Image super-resolution by dictionary concatenation and sparse representation with approximate L0 norm minimization
[Display omitted] ► Universal dictionary and fixed sparsity are not beneficial to super-resolution. ► We use dictionary concatenation and more precise sparse representation algorithm. ► Universal dictionary is cascaded with specific one learned from given image. ► Approximate L0 norm minimization ov...
Saved in:
| Published in | Computers & electrical engineering Vol. 38; no. 5; pp. 1336 - 1345 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier Ltd
01.09.2012
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | [Display omitted]
► Universal dictionary and fixed sparsity are not beneficial to super-resolution. ► We use dictionary concatenation and more precise sparse representation algorithm. ► Universal dictionary is cascaded with specific one learned from given image. ► Approximate L0 norm minimization overcomes disadvantage of fixed sparsity. ► Various reconstruction results show effectiveness of proposed framework.
This paper proposes a different image super-resolution (SR) reconstruction scheme, based on the newly advanced results of sparse representation and the recently presented SR methods via this model. Firstly, we online learn a subsidiary dictionary with the degradation estimation of the given low-resolution image, and concatenate it with main one offline learned from many natural images with high quality. This strategy can strengthen the expressive ability of dictionary atoms. Secondly, the conventional matching pursuit algorithms commonly use a fixed sparsity threshold for sparse decomposition of all image patches, which is not optimal and even introduces annoying artifacts. Alternatively, we employ the approximate L0 norm minimization to decompose accurately the patch over its dictionary. Thus the coefficients of representation with variant number of nonzero items can exactly weight atoms for those complicated local structures of image. Experimental results show that the proposed method produces high-resolution images that are competitive or superior in quality to results generated by similar techniques. |
|---|---|
| AbstractList | [Display omitted]
► Universal dictionary and fixed sparsity are not beneficial to super-resolution. ► We use dictionary concatenation and more precise sparse representation algorithm. ► Universal dictionary is cascaded with specific one learned from given image. ► Approximate L0 norm minimization overcomes disadvantage of fixed sparsity. ► Various reconstruction results show effectiveness of proposed framework.
This paper proposes a different image super-resolution (SR) reconstruction scheme, based on the newly advanced results of sparse representation and the recently presented SR methods via this model. Firstly, we online learn a subsidiary dictionary with the degradation estimation of the given low-resolution image, and concatenate it with main one offline learned from many natural images with high quality. This strategy can strengthen the expressive ability of dictionary atoms. Secondly, the conventional matching pursuit algorithms commonly use a fixed sparsity threshold for sparse decomposition of all image patches, which is not optimal and even introduces annoying artifacts. Alternatively, we employ the approximate L0 norm minimization to decompose accurately the patch over its dictionary. Thus the coefficients of representation with variant number of nonzero items can exactly weight atoms for those complicated local structures of image. Experimental results show that the proposed method produces high-resolution images that are competitive or superior in quality to results generated by similar techniques. This paper proposes a different image super-resolution (SR) reconstruction scheme, based on the newly advanced results of sparse representation and the recently presented SR methods via this model. Firstly, we online learn a subsidiary dictionary with the degradation estimation of the given low-resolution image, and concatenate it with main one offline learned from many natural images with high quality. This strategy can strengthen the expressive ability of dictionary atoms. Secondly, the conventional matching pursuit algorithms commonly use a fixed sparsity threshold for sparse decomposition of all image patches, which is not optimal and even introduces annoying artifacts. Alternatively, we employ the approximate L0 norm minimization to decompose accurately the patch over its dictionary. Thus the coefficients of representation with variant number of nonzero items can exactly weight atoms for those complicated local structures of image. Experimental results show that the proposed method produces high-resolution images that are competitive or superior in quality to results generated by similar techniques. |
| Author | Zhang, Qiheng Lu, Jinzheng Peng, Zhenming Xu, Zhiyong |
| Author_xml | – sequence: 1 givenname: Jinzheng surname: Lu fullname: Lu, Jinzheng email: lujinzheng@163.com organization: Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu 610209, China – sequence: 2 givenname: Qiheng surname: Zhang fullname: Zhang, Qiheng organization: Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu 610209, China – sequence: 3 givenname: Zhiyong surname: Xu fullname: Xu, Zhiyong organization: Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu 610209, China – sequence: 4 givenname: Zhenming surname: Peng fullname: Peng, Zhenming organization: School of Optoelectronic Information, University of Electronic Science and Technology of China, Chengdu 610054, China |
| BookMark | eNqNkE1PwzAMhiM0JLbBfwg3Li1J2qTrEU18TJrEBc5RmrojU5uUpAXGrydbOXBEsmRbfh_LfhdoZp0FhK4pSSmh4nafatf10IIGu0sZoTSNQZg4Q3O6KsqEFJzP0JyQnCdFScQFWoSwJ7EXdDVHftOpHeAw9uATD8G142CcxdUB10YfS-UPWDur1QBWnWbK1jj0ygfAHvoIgR2myacZ3rDqe---TBcBvCXYOt_hzljTme-T6hKdN6oNcPWbl-j14f5l_ZRsnx8367ttopkoh6SivGAg9KqCuqQsaxirFNE6o7qoeZFRXnIumkqpHEDXRZ5VosqhVFCTQimeLdHNtDee8z5CGGRngoa2VRbcGCSlmeAiZ4xEaTlJtXcheGhk7-MD_iApkUef5V7-8VkefY68jD5Hdj2xEH_5MOBl0Aashtp40IOsnfnHlh-i_JJy |
| CitedBy_id | crossref_primary_10_1016_j_compeleceng_2015_12_017 crossref_primary_10_1016_j_image_2020_116056 crossref_primary_10_1109_ACCESS_2018_2841030 |
| Cites_doi | 10.1109/TIP.2010.2050625 10.1109/TSP.2008.2007606 10.1016/j.imavis.2005.05.005 10.1109/TIP.2003.819861 10.1016/j.imavis.2006.02.026 10.1109/MSP.2003.1203207 10.1109/38.988747 10.1109/83.748893 10.1109/TIP.2009.2022440 10.1109/TIT.2006.871582 |
| ContentType | Journal Article |
| Copyright | 2011 Elsevier Ltd |
| Copyright_xml | – notice: 2011 Elsevier Ltd |
| DBID | AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D |
| DOI | 10.1016/j.compeleceng.2011.11.026 |
| DatabaseName | CrossRef Computer and Information Systems Abstracts Electronics & Communications 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 Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Technology Research Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1879-0755 |
| EndPage | 1345 |
| ExternalDocumentID | 10_1016_j_compeleceng_2011_11_026 S0045790611002023 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 29F 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABEFU ABFNM ABJNI ABMAC ABXDB ABYKQ ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADTZH AEBSH AECPX AEKER AENEX AFFNX 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 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA GBOLZ HLZ HVGLF HZ~ IHE J1W JJJVA KOM LG9 LY7 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PQQKQ Q38 R2- RIG ROL RPZ RXW SBC SDF SDG SDP SES SET SEW SPC SPCBC SST SSV SSZ T5K TAE TN5 UHS VOH WH7 WUQ XPP ZMT ~G- ~S- AAXKI AAYXX AFJKZ AKRWK CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c269t-b1572e6c8bed9123f22ba0cc31c7d573159556fbaa4eecd743b6b4e9aed07aa53 |
| IEDL.DBID | AIKHN |
| ISSN | 0045-7906 |
| IngestDate | Fri Oct 25 23:22:08 EDT 2024 Thu Sep 26 18:58:03 EDT 2024 Fri Feb 23 02:32:44 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 5 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c269t-b1572e6c8bed9123f22ba0cc31c7d573159556fbaa4eecd743b6b4e9aed07aa53 |
| Notes | ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23 |
| PQID | 1136564220 |
| PQPubID | 23500 |
| PageCount | 10 |
| ParticipantIDs | proquest_miscellaneous_1136564220 crossref_primary_10_1016_j_compeleceng_2011_11_026 elsevier_sciencedirect_doi_10_1016_j_compeleceng_2011_11_026 |
| PublicationCentury | 2000 |
| PublicationDate | 20120901 |
| PublicationDateYYYYMMDD | 2012-09-01 |
| PublicationDate_xml | – month: 09 year: 2012 text: 20120901 day: 01 |
| PublicationDecade | 2010 |
| PublicationTitle | Computers & electrical engineering |
| PublicationYear | 2012 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Protter, Elad (b0040) 2009; 18 van Ouwerkerk (b0010) 2006; 24 Chang H, Yeung DY, Xiong Y. Super-resolution through neighbor embedding. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), vol. 1; 2004. p. 275–82. Chen, Huang, Lee (b0015) 2005; 23 Mallat (b0070) 2009 Park, Park, Kang (b0005) 2003; 20 Elad, Feuer (b0045) 1999; 8 Roman Z, Elad M, Protter M. On single image scale-up using sparse-representations. In: Proceedings of the 7th international conferences on curves and surfaces; 2010. Yang JC, Wright J, Huang T, Ma Y. Image super-resolution as sparse representation of raw image patches. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), vol. 1; 2008. p. 1–8. Freeman, Jones, Pasztor (b0025) 2002; 22 Donoho (b0080) 2006; 52 Yang, Wright, Huang, Ma (b0055) 2010; 19 Wang, Bovik, Sheikh (b0085) 2004; 13 Milanfar (b0035) 2010 Bruckstein, Donoho, Elad (b0075) 2009; 51 Mohimani, Massoud, Jutten (b0065) 2009; 57 Baker S, Kanade T. Limits on super-resolution and how to break them. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), vol. 2; 2000. p. 372–9. van Ouwerkerk (10.1016/j.compeleceng.2011.11.026_b0010) 2006; 24 Donoho (10.1016/j.compeleceng.2011.11.026_b0080) 2006; 52 Chen (10.1016/j.compeleceng.2011.11.026_b0015) 2005; 23 10.1016/j.compeleceng.2011.11.026_b0060 Protter (10.1016/j.compeleceng.2011.11.026_b0040) 2009; 18 Wang (10.1016/j.compeleceng.2011.11.026_b0085) 2004; 13 Mallat (10.1016/j.compeleceng.2011.11.026_b0070) 2009 Park (10.1016/j.compeleceng.2011.11.026_b0005) 2003; 20 Freeman (10.1016/j.compeleceng.2011.11.026_b0025) 2002; 22 Milanfar (10.1016/j.compeleceng.2011.11.026_b0035) 2010 Elad (10.1016/j.compeleceng.2011.11.026_b0045) 1999; 8 Yang (10.1016/j.compeleceng.2011.11.026_b0055) 2010; 19 Mohimani (10.1016/j.compeleceng.2011.11.026_b0065) 2009; 57 10.1016/j.compeleceng.2011.11.026_b0030 10.1016/j.compeleceng.2011.11.026_b0020 Bruckstein (10.1016/j.compeleceng.2011.11.026_b0075) 2009; 51 10.1016/j.compeleceng.2011.11.026_b0050 |
| References_xml | – volume: 51 start-page: 34 year: 2009 end-page: 81 ident: b0075 article-title: From sparse solutions of systems of equations to sparse modeling of signals and images publication-title: SIAM Rev Soc Ind Appl Math contributor: fullname: Elad – volume: 52 start-page: 1289 year: 2006 end-page: 1306 ident: b0080 article-title: Compressed sensing publication-title: IEEE Trans Inf Theory contributor: fullname: Donoho – volume: 24 start-page: 1039 year: 2006 end-page: 1052 ident: b0010 article-title: Image super-resolution survey publication-title: Image Vis Comput contributor: fullname: van Ouwerkerk – volume: 20 start-page: 21 year: 2003 end-page: 36 ident: b0005 article-title: Super-resolution image reconstruction: a technical overview publication-title: IEEE Signal Process Mag contributor: fullname: Kang – year: 2010 ident: b0035 article-title: Super-resolution imaging contributor: fullname: Milanfar – volume: 18 start-page: 1899 year: 2009 end-page: 1904 ident: b0040 article-title: Super resolution with proballistic motion estimation publication-title: IEEE Trans Image Process contributor: fullname: Elad – volume: 8 start-page: 387 year: 1999 end-page: 395 ident: b0045 article-title: Superresolution restoration of an image sequence: adaptive filtering approach publication-title: IEEE Trans Image Process contributor: fullname: Feuer – volume: 19 start-page: 2861 year: 2010 end-page: 2873 ident: b0055 article-title: Image super-resolution via sparse representation publication-title: IEEE Trans Image Process contributor: fullname: Ma – volume: 23 start-page: 791 year: 2005 end-page: 798 ident: b0015 article-title: A fast edge-oriented algorithm for image interpolation publication-title: Image Vis Comput contributor: fullname: Lee – year: 2009 ident: b0070 article-title: A wavelet tour of signal processing, the sparse way contributor: fullname: Mallat – volume: 22 start-page: 56 year: 2002 end-page: 65 ident: b0025 article-title: Example-based super-resolution publication-title: IEEE Trans Comput Graph Appl contributor: fullname: Pasztor – volume: 57 start-page: 289 year: 2009 end-page: 301 ident: b0065 article-title: A fast approach for over-complete sparse decomposition based on smoothed publication-title: IEEE Trans Signal Process contributor: fullname: Jutten – volume: 13 start-page: 600 year: 2004 end-page: 612 ident: b0085 article-title: Image quality assessment: form error visibility to structural similarity publication-title: IEEE Trans Image Process contributor: fullname: Sheikh – volume: 19 start-page: 2861 issue: 11 year: 2010 ident: 10.1016/j.compeleceng.2011.11.026_b0055 article-title: Image super-resolution via sparse representation publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2010.2050625 contributor: fullname: Yang – ident: 10.1016/j.compeleceng.2011.11.026_b0030 – volume: 57 start-page: 289 issue: 1 year: 2009 ident: 10.1016/j.compeleceng.2011.11.026_b0065 article-title: A fast approach for over-complete sparse decomposition based on smoothed L0 norm publication-title: IEEE Trans Signal Process doi: 10.1109/TSP.2008.2007606 contributor: fullname: Mohimani – ident: 10.1016/j.compeleceng.2011.11.026_b0050 – year: 2010 ident: 10.1016/j.compeleceng.2011.11.026_b0035 contributor: fullname: Milanfar – volume: 23 start-page: 791 year: 2005 ident: 10.1016/j.compeleceng.2011.11.026_b0015 article-title: A fast edge-oriented algorithm for image interpolation publication-title: Image Vis Comput doi: 10.1016/j.imavis.2005.05.005 contributor: fullname: Chen – volume: 13 start-page: 600 issue: 4 year: 2004 ident: 10.1016/j.compeleceng.2011.11.026_b0085 article-title: Image quality assessment: form error visibility to structural similarity publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2003.819861 contributor: fullname: Wang – year: 2009 ident: 10.1016/j.compeleceng.2011.11.026_b0070 contributor: fullname: Mallat – volume: 24 start-page: 1039 year: 2006 ident: 10.1016/j.compeleceng.2011.11.026_b0010 article-title: Image super-resolution survey publication-title: Image Vis Comput doi: 10.1016/j.imavis.2006.02.026 contributor: fullname: van Ouwerkerk – volume: 20 start-page: 21 issue: 3 year: 2003 ident: 10.1016/j.compeleceng.2011.11.026_b0005 article-title: Super-resolution image reconstruction: a technical overview publication-title: IEEE Signal Process Mag doi: 10.1109/MSP.2003.1203207 contributor: fullname: Park – volume: 22 start-page: 56 issue: 2 year: 2002 ident: 10.1016/j.compeleceng.2011.11.026_b0025 article-title: Example-based super-resolution publication-title: IEEE Trans Comput Graph Appl doi: 10.1109/38.988747 contributor: fullname: Freeman – volume: 8 start-page: 387 issue: 3 year: 1999 ident: 10.1016/j.compeleceng.2011.11.026_b0045 article-title: Superresolution restoration of an image sequence: adaptive filtering approach publication-title: IEEE Trans Image Process doi: 10.1109/83.748893 contributor: fullname: Elad – ident: 10.1016/j.compeleceng.2011.11.026_b0060 – ident: 10.1016/j.compeleceng.2011.11.026_b0020 – volume: 51 start-page: 34 issue: 1 year: 2009 ident: 10.1016/j.compeleceng.2011.11.026_b0075 article-title: From sparse solutions of systems of equations to sparse modeling of signals and images publication-title: SIAM Rev Soc Ind Appl Math contributor: fullname: Bruckstein – volume: 18 start-page: 1899 issue: 8 year: 2009 ident: 10.1016/j.compeleceng.2011.11.026_b0040 article-title: Super resolution with proballistic motion estimation publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2009.2022440 contributor: fullname: Protter – volume: 52 start-page: 1289 issue: 4 year: 2006 ident: 10.1016/j.compeleceng.2011.11.026_b0080 article-title: Compressed sensing publication-title: IEEE Trans Inf Theory doi: 10.1109/TIT.2006.871582 contributor: fullname: Donoho |
| SSID | ssj0004618 |
| Score | 2.0028257 |
| Snippet | [Display omitted]
► Universal dictionary and fixed sparsity are not beneficial to super-resolution. ► We use dictionary concatenation and more precise sparse... This paper proposes a different image super-resolution (SR) reconstruction scheme, based on the newly advanced results of sparse representation and the... |
| SourceID | proquest crossref elsevier |
| SourceType | Aggregation Database Publisher |
| StartPage | 1336 |
| SubjectTerms | Decomposition Dictionaries Mathematical models Minimization Norms Optimization Representations |
| Title | Image super-resolution by dictionary concatenation and sparse representation with approximate L0 norm minimization |
| URI | https://dx.doi.org/10.1016/j.compeleceng.2011.11.026 https://search.proquest.com/docview/1136564220 |
| Volume | 38 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8QwEB50BdGD-MTnEsFrNU2TZgteFlHW50nBW0jaqaxgXbq7oBd_u5M-cBUPgscWSss0-eabZL4vAEehRB45pwNUkgoUqfKgJ2wSuJ52uc16Uc69Gvn2Lh48yKtH9TgHZ60WxrdVNthfY3qF1s2dkyaaJ6Ph0Gt8pdIJ5SPvIkqpZx4Wqk2iDiz0L68HdzPyyLAGZOndGXm8CIdfbV6-c9ufOIPFU23o6T09vdXC72nqB2BXWehiFVYa-sj69ReuwRwW67A8Yyq4AeXlC2EEG09HWAZUTDdji7l3lg0rFYMt3xmVwb4Xql4LZLbIGEFLOUZWuVy2iqSC-XVaVhmPvw2J3CK74awgnsu8J8lLI-LchIeL8_uzQdCcrBCkIk4mgQuVFhinPYdZQrkrF8JZnqZRmOpM6Yg4jlJx7qyViGlGLMPFTmJiMePaWhVtQad4LXAbGJUkaeY0sUBuZSKVzTnKMBVCC6m1sjsg2kCaUW2gYdrOsmczE33jo08FiaHo78BpG3LzbTQYAvq_PH7Y_iZDs8VvgdgCX6dj40-wUVRyCb77v1fswRJdibrbbB86k3KKB0RPJq4L88cfYbcZhJ8HselD |
| link.rule.ids | 315,783,787,4511,24130,27938,27939,45599,45693 |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8QwEB58gI-D-MS3EbwW0zRptuBFRNnVdU8K3kLSTmUF69LdBf33TvrAVTwIXltKy3T6zTfpfF8AzkKJPHJOB6gkNShS5UFH2CRwHe1ym3WinHs18v0g7j7K2yf1NAdXrRbGj1U22F9jeoXWzZHzJprno-HQa3yl0gnVI-8iSqVnHhaJDSSU7IuXvbvuYEYeGdaALL07I4-X4PRrzMtPbvsdZ7B4rg09vaent1r4vUz9AOyqCt2sw1pDH9ll_YQbMIfFJqzOmApuQdl7JYxg4-kIy4Ca6Sa3mPtg2bBSMdjyg1Eb7Geh6rVAZouMEbSUY2SVy2WrSCqYX6dllfH4-5DILbI-ZwXxXOY9SV4bEec2PN5cP1x1g2ZnhSAVcTIJXKi0wDjtOMwSql25EM7yNI3CVGdKR8RxlIpzZ61ETDNiGS52EhOLGdfWqmgHFoq3AneBUUuSZk4TC-RWJlLZnKMMUyG0kForuweiDaQZ1QYapp0sezEz0Tc--tSQGIr-Hly0ITffssEQ0P_l8tP2NRn6WvwvEFvg23Rs_A42ilouwff_d4sTWO4-3PdNvze4O4AVOiPqybNDWJiUUzwiqjJxx00qfgLEXOtA |
| 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=Image+super-resolution+by+dictionary+concatenation+and+sparse+representation+with+approximate+L0+norm+minimization&rft.jtitle=Computers+%26+electrical+engineering&rft.au=Lu%2C+Jinzheng&rft.au=Zhang%2C+Qiheng&rft.au=Xu%2C+Zhiyong&rft.au=Peng%2C+Zhenming&rft.date=2012-09-01&rft.issn=0045-7906&rft.volume=38&rft.issue=5&rft.spage=1336&rft.epage=1345&rft_id=info:doi/10.1016%2Fj.compeleceng.2011.11.026&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0045-7906&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0045-7906&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0045-7906&client=summon |