Automatic Page Analysis For The Creation PDF
Automatic Page Analysis For The Creation PDF
ZHOODVWKHSRRUVFDQQLQJUHVXOWVREWDLQHGEHFDXVHRIORZ
SULQW TXDOLW\ RU GHWHULRUDWLRQ WKURXJK WLPH $QRWKHU
,QWHJUDWHG$OJRULWKPVIRU LPSRUWDQW SUREOHP ZDV WKH UHSHDWHG FKDQJHV LQ OD\RXW
1HZVSDSHU3DJH'HFRPSRVLWLRQDQG KDELWVWKURXJKWLPH
%HDULQJ DOO WKH DERYH LQ PLQG ZH SURFHHGHG LQ
$UWLFOH7UDFNLQJ GHVLJQLQJDQGLPSOHPHQWLQJDVHWRIDOJRULWKPVWKDWFRXOG
LQ HIIHFW DXWRPDWH WKH PDUNXS SURFHGXUH RI SDJH
%*DWRV6/0DQW]DULV.9 VHJPHQWV DQG DOORZ WKURXJK SRVWSURFHVVLQJ RI
&KDQGULQRV$7VLJULV6-3HUDQWRQLV DXWRPDWLFDOO\ VHJPHQWHGSDJHVDUXOHEDVHGDSSURDFKWR
DUWLFOHWUDFNLQJDQGLGHQWLILFDWLRQ
/DPEUDNLV3UHVV6$+H\GHQ6WU :HHYDOXDWHGRXUPHWKRGVLQWKHIUDPHZRUNRIDQ
H[WHQVLYHQHZVSDSHUGLJLWL]DWLRQSURMHFWDWWKH/DPEUDNLV
$WKHQV*UHHFH 3UHVV 6$ 7KH FRPSDQ\ RZQV QHZVSDSHUV UDQJLQJ LQ
EJDW#GROQHWJU SXEOLFDWLRQWLPHIURP WR GDWH DPRXQWLQJ WR D WRWDO
,QVWLWXWHRI,QIRUPDWLFVDQG RI PLOOLRQ SDJHV )RU WKLV ZRUN ZH XVHG DUFKLYDO
FRSLHV RI WKH QHZVSDSHU 72 9,0$ SXEOLVKHG GDLO\
7HOHFRPPXQLFDWLRQV IURPWRDQGZHHNO\WKHUHRI
1DWLRQDO5HVHDUFK&HQWHU³'HPRNULWRV´ 7KLVSDSHULVRUJDQL]HGDVIROORZV,Q6HFWLRQZH
$WKHQV*UHHFH SUHVHQW WKH DOJRULWKPV IRU SDJH VHJPHQWDWLRQ ,Q 6HFWLRQ
VSHU#LLWGHPRNULWRVJU ZH SUHVHQW RXU UXOHEDVHG V\VWHP IRU DUWLFOH
LGHQWLILFDWLRQ 6HFWLRQ KDV H[SHULPHQWDO UHVXOWV ZKLOH
$EVWUDFW7KHFRQYHUVLRQRIQHZVSDSHUSDJHVLQWRGLJLWDO 6HFWLRQFRQFOXGHVWKLVSDSHUDQGVHWVRXWIXWXUHSODQV
UHVRXUFHVLVDQLPSRUWDQWWDVNWKDWJUHDWO\FRQWULEXWHVWR
WKH SUHVHUYDWLRQ DQG DFFHVV WR QHZVSDSHU DUFKLYHV ,Q 3DJH6HJPHQWDWLRQ
WKLV SDSHU DQ LQWHJUDWHG PHWKRGRORJ\ LV SUHVHQWHG IRU
VHJPHQWLQJ QHZVSDSHU SDJH DQG LGHQWLI\LQJ QHZVSDSHU $WWKHSDJHVHJPHQWDWLRQSKDVH WKH QHZVSDSHU LPDJH LV
DUWLFOHV,QDILUVWVWDJHDVXFFHVVLRQRILPDJHSURFHVVLQJ GHFRPSRVHG LQ LWV EDVLF SULQFLSDO FRPSRQHQWV VXFK DV
DQG GRFXPHQW DQDO\VLV DOJRULWKPV LV HPSOR\HG IRU WH[WDUHDVWLWOHV LPDJHV OLQHV HWF 7KH KDSKD]DUG OD\RXW
VHJPHQWLQJ QHZVSDSHU SDJH LPDJHV LQWR YDULRXV REMHFWV RI QHZVSDSHU DUWLFOHV DQG WKH FORVH FRQWDFW RI GLIIHUHQW
WH[WLPDJHVDQGGUDZLQJVWLWOHV$UXOHEDVHGDSSURDFK VHJPHQWV KLQGHUV WKH DSSOLFDWLRQ RI PDQ\ VWDQGDUG SDJH
LVVXEVHTXHQWO\DSSOLHGWRWKHREMHFWVLGHQWLILHGGXULQJWKH VHJPHQWDWLRQDOJRULWKPVHJ>@>@:HSURSRVHDQHZ
SDJH VHJPHQWDWLRQ SKDVH IRU UHFRQVWUXFWLQJ LQGLYLGXDO WHFKQLTXH IRU QHZVSDSHU SDJH VHJPHQWDWLRQ EDVHG RQ
DUWLFOHV ([SHULPHQWDO UHVXOWV REWDLQHG IURP D ODUJH VPHDULQJ DQG ODEHOLQJ RI UHJLRQV DQG RQ JUDGXDO
WHVWEHG RI ROG QHZVSDSHU LVVXHV DUH SUHVHQWHG ZKLFK H[WUDFWLRQ RI LPDJH FRPSRQHQWV LQ WKH IROORZLQJ RUGHU
FOHDUO\ GHPRQVWUDWH WKH DSSOLFDELOLW\ RI RXU LQWHJUDWHG /LQHV LPDJHV DQG GUDZLQJV EDFNJURXQG OLQHV WH[W DQG
DSSURDFKWRVXFFHVVIXOQHZVSDSHUSDJHVHJPHQWDWLRQDQG WLWOH EORFNV %DFNJURXQG OLQHV DUH QDUURZ IRUHJURXQG
LGHQWLILFDWLRQRIQHZVSDSHUDUWLFOHV EODQN VWULSHV EHWZHHQ WH[W FROXPQV ,W LV HVVHQWLDO WR
SUHVHUYH YHUWLFDO EDFNJURXQG OLQHV DV D ERUGHU EHWZHHQ
.H\ZRUGV 3DJH VHJPHQWDWLRQ SDJH OD\RXW DQDO\VLV QHDUO\ WRXFKLQJ WH[W FROXPQV 2XU FRPSRQHQW H[WUDFWLRQ
GRFXPHQW XQGHUVWDQGLQJ UHJLRQ LGHQWLILFDWLRQ DUWLFOH PHWKRGVDUHGHVFULEHGLQWKHVXVEHTXHQWVXEVHFWLRQV
WUDFNLQJQHZVSDSHUSDJHDQDO\VLV
/LQHH[WUDFWLRQ
,QWURGXFWLRQ +RUL]RQWDO DQG YHUWLFDO IRUHJURXQG OLQHV DUH WKH
ILUVWHOHPHQWVWREHLGHQWLILHGEHFDXVHWKH\XVXDOO\DUHWRR
$XWRPDWLF GHFRPSRVLWLRQ RI GLJLWL]HG QHZVSDSHU SDJHV FORVH WR RWKHU NLQGV RI VHJPHQWV KHQFH DOO RWKHU UHJLRQ
FDQ UHVXOW LQ FRVWHIIHFWLYH VROXWLRQV FRQFHUQLQJ WKH FDWHJRULHV WH[W LPDJHV HWF ZLOO EH PRUH HIIHFWLYHO\
WUDQVIRUPDWLRQRISDSHU DUFKLYHV WR GLJLWDO FROOHFWLRQV $ H[WUDFWHG LI OLQHV DUH UHPRYHG IURP WKH RULJLQDO LPDJH
QXPEHURIWHFKQLTXHVKDYHEHHQSURSRVHGLQWKHOLWHUDWXUH 0RUHRYHULWLVHVVHQWLDOWRH[WUDFWKRUL]RQWDODQGYHUWLFDO
GHVFULELQJ DOJRULWKPV WR IDFLOLWDWH DXWRPDWLF SDJH IRUHJURXQGOLQHVEHFDXVHWKH\DUHXVHGDVWDJVIRUDUWLFOH
GHFRPSRVLWLRQ +RZHYHU PDQ\ RI WKHVH DOJRULWKPV DUH LGHQWLILFDWLRQ VHH 6HFWLRQ 0DLQ DSSURDFKHV IRU OLQH
QRW GLUHFWO\ DSSOLFDEOH WR QHZVSDSHU LPDJHV ZKLFK LGHQWLILFDWLRQ DUH EDVHG RQ +RXJK 7UDQVIRUP DV ZHOO DV
SUHVHQW VSHFLDO SUREOHPV 7KH PRVW VLJQLILFDQW SUREOHPV RQ PRUSKRORJLFDO WUDQVIRUPDWLRQV >@ :H SURSRVH D
LGHQWLILHGLQFOXGHWKHFRPSOH[OD\RXWRIQHZVSDSHUSDJHV QHZ WHFKQLTXH EDVHG RQ JUD\VFDOH WUDQVIRUPDWLRQ RI WKH
LQ SDUWLFXODU WKH ROGHVW RQHV ZKHUH WH[W FROXPQV DUH ELQDU\LPDJHDVVLJQLQJ YDOXHV IRU HYHU\ SL[HO DFFRUGLQJ
WRWKHOHQJWKRIWKHKRUL]RQWDORUYHUWLFDOOLQHHYHU\SL[HO GHWHFWHG)RUWKLVUHDVRQZHXVHDQRYHOWHFKQLTXHZKLFK
EHORQJVWR7KLVWHFKQLTXHFRPELQHVIDVWLPSOHPHQWDWLRQ LVEDVHGRQDSUHOLPLQDU\VHDUFKRQO\IRULPDJHVHJPHQWV
ZLWK DFFXUDWH UHVXOWV DQG FDQ EH VXPPDUL]HG LQ WKH ,QWKLVVWDJHRXUREMHFWLYHLVWRGHWHFWFRPSRVLWHUHJLRQV
IROORZLQJVWHSV ZKRVH VXUURXQGLQJ ER[ KHLJKW ZLOO KHOS XV GLVWLQJXLVK
6WHS ,PDJH VXEVDPSOLQJ ZLWK UHVSHFW WR IRUHJURXQG WH[W DQG LPDJH RU GUDZLQJ UHJLRQV 7KHUHIRUH ZH WU\ WR
SL[HOV NHHSWH[WOLQHVVHSDUDWHZKLOHDWWKHVDPHWLPHFRQQHFWLQJ
6WHS )URP WKH UHVXOWLQJ LPDJH ZH H[WUDFW WZR GLIIHUHQW UHJLRQV RI WKH VDPH LPDJH 7KLV LV GRQH E\
JUD\VFDOH LPDJHV ) DQG ) DVVLJQLQJ WR HYHU\
+ 9 VXEVDPSOLQJ WKH LPDJH RQO\ ZLWK UHVSHFW WR EDFNJURXQG
IRUHJURXQG SL[HO WKH OHQJWK RI WKH YHUWLFDO IRU ) RU
9 SL[HOV 7KLV VWDJH RIWHQ VXIILFHV WR GLVWLQJXLVK EHWZHHQ
KRUL]RQWDOOLQHIRU) LWEHORQJVWR
+ WH[W DQG LPDJHV RU GUDZLQJV 5HVXOWV IURP WKH
6WHS /LQHV WKDW DUH LQWHUHVWLQJ WR LGHQWLI\ DUH SUHOLPLQDU\VWDJHDUH LPSURYHG E\ D IXUWKHU FKHFN EDVHG
FKDUDFWHUL]HG E\ DQ D SULRUL NQRZQ PLQLPXP OHQJWK DQG RQ WKH ))7 RI WKH KRUL]RQWDO SURMHFWLRQV RI VHJPHQWHG
PD[LPXP ZLGWK ,PDJHV UHVXOWLQJ IURP VWHS DUH UHJLRQV 7KH DOJRULWKP ZH XVH IRU LPDJH DQG GUDZLQJ
WKUHVKROGHG VR WKDW WKH RQO\ UHPDLQLQJ SL[HOV EHORQJ WR H[WUDFWLRQLVVXPPDUL]HGLQWKHIROORZLQJVWHSV
OLQHV ZKRVH OHQJWKZLGWK DUH UHVSHFWLYHO\ ODUJHUVPDOOHU 6WHS :H HPSOR\ VXEVDPSOLQJ ZLWK UHVSHFW WR
WKDQDWKUHVKROG:HH[WUDFWWKHELQDU\LPDJHV/ DQG)
+ 9 EDFNJURXQGSL[HOV
6WHS /LQHV DUH GHILQHG XVLQJ D &RQWRXU )ROORZLQJ 6WHS )URP WKH UHVXOWLQJ LPDJH ZH H[WUDFW WZR
WHFKQLTXHIRUDOOSRLQWVRI/ DQG)
+ 9 JUD\VFDOH LPDJHV % DQG % UHWXUQLQJ IRU HYHU\
+ 9
7KH SURSRVHG PHWKRG IRU OLQH H[WUDFWLRQ KDV EDFNJURXQG SL[HO WKH OHQJWK RI WKH YHUWLFDO IRU % RU 9
WROHUDQFH WR VOLJKW OLQH VNHZLQJ OLQHV KDYH VXFFHVVLYH KRUL]RQWDO EDFNJURXQG OLQH IRU % LW EHORQJV WR
+
KRUL]RQWDOYHUWLFDOSL[HOVHYHQLIWKH\KDYHDVOLJKWVORSH &DQGLGDWHLPDJHGUDZLQJSRLQWVDUHVLQWKH,'5WDEOH
DQGWRWKHSUHVHQFHRIEURNHQOLQHVGXHWRVXEVDPSOLQJ
ZLWKUHVSHFWWRIRUHJURXQGSL[HOLQIRUPDWLRQ$SSOLFDWLRQ ÙLI %+ [ \<F + Æ%9 [ \<F 9 >@
=Ú
,'5 [ \
RIWKHPHWKRGLVVKRZQLQ)LJ ÛRWKHUZLVH
)RUEDFNJURXQGOLQHH[WUDFWLRQWKHVDPHWHFKQLTXH 3DUDPHWHUV& DQG& FRUUHVSRQGWR PD[LPXPOHQJWKRI
LVDSSOLHGWKLVWLPHZRUNLQJZLWKEDFNJURXQGSL[HOV
+ 9
KRUL]RQWDODQGYHUWLFDOEDFNJURXQGOLQHV
6WHS :H H[WUDFW VHJPHQWV XVLQJ &RQQHFWHG
&RPSRQHQW $QDO\VLV >@ RI WKH LPDJH ,'5 )URP DOO
UHVXOWLQJVHJPHQWVZHVHOHFWWKRVHZLWKVLJQLILFDQWKHLJKW
JUHDWHU WKDQ WKLV RI WKH ODUJHVW H[SHFWHG WLWOH OHWWHU $Q
H[DPSOHIRUWKLVSURFHGXUHLVJLYHQDW)LJ
6WHS)RUHDFKH[WUDFWHGDUHDKRUL]RQWDOSURMHFWLRQVDUH
XVHG %\ DQDO\]LQJ WKHLU ))7 ZH PD\ ILQG GRPLQDQW
IUHTXHQFLHV VLJQLI\LQJ WKH SHULRGLFDO VWUXFWXUH RI D WH[W
UHJLRQ ,I QR GRPLQDQW IUHTXHQFLHV DUH IRXQG WKH
FRUUHVSRQGLQJEORFNLVFODVVLILHGDVLPDJHGUDZLQJ
D E
)LJD2ULJLQDOLPDJHE9HUWLFDODQGKRUL]RQWDOOLQH
H[WUDFWLRQ
,PDJHDQGGUDZLQJH[WUDFWLRQ
D E
7KH SUHVHQFH RI QHDUO\ WRXFKLQJ LPDJHV RU )LJ D 2ULJLQDO LPDJH E ,PDJH ,'5 ZLWK DOO
GUDZLQJV DQG WH[W VHJPHQWV LV YHU\ IUHTXHQW LQ VHJPHQWVGHILQHGXVLQJ&RQQHFWHG&RPSRQHQW$QDO\VLV
QHZVSDSHU SDJHV 7KLV OLPLWV WKH XVHIXOQHVV RI PDQ\
FRPPRQDSSURDFKHVWRLPDJHDQGGUDZLQJLGHQWLILFDWLRQ 7H[WDQG7LWOHEORFNH[WUDFWLRQ
ZKLFKDWWHPSWWRGHWHFWPDMRUFRPSRQHQWEORFNVDQGWKHQ
$W WKLV ILQDO SDJH VHJPHQWDWLRQ VWDJH ZH H[WUDFW
XVH VLPSOH VWDWLVWLFDO WHVWV WR FODVVLI\ WKHP DV WH[W RU
WH[WDQGWLWOHDUHDVIURPWKHUHPDLQLQJLPDJH7LWOHEORFNV
LPDJHV >@>@ )RU H[DPSOH DQ LPDJH DQG LWV
DUHGLVWLQJXLVKHGWR VWDQGDUG WLWOH DQG PDVWHU WLWOH EORFNV
FRUUHVSRQGLQJFDSWLRQPD\LQWHUIHUHDQGEORFNVFDQQRWEH
DFFRUGLQJWROHWWHUKHLJKW:HSURSRVHDQRYHOPHWKRGIRU
WH[W DQG WLWOH EORFN H[WUDFWLRQ ZKLFK LV EDVHG RQ 5/6$ $UWLFOHLGHQWLILFDWLRQDQGUHFRJQLWLRQ
>@>@ZLWKDGDSWLYHSDUDPHWHUV:HILUVWIROORZVWHS
RI VHFWLRQ DQG VWHSV RI VHFWLRQ WR H[WUDFW 7KH RYHUZKHOPLQJ PDMRULW\ RI WKH UHVHDUFKHUV DUH
LPDJHV % DQG % XVLQJ VXEVDPSOLQJ ZLWK UHVSHFW WR
+ 9 DGGUHVVLQJ WKH GRFXPHQW LPDJH XQGHUVWDQGLQJ SUREOHPV
EDFNJURXQGSL[HOVUDWLR:HWKXVHQVXUHWKDWYHUWLFDO IRUVFLHQWLILFMRXUQDOVIRUDQRYHUYLHZVHH-DLQHWDO>@
QHLJKERULQJOHWWHUVZLOOQRWFRQQHFWZKLFKLVHVVHQWLDOIRU 7KHLU UHVXOWV DUH QRW GLUHFWO\ DSSOLFDEOH WR QHZVSDSHUV
GLVFULPLQDWLQJ WH[W DJDLQVW WLWOHV 7KHQ ZH SURFHHG ZLWK ZKLFKKDYHDFRPSOHWHO\GLIIHUHQWDQGFRQVLGHUDEO\PRUH
FRQQHFWHGFRPSRQHQWDQDO\VLVDQGHYHU\IRUHJURXQGSL[HO FRPSOH[SDJHOD\RXW2XUDSSURDFKH[SORLWVWKHVHJPHQW
LVDVVLJQHGDYDOXHDFFRUGLQJWRWKH KHLJKWRI WKH ER[ RI UHODWLRQVKLSVWKDWH[LVWLQWKHSDJHOD\RXWRIDQHZVSDSHU
LWVFRQQHFWHGDUHD,QWKLVZD\VWDUWLQJIURPWKHRULJLQDO 7KHVHUHODWLRQVDUHIRUPXODWHGDVDVHWRIUXOHV$VLPLODU
LPDJH ZH H[WUDFW JUD\VFDOH LPDJH + $IWHU WKLV
6 DSSURDFK LV JLYHQ E\ 1L\RJL >@ +RZHYHU WKH VHW RI
SURFHGXUH HYHU\ SL[HO KDV DQ DSSUR[LPDWH FODVVLILFDWLRQ UXOHV JLYHQ E\ 1L\RJL DUH LQDGHTXDWH WR KDQGOH WKH ODUJH
WR HLWKHU WH[W RU WLWOH DFFRUGLQJ WR LWV JUD\VFDOH YDOXH $W YDULHW\RISDJHOD\RXWRIRXUWHVWEHGFROOHFWLRQ
WKHVDPHWLPHSRVVLEOHUHPDLQLQJLPDJHQRLVHLVUHMHFWHG $IWHU WKH VHJPHQWDWLRQ VWDJH LW LV YHU\ LPSRUWDQW
$ QHZ LPDJH 7 LV H[WUDFWHG ZLWK YDOXHV IRU QRLVH WRDXWRPDWLFDOO\LGHQWLI\WKHDUWLFOHVRQDSDJHVLQFHWKH
6
SL[HOV IRU WH[W SL[HOV IRU VWDQGDUG WLWOH SL[HOV DQG SULPDU\XQLWRILQIRUPDWLRQLQDQHZVSDSHULVWKHDUWLFOH
IRUPDVWHUWLWOHSL[HOV,PDJH 7V LVJLYHQE\WKHIRUPXOD $Q DUWLFOH FRQVLVWV RI D KHDGOLQH DQG D FROOHFWLRQ RI
VHJPHQWVKDYLQJDORJLFDOW\SHDPRQJWKHIROORZLQJVXE
ÙLI +V [ \ < W KHDGOLQHWLWOHWH[WSLFWXUHFDSWLRQDQGUHIHUHQFHV
ÜLI + [ \ W Æ+ [ \ < W 2XU VHW RI UXOHV WULHV WR DFFRPSOLVK WKUHH JRDOV
Ü V V >@ 7KH ILUVW JRDO LV WR GLVWLQJXLVK DPRQJ VHJPHQWV RI WKH
7V [ \ =Ú
Ü LI + V [ \ W Æ + V [ \ < W VDPH W\SH WKRVH WKDW VHSDUDWH DUWLFOHV )RU H[DPSOH
Ü
Û LI + V [ \ W KRUL]RQWDO OLQHV FDQ EH XQGHUOLQHV RU OLQHV WKDW VHSDUDWH
ZKHUHW W W DUHUHVSHFWLYHO\PLQLPXPH[SHFWHGOHWWHU DUWLFOHV7KHVHFRQGJRDOLVWRODEHOPDVWHUWLWOHWLWOHDQG