokc cuJTency is detL -cted 1 1 1 ununlly.
- 24. THANK YOU!!!