A fast and robust feature-based 3D algorithm using compressed image correlation

Two objectives of 3D computer vision are high processing speed and precise recovery of object boundaries. This paper addresses these issues by presenting an algorithm that combines feature-based 3D matching with Compressed Image Correlation. The algorithm uses an image compression scheme that retain...

Full description

Saved in:

Bibliographic Details
Published in:	Pattern recognition letters Vol. 26; no. 11; pp. 1620 - 1631
Main Authors:	Tan, Sheng S., Hart, Douglas P.
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 01.08.2005
Subjects:	3D vision Adaptive window Compressed image correlation Feature matching Gradient-based compression Feature matching Gradient-based compression 3D vision Adaptive window Compressed image correlation
ISSN:	0167-8655, 1872-7344
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Two objectives of 3D computer vision are high processing speed and precise recovery of object boundaries. This paper addresses these issues by presenting an algorithm that combines feature-based 3D matching with Compressed Image Correlation. The algorithm uses an image compression scheme that retains pixel values in high intensity gradient areas while eliminating pixels with little correlation information in smooth surface regions. The remaining pixels are stored in sparse format along with their relative locations encoded into 32-bit words. The result is a highly reduced image data set containing distinct features at object boundaries. Consequently, far fewer memory calls and data entry comparisons are required to accurately determine edge movement. In addition, by utilizing an error correlation function, pixel comparisons are made through single integer calculations eliminating time consuming multiplication and floating point arithmetic. Thus, this algorithm typically results in much higher correlation speeds than spectral correlation and SSD algorithms. Unlike the traditional fixed window sorting scheme, adaptive correlation window positioning is implemented by dynamically placing object boundaries at the center of each correlation window. Processing speed is further improved by compressing and correlating the images in only the direction of disparity motion between frames. Test results on both simulated disparities and real motion image pair are presented.
AbstractList	Two objectives of 3D computer vision are high processing speed and precise recovery of object boundaries. This paper addresses these issues by presenting an algorithm that combines feature-based 3D matching with Compressed Image Correlation. The algorithm uses an image compression scheme that retains pixel values in high intensity gradient areas while eliminating pixels with little correlation information in smooth surface regions. The remaining pixels are stored in sparse format along with their relative locations encoded into 32-bit words. The result is a highly reduced image data set containing distinct features at object boundaries. Consequently, far fewer memory calls and data entry comparisons are required to accurately determine edge movement. In addition, by utilizing an error correlation function, pixel comparisons are made through single integer calculations eliminating time consuming multiplication and floating point arithmetic. Thus, this algorithm typically results in much higher correlation speeds than spectral correlation and SSD algorithms. Unlike the traditional fixed window sorting scheme, adaptive correlation window positioning is implemented by dynamically placing object boundaries at the center of each correlation window. Processing speed is further improved by compressing and correlating the images in only the direction of disparity motion between frames. Test results on both simulated disparities and real motion image pair are presented.
Author	Tan, Sheng S. Hart, Douglas P.
Author_xml	– sequence: 1 givenname: Sheng S. surname: Tan fullname: Tan, Sheng S. email: shtan@alum.mit.edu – sequence: 2 givenname: Douglas P. surname: Hart fullname: Hart, Douglas P.
BookMark	eNp9kM1qwzAQhEVJoUnaN-hBL2B3JVm2fCmE9BcCubRnIUurVCGxg2QX-vZVSM897bI7Mwzfgsz6oUdC7hmUDFj9sC9PZoxoSw4gS2AlQHtF5kw1vGhEVc3IPMuaQtVS3pBFSnsAqEWr5mS7ot6kkZre0Th0U149mnGKWHQmoaPiiZrDbohh_DrSKYV-R-1wPEVM5284mh3mQ4x4MGMY-lty7c0h4d3fXJLPl-eP9Vux2b6-r1ebwnIpx8JJ62SnpKikcqIB3jklvOO1aQFNJ5XgrlZd61trrFBOSe7BYyVa45W0tViS6pJr45BSRK9PMZeJP5qBPkPRe32Bos9QNDCdoWTb48WGudt3wKiTDdhbdCFLR-2G8H_ALxZnb48
Cites_doi	10.1023/A:1008183703117 10.1109/34.16709 10.1109/TPAMI.2002.1017620 10.1115/1.2820685 10.1109/34.310690 10.1145/383259.383310 10.1109/TPAMI.2002.1008383 10.1109/76.767125 10.1023/A:1014510328154 10.1109/TPAMI.2003.1177151 10.1023/A:1014573219977 10.1109/34.254061 10.1109/34.49055 10.1016/S0022-5347(05)65162-2 10.1007/BFb0014872 10.1109/TPAMI.2003.1190570 10.1109/TPAMI.2002.1017621
ContentType	Journal Article
Copyright	2005 Elsevier B.V.
Copyright_xml	– notice: 2005 Elsevier B.V.
DBID	AAYXX CITATION
DOI	10.1016/j.patrec.2005.01.009
DatabaseName	CrossRef
DatabaseTitle	CrossRef
DatabaseTitleList
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	1872-7344
EndPage	1631
ExternalDocumentID	10_1016_j_patrec_2005_01_009 S0167865505000188
GroupedDBID	--K --M .DC .~1 0R~ 123 1B1 1RT 1~. 1~5 29O 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABFNM ABFRF ABJNI ABMAC ABXDB ABYKQ ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADMXK ADTZH AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q G8K GBLVA GBOLZ HLZ HVGLF HZ~ IHE J1W JJJVA KOM LG9 LY1 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SBC SDF SDG SDP SDS SES SEW SPC SPCBC SST SSV SSZ T5K TN5 UNMZH VOH WH7 WUQ XFK XPP Y6R ZMT ~G- 9DU AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD
ID	FETCH-LOGICAL-c255t-d5cd5b853458d3702bd83fd26a90eab5832d68b9f9cac38d852f0fe439af85c63
ISICitedReferencesCount	3
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000230052300002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0167-8655
IngestDate	Sat Nov 29 06:43:27 EST 2025 Fri Feb 23 02:34:03 EST 2024
IsPeerReviewed	true
IsScholarly	true
Issue	11
Keywords	Feature matching Gradient-based compression 3D vision Adaptive window Compressed image correlation
Language	English
License	https://www.elsevier.com/tdm/userlicense/1.0
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c255t-d5cd5b853458d3702bd83fd26a90eab5832d68b9f9cac38d852f0fe439af85c63
PageCount	12
ParticipantIDs	crossref_primary_10_1016_j_patrec_2005_01_009 elsevier_sciencedirect_doi_10_1016_j_patrec_2005_01_009
PublicationCentury	2000
PublicationDate	2005-08-01
PublicationDateYYYYMMDD	2005-08-01
PublicationDate_xml	– month: 08 year: 2005 text: 2005-08-01 day: 01
PublicationDecade	2000
PublicationTitle	Pattern recognition letters
PublicationYear	2005
Publisher	Elsevier B.V
Publisher_xml	– name: Elsevier B.V
References	Hart (bib7) 1998; 120 Izquierdo (bib11) 1999; 9 Maciel, Costeira (bib13) 2003; 25 Sharma, Dragoi, Tenenbaum, Miller, Sur (bib21) 2003; 300 Elder (bib5) 1999; 34 Mahamud, Williams, Thornber, Xu (bib14) 2003; 25 Mansouri (bib15) 2002; 24 Horn (bib9) 1986 Kanade, Okutomi (bib12) 1994; 16 Gao, Leung (bib6) 2002; 24 Brunelli, Poggio (bib2) 1993; 15 Scharstein, Szeliski (bib20) 2002; 47 Okutomi, Katayama, Oka (bib17) 2002; 47 Drummond, Cipolla (bib4) 2002; 24 Deriche, R., Faugeras, O.D., 1990. Tracking line segments. European Conference on Computer Vision (ECCV’90), Antibes, France, Springer 1990 Oh, B.M., Chen, M., Dorsey, J., Durand, F., 2001. Image-based modeling and photo editing. SIGGRAPH 2001 Hoznek, Zaki, Samadi, Salomon, Lobontiu, Lang, Abbou (bib10) 2002; 167 Olsen (bib18) 1990; 12 Bartoli, A., Hartley, R., Kahl, F., 2003. Motion from 3D line correspondences: Linear and non-linear solutions. IEEE Internat. Conf. on Computer Vision and Pattern Recognition (CVPR’03), Madison, Wisconsin Roth, G., Hart, D.P., Katz, J., 1995. Feasibility of using the L64720 video motion estimation processor (MEP) to increase efficiency of velocity map generation for particle image velocimetry (PIV). ASME/JSME Fluids Engineering and laser Anemometry Conference, Hilton Head, South Carolina Hoff, Ahuja (bib8) 1989; 11 Maciel (10.1016/j.patrec.2005.01.009_bib13) 2003; 25 Mansouri (10.1016/j.patrec.2005.01.009_bib15) 2002; 24 Hart (10.1016/j.patrec.2005.01.009_bib7) 1998; 120 Mahamud (10.1016/j.patrec.2005.01.009_bib14) 2003; 25 10.1016/j.patrec.2005.01.009_bib19 Olsen (10.1016/j.patrec.2005.01.009_bib18) 1990; 12 Hoff (10.1016/j.patrec.2005.01.009_bib8) 1989; 11 10.1016/j.patrec.2005.01.009_bib16 Horn (10.1016/j.patrec.2005.01.009_bib9) 1986 10.1016/j.patrec.2005.01.009_bib1 Elder (10.1016/j.patrec.2005.01.009_bib5) 1999; 34 Okutomi (10.1016/j.patrec.2005.01.009_bib17) 2002; 47 Kanade (10.1016/j.patrec.2005.01.009_bib12) 1994; 16 Brunelli (10.1016/j.patrec.2005.01.009_bib2) 1993; 15 Izquierdo (10.1016/j.patrec.2005.01.009_bib11) 1999; 9 10.1016/j.patrec.2005.01.009_bib3 Sharma (10.1016/j.patrec.2005.01.009_bib21) 2003; 300 Drummond (10.1016/j.patrec.2005.01.009_bib4) 2002; 24 Hoznek (10.1016/j.patrec.2005.01.009_bib10) 2002; 167 Gao (10.1016/j.patrec.2005.01.009_bib6) 2002; 24 Scharstein (10.1016/j.patrec.2005.01.009_bib20) 2002; 47
References_xml	– volume: 47 start-page: 261 year: 2002 end-page: 273 ident: bib17 article-title: A simple stereo algorithm to recover precise object boundaries and smooth surfaces publication-title: Internat. J. Comput. Vision – volume: 16 start-page: 920 year: 1994 end-page: 932 ident: bib12 article-title: A stereo matching algorithm with an adaptive window: Theory and experiment publication-title: IEEE Trans. Pattern Anal. Machine Intell. – volume: 300 start-page: 1758 year: 2003 end-page: 1763 ident: bib21 article-title: V1 Neurons signal acquisition of an internal representation of stimulus location publication-title: Sci. Mag. – volume: 15 start-page: 1042 year: 1993 end-page: 1052 ident: bib2 article-title: Face recognition: Features versus templates publication-title: IEEE Trans. Pattern Anal. Machine Intell. – volume: 24 start-page: 932 year: 2002 end-page: 946 ident: bib4 article-title: Real-time visual tracking of complex structures publication-title: IEEE Trans. Pattern Anal. Machine Intell. – reference: Roth, G., Hart, D.P., Katz, J., 1995. Feasibility of using the L64720 video motion estimation processor (MEP) to increase efficiency of velocity map generation for particle image velocimetry (PIV). ASME/JSME Fluids Engineering and laser Anemometry Conference, Hilton Head, South Carolina – volume: 24 start-page: 764 year: 2002 end-page: 779 ident: bib6 article-title: Face recognition using line edge map publication-title: IEEE Trans. Pattern Anal. Machine Intell. – volume: 167 start-page: 1604 year: 2002 end-page: 1606 ident: bib10 article-title: Robotic assisted kidney transplantation: An initial experience publication-title: J. Urology – volume: 24 start-page: 947 year: 2002 end-page: 961 ident: bib15 article-title: Region tracking via level set PDEs without motion computation publication-title: IEEE Trans. Pattern Anal. Machine Intell. – year: 1986 ident: bib9 article-title: Robot vision – reference: Deriche, R., Faugeras, O.D., 1990. Tracking line segments. European Conference on Computer Vision (ECCV’90), Antibes, France, Springer 1990 – volume: 11 start-page: 121 year: 1989 end-page: 136 ident: bib8 article-title: Surfaces from stereo: Integrating feature matching, disparity estimation, and contour detection publication-title: IEEE Trans. Pattern Anal. Machine Intell. – reference: Oh, B.M., Chen, M., Dorsey, J., Durand, F., 2001. Image-based modeling and photo editing. SIGGRAPH 2001 – volume: 25 start-page: 433 year: 2003 end-page: 444 ident: bib14 article-title: Segmentation of multiple salient closed contours from real images publication-title: IEEE Trans. Pattern Anal. Machine Intell. – volume: 9 start-page: 589 year: 1999 end-page: 607 ident: bib11 article-title: Disparity segmentation analysis: Matching with an adaptive window and depth-driven segmentation publication-title: IEEE Trans. Circuits Syst Video Technol – volume: 34 start-page: 97 year: 1999 end-page: 122 ident: bib5 article-title: Are edges incomplete? publication-title: Internat. J. Comput. Vision – reference: Bartoli, A., Hartley, R., Kahl, F., 2003. Motion from 3D line correspondences: Linear and non-linear solutions. IEEE Internat. Conf. on Computer Vision and Pattern Recognition (CVPR’03), Madison, Wisconsin – volume: 47 start-page: 7 year: 2002 end-page: 42 ident: bib20 article-title: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms publication-title: Internat. J. Comput. Vision – volume: 12 start-page: 309 year: 1990 end-page: 315 ident: bib18 article-title: Stereo correspondence by surface reconstruction publication-title: IEEE Trans. Pattern Anal. Machine Intell. – volume: 120 start-page: 463 year: 1998 end-page: 470 ident: bib7 article-title: High-speed PIV analysis using compressed image correlation publication-title: J. Fluids Eng—Trans. ASME – volume: 25 start-page: 187 year: 2003 end-page: 199 ident: bib13 article-title: A global solution to sparse correspondence problems publication-title: IEEE Trans. Pattern Anal. Machine Intell. – volume: 34 start-page: 97 issue: 2–3 year: 1999 ident: 10.1016/j.patrec.2005.01.009_bib5 article-title: Are edges incomplete? publication-title: Internat. J. Comput. Vision doi: 10.1023/A:1008183703117 – volume: 11 start-page: 121 issue: 2 year: 1989 ident: 10.1016/j.patrec.2005.01.009_bib8 article-title: Surfaces from stereo: Integrating feature matching, disparity estimation, and contour detection publication-title: IEEE Trans. Pattern Anal. Machine Intell. doi: 10.1109/34.16709 – volume: 24 start-page: 932 issue: 7 year: 2002 ident: 10.1016/j.patrec.2005.01.009_bib4 article-title: Real-time visual tracking of complex structures publication-title: IEEE Trans. Pattern Anal. Machine Intell. doi: 10.1109/TPAMI.2002.1017620 – volume: 120 start-page: 463 issue: 3 year: 1998 ident: 10.1016/j.patrec.2005.01.009_bib7 article-title: High-speed PIV analysis using compressed image correlation publication-title: J. Fluids Eng—Trans. ASME doi: 10.1115/1.2820685 – volume: 16 start-page: 920 issue: 9 year: 1994 ident: 10.1016/j.patrec.2005.01.009_bib12 article-title: A stereo matching algorithm with an adaptive window: Theory and experiment publication-title: IEEE Trans. Pattern Anal. Machine Intell. doi: 10.1109/34.310690 – ident: 10.1016/j.patrec.2005.01.009_bib16 doi: 10.1145/383259.383310 – volume: 24 start-page: 764 issue: 6 year: 2002 ident: 10.1016/j.patrec.2005.01.009_bib6 article-title: Face recognition using line edge map publication-title: IEEE Trans. Pattern Anal. Machine Intell. doi: 10.1109/TPAMI.2002.1008383 – volume: 9 start-page: 589 issue: 4 year: 1999 ident: 10.1016/j.patrec.2005.01.009_bib11 article-title: Disparity segmentation analysis: Matching with an adaptive window and depth-driven segmentation publication-title: IEEE Trans. Circuits Syst Video Technol doi: 10.1109/76.767125 – volume: 47 start-page: 261 issue: 1–3 year: 2002 ident: 10.1016/j.patrec.2005.01.009_bib17 article-title: A simple stereo algorithm to recover precise object boundaries and smooth surfaces publication-title: Internat. J. Comput. Vision doi: 10.1023/A:1014510328154 – volume: 25 start-page: 187 issue: 2 year: 2003 ident: 10.1016/j.patrec.2005.01.009_bib13 article-title: A global solution to sparse correspondence problems publication-title: IEEE Trans. Pattern Anal. Machine Intell. doi: 10.1109/TPAMI.2003.1177151 – volume: 47 start-page: 7 issue: 1–3 year: 2002 ident: 10.1016/j.patrec.2005.01.009_bib20 article-title: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms publication-title: Internat. J. Comput. Vision doi: 10.1023/A:1014573219977 – volume: 15 start-page: 1042 issue: 10 year: 1993 ident: 10.1016/j.patrec.2005.01.009_bib2 article-title: Face recognition: Features versus templates publication-title: IEEE Trans. Pattern Anal. Machine Intell. doi: 10.1109/34.254061 – ident: 10.1016/j.patrec.2005.01.009_bib19 – volume: 12 start-page: 309 issue: 3 year: 1990 ident: 10.1016/j.patrec.2005.01.009_bib18 article-title: Stereo correspondence by surface reconstruction publication-title: IEEE Trans. Pattern Anal. Machine Intell. doi: 10.1109/34.49055 – volume: 167 start-page: 1604 issue: 4 year: 2002 ident: 10.1016/j.patrec.2005.01.009_bib10 article-title: Robotic assisted kidney transplantation: An initial experience publication-title: J. Urology doi: 10.1016/S0022-5347(05)65162-2 – ident: 10.1016/j.patrec.2005.01.009_bib3 doi: 10.1007/BFb0014872 – ident: 10.1016/j.patrec.2005.01.009_bib1 – year: 1986 ident: 10.1016/j.patrec.2005.01.009_bib9 – volume: 300 start-page: 1758 year: 2003 ident: 10.1016/j.patrec.2005.01.009_bib21 article-title: V1 Neurons signal acquisition of an internal representation of stimulus location publication-title: Sci. Mag. – volume: 25 start-page: 433 issue: 4 year: 2003 ident: 10.1016/j.patrec.2005.01.009_bib14 article-title: Segmentation of multiple salient closed contours from real images publication-title: IEEE Trans. Pattern Anal. Machine Intell. doi: 10.1109/TPAMI.2003.1190570 – volume: 24 start-page: 947 issue: 7 year: 2002 ident: 10.1016/j.patrec.2005.01.009_bib15 article-title: Region tracking via level set PDEs without motion computation publication-title: IEEE Trans. Pattern Anal. Machine Intell. doi: 10.1109/TPAMI.2002.1017621
SSID	ssj0006398
Score	1.7751212
Snippet	Two objectives of 3D computer vision are high processing speed and precise recovery of object boundaries. This paper addresses these issues by presenting an...
SourceID	crossref elsevier
SourceType	Index Database Publisher
StartPage	1620
SubjectTerms	3D vision Adaptive window Compressed image correlation Feature matching Gradient-based compression
Title	A fast and robust feature-based 3D algorithm using compressed image correlation
URI	https://dx.doi.org/10.1016/j.patrec.2005.01.009
Volume	26
WOSCitedRecordID	wos000230052300002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1872-7344 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0006398 issn: 0167-8655 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELag5QAHHgVEC0U-cIuycuI4sY8rWtRWqKzEIu0tcvygW22z1T5Qf37HsfOoWiFA4hJFXjmJZr6d-TKZB0KfLNVCZ7KK84qoOFMqjSXnGv7xVZXb3MBq0zL_a3F-zmczMQmh7HUzTqCoa35zI67_q6phDZTtSmf_Qt3dRWEBzkHpcAS1w_GPFD-OrFyHvPFltYVTa5runbHzWDqiR5Fc_Fyu5puLq2jbFt02-bDw6_zKJfEoN7Nj0SstsNdJ04zTFcCErCOAzqKpB-qY-TQEVC-M6_Q96g2cLw0KfD2ajO6EG1iX7BZiYPfqYHxYEsytK3H1XsWbUl4Ad6e-u2Nra311fIupZGA5kzwlAy8MNDF50ML7YMPlyH0qMCoExZIRIaL3aF2e4Xf3YO65iJv7kHD-GO2mBRNgwXfHp8ezs85pA1HjbRt4t6GtsmxSAe_f62EWM2Am05foeXilwGMPhVfokan30It2XAcO1nsPPRv0nnyNvo2xwwkGnGCPE3wHJ5ge4Q4nuMEJ7nGCG5zgAU7eoB9fjqefT-IwXSNW8Bq5iTVTmlXA1jLGNS1IWmlOrU5zKYiRFQNTr3NeCSuUVJRrzlJLrAECKy1nKqdv0U69rM07hE0iQcKKWa2yTBVWsqywRriP3Dohku6juJVWee2bqJRtduFl6aXr5qGykiQlSHcfFa1Iy0AEPcErAQW_3Xnwzzvfo6c93D-gnc1qaw7RE_VrM1-vPga43AIxVYUf
linkProvider	Elsevier
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+fast+and+robust+feature-based+3D+algorithm+using+compressed+image+correlation&rft.jtitle=Pattern+recognition+letters&rft.au=Tan%2C+Sheng+S.&rft.au=Hart%2C+Douglas+P.&rft.date=2005-08-01&rft.pub=Elsevier+B.V&rft.issn=0167-8655&rft.eissn=1872-7344&rft.volume=26&rft.issue=11&rft.spage=1620&rft.epage=1631&rft_id=info:doi/10.1016%2Fj.patrec.2005.01.009&rft.externalDocID=S0167865505000188
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0167-8655&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0167-8655&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0167-8655&client=summon