3D Scene interpretation by combining probability theory and logic: The tower of knowledge

► Linguistically inspired reasoning architecture. ► Generic framework for combining logic and conventional statistical pattern recognition. ► Generic framework for incorporating dynamic and static input. ► Application to 3D scene interpretation. We explore a newly proposed system architecture, calle...

Full description

Saved in:

Bibliographic Details
Published in:	Computer vision and image understanding Vol. 115; no. 11; pp. 1581 - 1596
Main Authors:	Xu, Mai, Petrou, Maria
Format:	Journal Article
Language:	English
Published:	Amsterdam Elsevier Inc 01.11.2011 Elsevier
Subjects:	Applied sciences Architecture Artificial intelligence Computer science; control theory; systems Exact sciences and technology Labelling Labels Logic Logic and probabilities Machine learning Mathematical analysis Mathematical models Pattern recognition. Digital image processing. Computational geometry Scene labelling systems System architecture Three dimensional models Logic and probabilities System architecture Scene labelling systems Machine learning Statistical analysis Probabilistic approach Utility function Labelling Inference Logical programming Modeling Multiple image Multiple view Utility theory Scene analysis Bayes network Probability learning Tridimensional image Maximum likelihood Artificial intelligence
ISSN:	1077-3142, 1090-235X
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	► Linguistically inspired reasoning architecture. ► Generic framework for combining logic and conventional statistical pattern recognition. ► Generic framework for incorporating dynamic and static input. ► Application to 3D scene interpretation. We explore a newly proposed system architecture, called tower of knowledge (ToK), in the context of labelling components of building scenes. The ToK architecture allows the incorporation of statistical feature distributions and logic rules concerning the definition of a component, within a probabilistic framework. The maximum likelihood method of label assignment is modified by being multiplied with a function, called utility function, that expresses the information coming from the logic rules programmed to the system. The logic rules are designed to define an object/component by answering the questions “why” and “how”, referring to the actions in which a particular object may be observed to participate and the characteristics it should have in order to be able to participate in these actions. Two sets of measurements are assumed to be available: those made initially for all components routinely, and which supply the initial statistically based inference of possible labels of each component, and those that are made in order to confirm or deny a particular characteristic of the component that would allow it to participate in a specific action. A recursive version of the architecture is also proposed, in which the distributions of the former types of measurement may be learnt in the process, having no training data at all. Multi-view images are used as input to the system, which uses standard techniques to build the 3D models of the buildings. The system is tested on labelling the components of 10 3D models of buildings. The components are identified either manually, or fully automatically. The results are compared with those obtained by expandable Bayesian networks. The recursive version of ToK proves to be able to cope very well even without any training data, where it learns the characteristics of the various components by simply applying the pre-programmed logic rules that connect labels, actions and attributes.
AbstractList	► Linguistically inspired reasoning architecture. ► Generic framework for combining logic and conventional statistical pattern recognition. ► Generic framework for incorporating dynamic and static input. ► Application to 3D scene interpretation. We explore a newly proposed system architecture, called tower of knowledge (ToK), in the context of labelling components of building scenes. The ToK architecture allows the incorporation of statistical feature distributions and logic rules concerning the definition of a component, within a probabilistic framework. The maximum likelihood method of label assignment is modified by being multiplied with a function, called utility function, that expresses the information coming from the logic rules programmed to the system. The logic rules are designed to define an object/component by answering the questions “why” and “how”, referring to the actions in which a particular object may be observed to participate and the characteristics it should have in order to be able to participate in these actions. Two sets of measurements are assumed to be available: those made initially for all components routinely, and which supply the initial statistically based inference of possible labels of each component, and those that are made in order to confirm or deny a particular characteristic of the component that would allow it to participate in a specific action. A recursive version of the architecture is also proposed, in which the distributions of the former types of measurement may be learnt in the process, having no training data at all. Multi-view images are used as input to the system, which uses standard techniques to build the 3D models of the buildings. The system is tested on labelling the components of 10 3D models of buildings. The components are identified either manually, or fully automatically. The results are compared with those obtained by expandable Bayesian networks. The recursive version of ToK proves to be able to cope very well even without any training data, where it learns the characteristics of the various components by simply applying the pre-programmed logic rules that connect labels, actions and attributes. We explore a newly proposed system architecture, called tower of knowledge (ToK), in the context of labelling components of building scenes. The ToK architecture allows the incorporation of statistical feature distributions and logic rules concerning the definition of a component, within a probabilistic framework. The maximum likelihood method of label assignment is modified by being multiplied with a function, called utility function, that expresses the information coming from the logic rules programmed to the system. The logic rules are designed to define an object/component by answering the questions 'why' and 'how', referring to the actions in which a particular object may be observed to participate and the characteristics it should have in order to be able to participate in these actions. Two sets of measurements are assumed to be available: those made initially for all components routinely, and which supply the initial statistically based inference of possible labels of each component, and those that are made in order to confirm or deny a particular characteristic of the component that would allow it to participate in a specific action. A recursive version of the architecture is also proposed, in which the distributions of the former types of measurement may be learnt in the process, having no training data at all. Multi-view images are used as input to the system, which uses standard techniques to build the 3D models of the buildings. The system is tested on labelling the components of 10 3D models of buildings. The components are identified either manually, or fully automatically. The results are compared with those obtained by expandable Bayesian networks. The recursive version of ToK proves to be able to cope very well even without any training data, where it learns the characteristics of the various components by simply applying the pre-programmed logic rules that connect labels, actions and attributes.
Author	Petrou, Maria Xu, Mai
Author_xml	– sequence: 1 givenname: Mai surname: Xu fullname: Xu, Mai – sequence: 2 givenname: Maria surname: Petrou fullname: Petrou, Maria email: maria.petrou@imperial.ac.uk
BackLink	http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=24603131$$DView record in Pascal Francis
BookMark	eNp9kD1PHDEQQC0EEnDwB6jcoFS7-Ot2vVEaRBISCYkCIoXK8s6OD1_27MP2ge7fZ0-HUqRALsbFe6PROyWHIQYk5IKzmjPeXC1rePWbWjDOa6ZrxvgBOeGsY5WQ89-Hu3_bVpIrcUxOc15OAFcdPyFP8it9AAxIfSiY1gmLLT4G2m8pxFXvgw8Luk6xt70ffdnS8owxbakNAx3jwsNn-viMtMQ3TDQ6-ifEtxGHBZ6RI2fHjOfvc0Z-ff_2ePOjuru__XlzfVeBbESpFDbKolOtlnPJwHItlJ73TApoULpuDqgbbJVzWlrHcbC9tkwp6DXTrUU5I5_2e6cjXzaYi1n5DDiONmDcZNOJRvJO63YiL99Jm8GOLtkAPpt18iubtkaohkk-vRkRew5SzDmh-4dwZna5zdLscptdbsO0mWpOkv5PAr9PWZL148fql72KU6ZXj8lk8BgAB58Qihmi_0j_CwCinf0
CODEN	CVIUF4
CitedBy_id	crossref_primary_10_1016_j_eswa_2015_09_049 crossref_primary_10_1016_j_patrec_2014_02_009 crossref_primary_10_1016_j_eswa_2014_07_051 crossref_primary_10_1016_j_aei_2015_01_001 crossref_primary_10_3390_rs10091412 crossref_primary_10_1016_j_ins_2013_05_030 crossref_primary_10_1109_JIOT_2018_2872435 crossref_primary_10_1016_j_cviu_2013_01_010
Cites_doi	10.1109/TPAMI.2006.92 10.1016/S0262-8856(99)00040-2 10.1109/CVPR.2007.383095 10.1007/s11263-007-0120-6 10.1007/s10994-006-5833-1 10.1109/TPAMI.2003.1206514 10.1023/B:VISI.0000029665.07652.61 10.1109/TSMCB.2005.846649 10.1007/3-540-45054-8_2 10.1016/0031-3203(90)90094-2 10.21236/AD0708563 10.1109/HLK.2003.1240859 10.1109/ICIP.2009.5414036 10.1016/j.imavis.2007.08.013 10.1109/ICCV.2001.937528 10.1109/ICCV.2005.77 10.1109/MC.2007.154 10.1109/34.400565 10.1016/0262-8856(88)90001-7 10.1109/CVPR.2007.383154 10.1109/TPAMI.2007.40 10.1109/ICIP.1996.561026 10.1109/ICPR.2002.1047411 10.1145/4078.4081 10.1109/TPAMI.2003.1201825 10.1142/S0218001493000479 10.1109/ICCV.2007.4408987 10.1007/978-3-540-70932-9_9 10.1007/978-3-540-24670-1_27 10.1109/ICCV.2005.258 10.1109/ICMLA.2007.26 10.1080/01621459.1926.10502161 10.1109/ROBOT.2005.1570108 10.1109/CVPR.2005.16 10.1016/j.cviu.2004.05.004 10.1109/ICAR.2005.1507432
ContentType	Journal Article
Copyright	2011 Elsevier Inc. 2015 INIST-CNRS
Copyright_xml	– notice: 2011 Elsevier Inc. – notice: 2015 INIST-CNRS
DBID	AAYXX CITATION IQODW 7SC 8FD JQ2 L7M L~C L~D
DOI	10.1016/j.cviu.2011.08.001
DatabaseName	CrossRef Pascal-Francis Computer and Information Systems Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional
DatabaseTitleList	Computer and Information Systems Abstracts
DeliveryMethod	fulltext_linktorsrc
Discipline	Applied Sciences Engineering Computer Science Architecture
EISSN	1090-235X
EndPage	1596
ExternalDocumentID	24603131 10_1016_j_cviu_2011_08_001 S1077314211001834
GroupedDBID	--K --M -~X .DC .~1 0R~ 1B1 1~. 1~5 29F 4.4 457 4G. 5GY 5VS 6TJ 7-5 71M 8P~ AABNK AACTN AAEDT AAEDW AAIAV AAIKC AAIKJ AAKOC AALRI AAMNW AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABEFU ABFNM ABJNI ABMAC ABXDB ABYKQ ACDAQ ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADFGL ADJOM ADMUD ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CAG COF CS3 DM4 DU5 EBS EFBJH EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HF~ HVGLF HZ~ IHE J1W JJJVA KOM LG5 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SDF SDG SDP SES SEW SPC SPCBC SSV SSZ T5K TN5 XPP ZMT ~G- 9DU AATTM AAXKI AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS SST ~HD BNPGV IQODW 7SC 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c362t-4e64aef4783530ca182485b032c6e3f95ce86e74ff83af1edab8a044cb8087ae3
ISICitedReferencesCount	14
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000295424200011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1077-3142
IngestDate	Thu Oct 02 06:57:25 EDT 2025 Wed Apr 02 08:12:30 EDT 2025 Sat Nov 29 07:08:27 EST 2025 Tue Nov 18 22:37:02 EST 2025 Fri Feb 23 02:26:56 EST 2024
IsPeerReviewed	true
IsScholarly	true
Issue	11
Keywords	Logic and probabilities System architecture Scene labelling systems Machine learning Statistical analysis Probabilistic approach Utility function Labelling Inference Logical programming Modeling Multiple image Multiple view Utility theory Scene analysis Bayes network Probability learning Tridimensional image Maximum likelihood Artificial intelligence
Language	English
License	CC BY 4.0
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c362t-4e64aef4783530ca182485b032c6e3f95ce86e74ff83af1edab8a044cb8087ae3
Notes	ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23
PQID	926319887
PQPubID	23500
PageCount	16
ParticipantIDs	proquest_miscellaneous_926319887 pascalfrancis_primary_24603131 crossref_primary_10_1016_j_cviu_2011_08_001 crossref_citationtrail_10_1016_j_cviu_2011_08_001 elsevier_sciencedirect_doi_10_1016_j_cviu_2011_08_001
PublicationCentury	2000
PublicationDate	2011-11-01
PublicationDateYYYYMMDD	2011-11-01
PublicationDate_xml	– month: 11 year: 2011 text: 2011-11-01 day: 01
PublicationDecade	2010
PublicationPlace	Amsterdam
PublicationPlace_xml	– name: Amsterdam
PublicationTitle	Computer vision and image understanding
PublicationYear	2011
Publisher	Elsevier Inc Elsevier
Publisher_xml	– name: Elsevier Inc – name: Elsevier
References	Russell, Norvig (b0225) 2003 Marengoni, Hanson, Zilberstein, Riseman (b0165) 2003; 25 B. Neumann, R. Moller, A.G. Cohn, D.C. Hogg, Logic and probability for scene interpretation, in: Dagstuhl Workshop, 2008. Sandini, Metta, Vernon (b0230) 2004; 8 Kohli, Rihan, Bray, Torr (b0145) 2008; 79 P. Carbonetto, N. Freitas, K. Barnard, A statistical model for general contextual object recognition, in: Proceedings of ECCV, 2004, pp. 350–362. Zhambok, Klein (b0290) 1997 Ripley, Hjort (b0220) 1995 A.R. Dick, P.H.S. Torr, S.J. Ruffle, R. Cipolla, Combining single view recognition and multiple view stereo for architectural, in: Proceeding of ICCV, 2001, pp. 268–274. Nagel (b0175) 1988; 6 I. Levner, V. Bulitko, Machine learning for adaptive image interpretation, in: Proceedings of the 16th Innovative Applications of Artificial Intelligence’04 Conference, San Jose, CA, USA, 2004. Sturges (b0255) 1926; 21 Pearl (b0200) 1988 S. Ekvall, D. Kragic, Integrating object and grasp recognition for dynamic scene interpretation, in: Proceeding of 12th ICAR, 2005, pp. 331–336. M. Petrou, Learning in computer vision: some thoughts, in: Proceeding of CIARP, Santiago, Cile, 2007. M. Weber, M. Welling, P. Perona, Unsupervised learning of models for recognition, in: Proceedings of ECCV, 2000, pp. 18–32. J. Hartz, B. Neumann, Learning a knowledge base of ontological concepts for high-level scene interpretation, in: International Conference on Machine Learning and Applications, 2007, pp. 350–362. J. Sivic, B.C. Russell, A.A. Efros, A. Zisserman, W.T. Freeman, Discovering objects and their location in images, in: Proceedings of ICCV, 2005, pp. 370–377. G. Fritz, C. Seifert, L.Paletta, Urban object recognition from informative local features, in: Proceedings of the 2005 ICAR, 2005, pp. 131–137. Kim, Nevatia (b0135) 2004; 96 M. Jahangiri, Blob detector tool, 2009. Batllea, Casalsb, Freixeneta, Marti (b0015) 2000; 18 Christmas, Kittler, Petrou (b0035) 1995; 17 B. Ommer, J.M. Buhmann, Learning the compositional nature of visual objects, in: Proceedings of CVPR, 2007, pp. 1–8. . M. Xu, Scene interpretation with the Tower of Knowledge, PhD thesis, Imperial College London, 2010. Schneider, Wersing, Sendhoff, Korner (b0240) 2005; 35 Heesch, Petrou (b0100) 2009; 10 Hancock, Kittler (b0080) 1990; 23 Haykin (b0090) 1986 Wisniewsk, Medin (b0280) 1995 A. Ogale, A. Karapurkar, Y. Aloimonos, View-invariant modeling and recognition of human actions using grammars, in: Workshop on Dynamical Vision at ICCV, 2005, pp. 115–126. > Cheng, Caelli, Sanchez-Azofeifa (b0025) 2006; 28 C. Hudelot, N. Maillot, M. Thonnat, Symbol grounding for semantic image interpretation: from image data to semantics, in: Workshop on Semantic Knowledge in Computer Vision, in Association with ICCV05, 16 October 2005, Beijing, China, pp. 1875–1883. Neumann, Möller (b0185) 2008; 26 S. Savarese, L. Fei-fei, 3D Generic object categorisation, localisation and pose estimation, in: Proceedings of ICCV, 2007, pp. 1–8. Arens, Nagel (b0005) 2003 M. Jahangiri, M. Petrou, Fully bottom-up blob extraction in building facades, in: Proceedings of the 9th International Conference on Pattern Recognition and Image Analysis: New Information Technologies, PRIA-9-2008, September 14–20, Nizhni Novgorod, Russian Federation, vol. 1, pp 238–241, 2008. von Neumann, Morgenstern (b0260) 1947 Guerra-Filho, Aloimonos (b0075) 2007; 40 H. Zimmermann, Fuzzy set theory and its applications, Kluwer Academic Publishers, Boston, ISBN 0-7923-7435-5. V.-T. Vu, F. Bremond, M. Thonnat, Temporal constraints for video interpretation, in: The 15th European Conference on Artificial Intelligence (ECAI’2002), Lyon, France, 21–26 July 2002. IST06, E-training for interpreting images of man-made scenes. Dick, Torr, Cipolla (b0045) 2004; 60 Besl, Jain (b0010) 1985; 17 Siagian, Itti (b0245) 2007; 29 Kim, Nevatia (b0130) 2003; 25 D. Damen, Constraint-based scene interpretation, in: Dagstuhl Logic and Probability for Scene Interpretation Workshop, 2008. Richardson, Domingos (b0215) 2006; 62 M. Jahangiri, M. Petrou, An attention model for extracting components that merit identification, in: Proceedings of ICIP, 2009. S. Lee, S. Jung, R. Nevatia, Integrating ground and aerial views for urban site modelling, in: Proceeding of ICPR, 2002, pp. 107–112 vol.4. G. Metta, D. Vernon, G. Sandini, The RobotCub Approach to the Development of Cognition, in: L. Berthouze, F. Kaplan, H. Kozima, H. Yano, J. Konczak, G. Metta, J. Nadel, G. Sandini, G. Stojanov, C. Balkenius (Eds.), Proceedings of the 5th International Workshop on Epigenic Robotics: Modelling Cognitive Development in Robotic Systems, Lund University Cognitive Studies, vol. 123, 2004, ISBN 91-974741-4-2. S. Lee, R. Nevatia, Interactive 3D building modelling using a hierarchical representation, in: Proceedings of the First IEEE International Workshop on Higher-Level Knowledge in 3D Modelling and Motion Analysis, Los Alamitos, CA, USA, 2003, pp. 58–65. N. Chleq, M. Thonnat, Real time image sequence interpretaion for video survellance applications, in: International Conference on Image Processing, IEEE ICIP’96, vol. 2, Lausanne, Switzerland, September 1996, pp 801–804. N. Komodakis, G. Tziritas, N. Paragios, Fast approximately optimal solutions for single and dynamic MRFs, in: Proceedings of CVPR, 2007, pp. 1–8. Wiskott, Malsburg (b0275) 1993; 7 L. Fei-fei, P. Perona, A Bayesian hierarchical model for learning natural scene categories, in: Proceedings of CVPR, 2005, pp. 524–531. de Raedt (b0210) 2008 P.C. Fishburn, Utility Theory for Decision Making, Robert E. Krieger Publishing Company, Huntington, NY, 1970, ISBN 978-0471260608. D. Heesch, M. Petrou, Non-Gibbsian Markov random fields for object recognition, in: Proceedings of BMVC, 2007. Hotz, Neumann (b0105) 2005; 3 10.1016/j.cviu.2011.08.001_b0305 10.1016/j.cviu.2011.08.001_b0300 Russell (10.1016/j.cviu.2011.08.001_b0225) 2003 Hotz (10.1016/j.cviu.2011.08.001_b0105) 2005; 3 10.1016/j.cviu.2011.08.001_b0265 10.1016/j.cviu.2011.08.001_b0065 10.1016/j.cviu.2011.08.001_b0020 10.1016/j.cviu.2011.08.001_b0140 10.1016/j.cviu.2011.08.001_b0060 10.1016/j.cviu.2011.08.001_b0180 de Raedt (10.1016/j.cviu.2011.08.001_b0210) 2008 Dick (10.1016/j.cviu.2011.08.001_b0045) 2004; 60 von Neumann (10.1016/j.cviu.2011.08.001_b0260) 1947 10.1016/j.cviu.2011.08.001_b0115 10.1016/j.cviu.2011.08.001_b0235 Arens (10.1016/j.cviu.2011.08.001_b0005) 2003 10.1016/j.cviu.2011.08.001_b0155 10.1016/j.cviu.2011.08.001_b0110 10.1016/j.cviu.2011.08.001_b0030 Neumann (10.1016/j.cviu.2011.08.001_b0185) 2008; 26 10.1016/j.cviu.2011.08.001_b0195 10.1016/j.cviu.2011.08.001_b0150 10.1016/j.cviu.2011.08.001_b0270 10.1016/j.cviu.2011.08.001_b0070 10.1016/j.cviu.2011.08.001_b0190 Guerra-Filho (10.1016/j.cviu.2011.08.001_b0075) 2007; 40 Zhambok (10.1016/j.cviu.2011.08.001_b0290) 1997 Besl (10.1016/j.cviu.2011.08.001_b0010) 1985; 17 Hancock (10.1016/j.cviu.2011.08.001_b0080) 1990; 23 Sandini (10.1016/j.cviu.2011.08.001_b0230) 2004; 8 10.1016/j.cviu.2011.08.001_b0205 10.1016/j.cviu.2011.08.001_b0125 Richardson (10.1016/j.cviu.2011.08.001_b0215) 2006; 62 Wisniewsk (10.1016/j.cviu.2011.08.001_b0280) 1995 10.1016/j.cviu.2011.08.001_b0120 10.1016/j.cviu.2011.08.001_b0285 Kim (10.1016/j.cviu.2011.08.001_b0130) 2003; 25 Kohli (10.1016/j.cviu.2011.08.001_b0145) 2008; 79 10.1016/j.cviu.2011.08.001_b0085 10.1016/j.cviu.2011.08.001_b0040 10.1016/j.cviu.2011.08.001_b0160 Pearl (10.1016/j.cviu.2011.08.001_b0200) 1988 Batllea (10.1016/j.cviu.2011.08.001_b0015) 2000; 18 Christmas (10.1016/j.cviu.2011.08.001_b0035) 1995; 17 Nagel (10.1016/j.cviu.2011.08.001_b0175) 1988; 6 Ripley (10.1016/j.cviu.2011.08.001_b0220) 1995 Marengoni (10.1016/j.cviu.2011.08.001_b0165) 2003; 25 Heesch (10.1016/j.cviu.2011.08.001_b0100) 2009; 10 Cheng (10.1016/j.cviu.2011.08.001_b0025) 2006; 28 Sturges (10.1016/j.cviu.2011.08.001_b0255) 1926; 21 Wiskott (10.1016/j.cviu.2011.08.001_b0275) 1993; 7 10.1016/j.cviu.2011.08.001_b0055 Haykin (10.1016/j.cviu.2011.08.001_b0090) 1986 10.1016/j.cviu.2011.08.001_b0295 10.1016/j.cviu.2011.08.001_b0250 10.1016/j.cviu.2011.08.001_b0095 10.1016/j.cviu.2011.08.001_b0050 10.1016/j.cviu.2011.08.001_b0170 Siagian (10.1016/j.cviu.2011.08.001_b0245) 2007; 29 Kim (10.1016/j.cviu.2011.08.001_b0135) 2004; 96 Schneider (10.1016/j.cviu.2011.08.001_b0240) 2005; 35
References_xml	– reference: S. Lee, R. Nevatia, Interactive 3D building modelling using a hierarchical representation, in: Proceedings of the First IEEE International Workshop on Higher-Level Knowledge in 3D Modelling and Motion Analysis, Los Alamitos, CA, USA, 2003, pp. 58–65. – reference: M. Jahangiri, Blob detector tool, 2009. < – volume: 6 start-page: 59 year: 1988 end-page: 74 ident: b0175 article-title: From image sequences towards conceptual descriptions publication-title: Image Vision Comput. – volume: 28 start-page: 684 year: 2006 end-page: 693 ident: b0025 article-title: Component optimisation for image understanding: a Bayesian approach publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – reference: M. Weber, M. Welling, P. Perona, Unsupervised learning of models for recognition, in: Proceedings of ECCV, 2000, pp. 18–32. – volume: 79 start-page: 59 year: 2008 end-page: 80 ident: b0145 article-title: Simultaneous segmentation and pose estimation of humans using dynamic graph cuts publication-title: Int. J. Comput. Vision – volume: 62 start-page: 107 year: 2006 end-page: 136 ident: b0215 article-title: Markov logic networks publication-title: Mach. Learn. – year: 1995 ident: b0280 article-title: The Interaction of Theory and Similarity in Rule Induction – reference: M. Petrou, Learning in computer vision: some thoughts, in: Proceeding of CIARP, Santiago, Cile, 2007. – reference: A. Ogale, A. Karapurkar, Y. Aloimonos, View-invariant modeling and recognition of human actions using grammars, in: Workshop on Dynamical Vision at ICCV, 2005, pp. 115–126. – reference: M. Jahangiri, M. Petrou, An attention model for extracting components that merit identification, in: Proceedings of ICIP, 2009. – volume: 17 start-page: 75 year: 1985 end-page: 145 ident: b0010 article-title: Three-dimensional object recognition publication-title: Comput. Surv. – reference: M. Jahangiri, M. Petrou, Fully bottom-up blob extraction in building facades, in: Proceedings of the 9th International Conference on Pattern Recognition and Image Analysis: New Information Technologies, PRIA-9-2008, September 14–20, Nizhni Novgorod, Russian Federation, vol. 1, pp 238–241, 2008. – year: 1997 ident: b0290 article-title: Naturalistic Decision Making – reference: P.C. Fishburn, Utility Theory for Decision Making, Robert E. Krieger Publishing Company, Huntington, NY, 1970, ISBN 978-0471260608. – year: 1995 ident: b0220 article-title: Pattern Recognition and Neural Networks – reference: G. Metta, D. Vernon, G. Sandini, The RobotCub Approach to the Development of Cognition, in: L. Berthouze, F. Kaplan, H. Kozima, H. Yano, J. Konczak, G. Metta, J. Nadel, G. Sandini, G. Stojanov, C. Balkenius (Eds.), Proceedings of the 5th International Workshop on Epigenic Robotics: Modelling Cognitive Development in Robotic Systems, Lund University Cognitive Studies, vol. 123, 2004, ISBN 91-974741-4-2. – reference: D. Heesch, M. Petrou, Non-Gibbsian Markov random fields for object recognition, in: Proceedings of BMVC, 2007. – reference: G. Fritz, C. Seifert, L.Paletta, Urban object recognition from informative local features, in: Proceedings of the 2005 ICAR, 2005, pp. 131–137. – reference: J. Hartz, B. Neumann, Learning a knowledge base of ontological concepts for high-level scene interpretation, in: International Conference on Machine Learning and Applications, 2007, pp. 350–362. – reference: M. Xu, Scene interpretation with the Tower of Knowledge, PhD thesis, Imperial College London, 2010. – reference: D. Damen, Constraint-based scene interpretation, in: Dagstuhl Logic and Probability for Scene Interpretation Workshop, 2008. < – reference: S. Lee, S. Jung, R. Nevatia, Integrating ground and aerial views for urban site modelling, in: Proceeding of ICPR, 2002, pp. 107–112 vol.4. – volume: 23 start-page: 711 year: 1990 end-page: 733 ident: b0080 article-title: Discrete relaxation publication-title: Pattern Recogn. – year: 1986 ident: b0090 article-title: Adaptive Filter Theory – reference: . – reference: C. Hudelot, N. Maillot, M. Thonnat, Symbol grounding for semantic image interpretation: from image data to semantics, in: Workshop on Semantic Knowledge in Computer Vision, in Association with ICCV05, 16 October 2005, Beijing, China, pp. 1875–1883. – year: 1947 ident: b0260 article-title: Theory of Games and Economic Behavior – reference: N. Komodakis, G. Tziritas, N. Paragios, Fast approximately optimal solutions for single and dynamic MRFs, in: Proceedings of CVPR, 2007, pp. 1–8. – volume: 35 start-page: 426 year: 2005 end-page: 437 ident: b0240 article-title: Evolutionary optimisation of a hierarchical object recognition model publication-title: IEEE Trans. Syst., Man, Cybern. – Part B: Cybern. – volume: 96 start-page: 60 year: 2004 end-page: 95 ident: b0135 article-title: Automatic description of complex buildings from multiple fimages publication-title: Comput. Vision Image Und. – volume: 25 start-page: 769 year: 2003 end-page: 774 ident: b0130 article-title: Expandable Bayesian networks for 3D object description from multiple views and multiple mode inputs publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – reference: B. Ommer, J.M. Buhmann, Learning the compositional nature of visual objects, in: Proceedings of CVPR, 2007, pp. 1–8. – start-page: 149 year: 2003 end-page: 163 ident: b0005 article-title: Behavioural knowledge representation for the understanding and creation of video sequences publication-title: Proceedings of the 26th German Conference on Artificial Intelligence (KI-2003), LNAI – volume: 21 start-page: 65 year: 1926 end-page: 66 ident: b0255 article-title: The choice of a class interval publication-title: J. Am. Stat. Assoc. – volume: 7 start-page: 735 year: 1993 end-page: 748 ident: b0275 article-title: A neural system for the recognition of partially occluded objects in cluttered scenes publication-title: Int. J. Pattern Recogn. Artif. Intell. – volume: 25 start-page: 852 year: 2003 end-page: 858 ident: b0165 article-title: Decision making and uncertainty management in a 3D reconstruction system publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 8 year: 2004 ident: b0230 article-title: RobotCub: an open framework for research in embodied cognition publication-title: Int. J. Humanoid Robotics – reference: H. Zimmermann, Fuzzy set theory and its applications, Kluwer Academic Publishers, Boston, ISBN 0-7923-7435-5. – reference: B. Neumann, R. Moller, A.G. Cohn, D.C. Hogg, Logic and probability for scene interpretation, in: Dagstuhl Workshop, 2008. < – volume: 60 start-page: 111 year: 2004 end-page: 134 ident: b0045 article-title: Modelling and interpretation of architecture from several images publication-title: Int. J. Comput. Vision – year: 1988 ident: b0200 article-title: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference – reference: IST06, E-training for interpreting images of man-made scenes. < – volume: 40 start-page: 42 year: 2007 end-page: 51 ident: b0075 article-title: A language for human action publication-title: IEEE Comput. – reference: S. Savarese, L. Fei-fei, 3D Generic object categorisation, localisation and pose estimation, in: Proceedings of ICCV, 2007, pp. 1–8. – volume: 17 start-page: 749 year: 1995 end-page: 764 ident: b0035 article-title: Structural matching in computer vision publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – year: 2003 ident: b0225 article-title: Artificial Intelligence: A Modern Approach – reference: L. Fei-fei, P. Perona, A Bayesian hierarchical model for learning natural scene categories, in: Proceedings of CVPR, 2005, pp. 524–531. – reference: V.-T. Vu, F. Bremond, M. Thonnat, Temporal constraints for video interpretation, in: The 15th European Conference on Artificial Intelligence (ECAI’2002), Lyon, France, 21–26 July 2002. – reference: N. Chleq, M. Thonnat, Real time image sequence interpretaion for video survellance applications, in: International Conference on Image Processing, IEEE ICIP’96, vol. 2, Lausanne, Switzerland, September 1996, pp 801–804. – volume: 26 start-page: 82 year: 2008 end-page: 101 ident: b0185 article-title: On scene interpretation with description logics publication-title: Image Vision Comput. – reference: >. – volume: 10 year: 2009 ident: b0100 article-title: Markov random fields with asymmetric interactions for modelling spatial context in structured scene labelling publication-title: J. Sig. Proc. Syst. – reference: P. Carbonetto, N. Freitas, K. Barnard, A statistical model for general contextual object recognition, in: Proceedings of ECCV, 2004, pp. 350–362. – reference: I. Levner, V. Bulitko, Machine learning for adaptive image interpretation, in: Proceedings of the 16th Innovative Applications of Artificial Intelligence’04 Conference, San Jose, CA, USA, 2004. – reference: A.R. Dick, P.H.S. Torr, S.J. Ruffle, R. Cipolla, Combining single view recognition and multiple view stereo for architectural, in: Proceeding of ICCV, 2001, pp. 268–274. – reference: J. Sivic, B.C. Russell, A.A. Efros, A. Zisserman, W.T. Freeman, Discovering objects and their location in images, in: Proceedings of ICCV, 2005, pp. 370–377. – volume: 3 start-page: 59 year: 2005 end-page: 65 ident: b0105 article-title: Scene interpretation as a configuration task publication-title: Kunstliche Intelligenz – reference: > – volume: 29 start-page: 300 year: 2007 end-page: 312 ident: b0245 article-title: Rapid biologically-inspired scene classification using features shared with visual attention publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 18 start-page: 515 year: 2000 end-page: 530 ident: b0015 article-title: A review on strategies for recognising natural objects in colour images of outdoor scenes publication-title: Image Vision Comput. – year: 2008 ident: b0210 article-title: Logical and Relational Learning – reference: S. Ekvall, D. Kragic, Integrating object and grasp recognition for dynamic scene interpretation, in: Proceeding of 12th ICAR, 2005, pp. 331–336. – volume: 28 start-page: 684 issue: 5 year: 2006 ident: 10.1016/j.cviu.2011.08.001_b0025 article-title: Component optimisation for image understanding: a Bayesian approach publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2006.92 – volume: 18 start-page: 515 issue: 6 year: 2000 ident: 10.1016/j.cviu.2011.08.001_b0015 article-title: A review on strategies for recognising natural objects in colour images of outdoor scenes publication-title: Image Vision Comput. doi: 10.1016/S0262-8856(99)00040-2 – ident: 10.1016/j.cviu.2011.08.001_b0095 – ident: 10.1016/j.cviu.2011.08.001_b0140 doi: 10.1109/CVPR.2007.383095 – volume: 79 start-page: 59 issue: 3 year: 2008 ident: 10.1016/j.cviu.2011.08.001_b0145 article-title: Simultaneous segmentation and pose estimation of humans using dynamic graph cuts publication-title: Int. J. Comput. Vision doi: 10.1007/s11263-007-0120-6 – volume: 62 start-page: 107 issue: 1-2 year: 2006 ident: 10.1016/j.cviu.2011.08.001_b0215 article-title: Markov logic networks publication-title: Mach. Learn. doi: 10.1007/s10994-006-5833-1 – volume: 25 start-page: 852 issue: 7 year: 2003 ident: 10.1016/j.cviu.2011.08.001_b0165 article-title: Decision making and uncertainty management in a 3D reconstruction system publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2003.1206514 – year: 1988 ident: 10.1016/j.cviu.2011.08.001_b0200 – volume: 60 start-page: 111 issue: 2 year: 2004 ident: 10.1016/j.cviu.2011.08.001_b0045 article-title: Modelling and interpretation of architecture from several images publication-title: Int. J. Comput. Vision doi: 10.1023/B:VISI.0000029665.07652.61 – volume: 35 start-page: 426 issue: 3 year: 2005 ident: 10.1016/j.cviu.2011.08.001_b0240 article-title: Evolutionary optimisation of a hierarchical object recognition model publication-title: IEEE Trans. Syst., Man, Cybern. – Part B: Cybern. doi: 10.1109/TSMCB.2005.846649 – ident: 10.1016/j.cviu.2011.08.001_b0040 – year: 1947 ident: 10.1016/j.cviu.2011.08.001_b0260 – ident: 10.1016/j.cviu.2011.08.001_b0270 doi: 10.1007/3-540-45054-8_2 – volume: 23 start-page: 711 issue: 7 year: 1990 ident: 10.1016/j.cviu.2011.08.001_b0080 article-title: Discrete relaxation publication-title: Pattern Recogn. doi: 10.1016/0031-3203(90)90094-2 – ident: 10.1016/j.cviu.2011.08.001_b0065 doi: 10.21236/AD0708563 – ident: 10.1016/j.cviu.2011.08.001_b0150 doi: 10.1109/HLK.2003.1240859 – ident: 10.1016/j.cviu.2011.08.001_b0120 doi: 10.1109/ICIP.2009.5414036 – volume: 26 start-page: 82 issue: 1 year: 2008 ident: 10.1016/j.cviu.2011.08.001_b0185 article-title: On scene interpretation with description logics publication-title: Image Vision Comput. doi: 10.1016/j.imavis.2007.08.013 – ident: 10.1016/j.cviu.2011.08.001_b0050 doi: 10.1109/ICCV.2001.937528 – ident: 10.1016/j.cviu.2011.08.001_b0250 doi: 10.1109/ICCV.2005.77 – ident: 10.1016/j.cviu.2011.08.001_b0180 – volume: 40 start-page: 42 issue: 5 year: 2007 ident: 10.1016/j.cviu.2011.08.001_b0075 article-title: A language for human action publication-title: IEEE Comput. doi: 10.1109/MC.2007.154 – volume: 3 start-page: 59 year: 2005 ident: 10.1016/j.cviu.2011.08.001_b0105 article-title: Scene interpretation as a configuration task publication-title: Kunstliche Intelligenz – volume: 17 start-page: 749 issue: 8 year: 1995 ident: 10.1016/j.cviu.2011.08.001_b0035 article-title: Structural matching in computer vision publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/34.400565 – ident: 10.1016/j.cviu.2011.08.001_b0305 – volume: 6 start-page: 59 issue: 2 year: 1988 ident: 10.1016/j.cviu.2011.08.001_b0175 article-title: From image sequences towards conceptual descriptions publication-title: Image Vision Comput. doi: 10.1016/0262-8856(88)90001-7 – ident: 10.1016/j.cviu.2011.08.001_b0195 doi: 10.1109/CVPR.2007.383154 – volume: 29 start-page: 300 issue: 2 year: 2007 ident: 10.1016/j.cviu.2011.08.001_b0245 article-title: Rapid biologically-inspired scene classification using features shared with visual attention publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2007.40 – ident: 10.1016/j.cviu.2011.08.001_b0265 – ident: 10.1016/j.cviu.2011.08.001_b0030 doi: 10.1109/ICIP.1996.561026 – ident: 10.1016/j.cviu.2011.08.001_b0155 doi: 10.1109/ICPR.2002.1047411 – ident: 10.1016/j.cviu.2011.08.001_b0125 – year: 2003 ident: 10.1016/j.cviu.2011.08.001_b0225 – ident: 10.1016/j.cviu.2011.08.001_b0205 – volume: 17 start-page: 75 year: 1985 ident: 10.1016/j.cviu.2011.08.001_b0010 article-title: Three-dimensional object recognition publication-title: Comput. Surv. doi: 10.1145/4078.4081 – volume: 25 start-page: 769 issue: 6 year: 2003 ident: 10.1016/j.cviu.2011.08.001_b0130 article-title: Expandable Bayesian networks for 3D object description from multiple views and multiple mode inputs publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2003.1201825 – volume: 7 start-page: 735 issue: 4 year: 1993 ident: 10.1016/j.cviu.2011.08.001_b0275 article-title: A neural system for the recognition of partially occluded objects in cluttered scenes publication-title: Int. J. Pattern Recogn. Artif. Intell. doi: 10.1142/S0218001493000479 – ident: 10.1016/j.cviu.2011.08.001_b0115 – ident: 10.1016/j.cviu.2011.08.001_b0160 – ident: 10.1016/j.cviu.2011.08.001_b0235 doi: 10.1109/ICCV.2007.4408987 – ident: 10.1016/j.cviu.2011.08.001_b0190 doi: 10.1007/978-3-540-70932-9_9 – ident: 10.1016/j.cviu.2011.08.001_b0170 – year: 1995 ident: 10.1016/j.cviu.2011.08.001_b0280 – ident: 10.1016/j.cviu.2011.08.001_b0020 doi: 10.1007/978-3-540-24670-1_27 – ident: 10.1016/j.cviu.2011.08.001_b0285 – ident: 10.1016/j.cviu.2011.08.001_b0300 – year: 1986 ident: 10.1016/j.cviu.2011.08.001_b0090 – year: 2008 ident: 10.1016/j.cviu.2011.08.001_b0210 – year: 1997 ident: 10.1016/j.cviu.2011.08.001_b0290 – ident: 10.1016/j.cviu.2011.08.001_b0110 doi: 10.1109/ICCV.2005.258 – volume: 10 issue: 07 year: 2009 ident: 10.1016/j.cviu.2011.08.001_b0100 article-title: Markov random fields with asymmetric interactions for modelling spatial context in structured scene labelling publication-title: J. Sig. Proc. Syst. – ident: 10.1016/j.cviu.2011.08.001_b0085 doi: 10.1109/ICMLA.2007.26 – volume: 21 start-page: 65 issue: 153 year: 1926 ident: 10.1016/j.cviu.2011.08.001_b0255 article-title: The choice of a class interval publication-title: J. Am. Stat. Assoc. doi: 10.1080/01621459.1926.10502161 – year: 1995 ident: 10.1016/j.cviu.2011.08.001_b0220 – ident: 10.1016/j.cviu.2011.08.001_b0295 – volume: 8 issue: 2 year: 2004 ident: 10.1016/j.cviu.2011.08.001_b0230 article-title: RobotCub: an open framework for research in embodied cognition publication-title: Int. J. Humanoid Robotics – ident: 10.1016/j.cviu.2011.08.001_b0070 doi: 10.1109/ROBOT.2005.1570108 – start-page: 149 year: 2003 ident: 10.1016/j.cviu.2011.08.001_b0005 article-title: Behavioural knowledge representation for the understanding and creation of video sequences – ident: 10.1016/j.cviu.2011.08.001_b0060 doi: 10.1109/CVPR.2005.16 – volume: 96 start-page: 60 issue: 1 year: 2004 ident: 10.1016/j.cviu.2011.08.001_b0135 article-title: Automatic description of complex buildings from multiple fimages publication-title: Comput. Vision Image Und. doi: 10.1016/j.cviu.2004.05.004 – ident: 10.1016/j.cviu.2011.08.001_b0055 doi: 10.1109/ICAR.2005.1507432
SSID	ssj0011491
Score	2.0790508
Snippet	► Linguistically inspired reasoning architecture. ► Generic framework for combining logic and conventional statistical pattern recognition. ► Generic framework... We explore a newly proposed system architecture, called tower of knowledge (ToK), in the context of labelling components of building scenes. The ToK...
SourceID	proquest pascalfrancis crossref elsevier
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	1581
SubjectTerms	Applied sciences Architecture Artificial intelligence Computer science; control theory; systems Exact sciences and technology Labelling Labels Logic Logic and probabilities Machine learning Mathematical analysis Mathematical models Pattern recognition. Digital image processing. Computational geometry Scene labelling systems System architecture Three dimensional models
Title	3D Scene interpretation by combining probability theory and logic: The tower of knowledge
URI	https://dx.doi.org/10.1016/j.cviu.2011.08.001 https://www.proquest.com/docview/926319887
Volume	115
WOSCitedRecordID	wos000295424200011&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: ScienceDirect customDbUrl: eissn: 1090-235X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0011491 issn: 1077-3142 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLZKxwMIcRmgjcvkB96mTEnsJA5vExsCHiYkhhSeLNuxpU4jrdqm2v79jmM7TbhMgMRLVB0ltdvvy_Hx8bkg9AZWDCqTWkdFXmYRVYZEzEgaFTEzpJYyNrLumk0UZ2esqsrPk0kbcmE2l0XTsKurcvFfoQYZgG1TZ_8C7v5LQQCfAXS4Auxw_SPgyQm8sLorBjKKJwQ7E4aTXUMIG5YlXYXua5fL6MowdYowBGJ0DdSsMdn73YaWbGgHceiy090hxHcbAdQO82UCoFXrMoNmW128Xs690IU6994HG_428j70aTGjqE3YUlrnpyubdaS9rIyjlGTVSPW6VM7AsWSgSZPMtXLxqzJYXfkvNb5zPlwcqc2s3VZk9VMcV9L-Yudlp2XL5IEqo3fQTlpkJZuineOPp9Wn_vgJto2JC1Z1v8NnW7nAwB9H-p1F82AhVvCeGdcg5ae1vjNgzh-jh37ngY8dY56giW520SO_C8Fex69AFJANsl10f1C18in6Rk5wxzA8ZhiW17hnGB4wDDuGYWAE7hj2FgO_cMcvPDe459cz9PX96fm7D5Hv0BEpMHzWEdU5FdpQ6z4ksRKwWaUskzFJVa6JKTOlWa4LagwjwiS6FpKJmFIlWcwKoclzNG3mjd5DOCW1YrYJCyEZTVgpSF7WStjyfCJLCrOPkvAvc-XL19suKpc8xClecIsMt8hw21o1TvbRYf_MwhVvufXuLIDHvfnpzEoOXLv1uYMR0v1QKbUt3AncgAP0HJS3PZETjZ63K16mOSyBsM6_-MexX6J727fyFZqul61-je6qzXq2Wh54Wt8APrLBEA
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=3D+Scene+interpretation+by+combining+probability+theory+and+logic%3A+The+tower+of+knowledge&rft.jtitle=Computer+vision+and+image+understanding&rft.au=Xu%2C+Mai&rft.au=Petrou%2C+Maria&rft.date=2011-11-01&rft.pub=Elsevier+Inc&rft.issn=1077-3142&rft.eissn=1090-235X&rft.volume=115&rft.issue=11&rft.spage=1581&rft.epage=1596&rft_id=info:doi/10.1016%2Fj.cviu.2011.08.001&rft.externalDocID=S1077314211001834
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1077-3142&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1077-3142&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1077-3142&client=summon