%PDF-1.4
%
1 0 obj
<<
/Metadata 2 0 R
/OpenAction 3 0 R
/OutputIntents [4 0 R]
/PageLabels 5 0 R
/Pages 6 0 R
/Type /Catalog
>>
endobj
7 0 obj
<<
/Author (Young Ho Park, Seung Yong Kwon, Tuyen Danh Pham, Kang Ryoung Park, Dae Sik Jeong, Sungsoo Yoon)
/CreationDate (D:20150615180459+08'00')
/Creator (PScript5.dll Version 5.2.2)
/Keywords <62616E6B6E6F7465207265636F676E6974696F6E3B206F6E652D64696D656E73696F6E616C20286C696E65292073656E736F723B207072652D636C617373696669636174696F6E3B200D0A5553442062616E6B6E6F74650D0A>
/ModDate (D:20150615180624+08'00')
/Producer (Acrobat Distiller 10.0.0 \(Windows\))
/Subject (An algorithm for recognizing banknotes is required in many fields, such as banknote-counting machines and automatic teller machines \(ATM\). Due to the size and cost limitations of banknote-counting machines and ATMs, the banknote image is usually captured by a one-dimensional \(line\) sensor instead of a conventional two-dimensional \(area\) sensor. Because the banknote image is captured by the line sensor while it is moved at fast speed through the rollers inside the banknote-counting machine or ATM, misalignment, geometric distortion, and non-uniform illumination of the captured images frequently occur, which degrades the banknote recognition accuracy. To overcome these problems, we propose a new method for recognizing banknotes. The experimental results using two-fold cross-validation for 61,240 United States dollar \(USD\) images show that the pre-classification error rate is 0%, and the average error rate for the final recognition of the USD banknotes is 0.114%.)
/Title (A High Performance Banknote Recognition System Based on a One-Dimensional Visible Light Line Sensor)
/rgid (PB:278792894_AS:251032865341440@1436862307177)
>>
endobj
2 0 obj
<<
/Length 5609
/Subtype /XML
/Type /Metadata
>>
stream
1
B
Acrobat Distiller 10.0.0 (Windows)
banknote recognition; one-dimensional (line) sensor; pre-classification;
USD banknote
PScript5.dll Version 5.2.2
2015-06-15T18:06:24+08:00
2015-06-15T18:04:59+08:00
2015-06-15T18:06:24+08:00
application/pdf
A High Performance Banknote Recognition System Based on a One-Dimensional Visible Light Line Sensor
Young Ho Park, Seung Yong Kwon, Tuyen Danh Pham, Kang Ryoung Park, Dae Sik Jeong, Sungsoo Yoon
An algorithm for recognizing banknotes is required in many fields, such as banknote-counting machines and automatic teller machines (ATM). Due to the size and cost limitations of banknote-counting machines and ATMs, the banknote image is usually captured by a one-dimensional (line) sensor instead of a conventional two-dimensional (area) sensor. Because the banknote image is captured by the line sensor while it is moved at fast speed through the rollers inside the banknote-counting machine or ATM, misalignment, geometric distortion, and non-uniform illumination of the captured images frequently occur, which degrades the banknote recognition accuracy. To overcome these problems, we propose a new method for recognizing banknotes. The experimental results using two-fold cross-validation for 61,240 United States dollar (USD) images show that the pre-classification error rate is 0%, and the average error rate for the final recognition of the USD banknotes is 0.114%.
banknote recognition
one-dimensional (line) sensor
pre-classification
USD banknote
uuid:85511b55-f499-47d1-858f-52ff29e4d22c
uuid:5467d43c-f82b-49c8-853e-92e5221f4c41
endstream
endobj
3 0 obj
<<
/D [8 0 R /FitH -32768]
/S /GoTo
>>
endobj
4 0 obj
<<
/DestOutputProfile 9 0 R
/Info (Coated FOGRA39 \(ISO 12647-2:2004\))
/OutputConditionIdentifier (Coated FOGRA39 \(ISO 12647-2:2004\))
/S /GTS_PDFA1
/Type /OutputIntent
>>
endobj
5 0 obj
<<
/Nums [0 10 0 R]
>>
endobj
6 0 obj
<<
/Count 24
/Kids [11 0 R 12 0 R 13 0 R]
/Type /Pages
>>
endobj
8 0 obj
<<
/Contents 14 0 R
/CropBox [0 0 595.22 842]
/MediaBox [0 0 595.22 842]
/Parent 11 0 R
/Resources 15 0 R
/Rotate 0
/Type /Page
>>
endobj
9 0 obj
<<
/Length 484351
/Filter /FlateDecode
/N 4
>>
stream
hެuP_7"" )` `"ݰ;؛t" "b *؊3Μ3s=3k}Y~f-ª:u 3;7/7&V_`=@
d:^ iyj|BN cี&ָf
r3;k/xknB9 `?y kQ kƻm\֘N\c`kL
n,`݁5l'ŤR >%C܄x}AζMm,lXYٙoP욑Yt.W+ E9 i9^q 3aB \]=ݜCq@Nrҿf$&ɹ_9plXRN 8 -ikK2i6j@V LwL:yN,7j()|U|4<ҫڠ&VmBjo>urVmf:j:+gwe
]vmuO.7e1۲ުؚdShg^AaC
N9G(Gq@dpNp3xT~EXOrdiFrumu
FNSsuz;# hݒM=lcPpp7Olm}wlgvs-}l`hDgKK/z)};w?X#Sg/
_|g/UFUwa`Y/r7nȧmU0STR|4\BVMWTٴeG4k[
#nSӿ]#o ]K=wM]ٻCkd2aڵ̌bHa``odA6܃Clçxu:flUM]_=Wz/
=t!BHS/>1y#j:z쳘_$%YsJ::%15?
.hz+ 0O20C+"G5oct'q|2RBMЗY9AL"~)&>"/!UUZVI1m5TM+mVcݯz{/.1td8uDtu|u&nM.ßpνg{=]d<=-zvv_Njz6{ϖ/}tEv_R{0_INuFVɥ?aIy83Q.OWI55o$kEmҖ՞Z
pc;źYz:
2w73gʸфhz~fZX 6v؛8l=σo=vvvHc%Tk[{N^>Z*~īŐG'N=8};awGG.D-E>!kjlbFι]RSB23Y쒜?ԀF G 9(&w n!ߢ1Xo\
Bh!!Qht9ϖrZtŞIXٗ
JT)iR]Cd#yuZ;p]j
/}н3XxE:4=j1z
=xM[ eSywWff}f??F/r}*x&Z*~^BR>9Cӟ|>^Uܷoxs'_//d3[RF.u=TJQFoUUj
ꓛxћ7/k^Ђoޤ=b[!;tg4b026ZsŘagjWqY9"ymO:@:tQ#G;op^pu~9%:0Xs~O9,t:l83:REF͏I;d{4Yvj\ϴKY#k7DK48Y@(@)H4
GD Pslgʈ!=[,};Î:qC'uBCKq-*Z\¸ң*q|}R/Ӡx)"jmk_uBB7b{K
}\weӐ0yƨ굠1I7o}}p
:=