Superpixel Segmentation Using Gaussian Mixture Model
Superpixel segmentation partitions an image into perceptually coherent segments of similar size, namely, superpixels. It is becoming a fundamental preprocessing step for various computer vision tasks because superpixels significantly reduce the number of inputs and provide a meaningful representatio...
Saved in:
| Published in | IEEE transactions on image processing Vol. 27; no. 8; pp. 4105 - 4117 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
IEEE
01.08.2018
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Superpixel segmentation partitions an image into perceptually coherent segments of similar size, namely, superpixels. It is becoming a fundamental preprocessing step for various computer vision tasks because superpixels significantly reduce the number of inputs and provide a meaningful representation for feature extraction. We present a pixel-related Gaussian mixture model (GMM) to segment images into superpixels. GMM is a weighted sum of Gaussian functions, each one corresponding to a superpixel, to describe the density of each pixel represented by a random variable. Different from previously proposed GMMs, our weights are constant, and Gaussian functions in the sums are subsets of all the Gaussian functions, resulting in segments of similar size and an algorithm of linear complexity with respect to the number of pixels. In addition to the linear complexity, our algorithm is inherently parallel and allows fast execution on multi-core systems. During the expectation-maximization iterations of estimating the unknown parameters in the Gaussian functions, we impose two lower bounds to truncate the eigenvalues of the covariance matrices, which enables the proposed algorithm to control the regularity of superpixels. Experiments on a well-known segmentation dataset show that our method can efficiently produce superpixels that adhere to object boundaries better than the current state-of-the-art methods. |
|---|---|
| AbstractList | Superpixel segmentation partitions an image into perceptually coherent segments of similar size, namely, superpixels. It is becoming a fundamental preprocessing step for various computer vision tasks because superpixels significantly reduce the number of inputs and provide a meaningful representation for feature extraction. We present a pixel-related Gaussian mixture model (GMM) to segment images into superpixels. GMM is a weighted sum of Gaussian functions, each one corresponding to a superpixel, to describe the density of each pixel represented by a random variable. Different from previously proposed GMMs, our weights are constant, and Gaussian functions in the sums are subsets of all the Gaussian functions, resulting in segments of similar size and an algorithm of linear complexity with respect to the number of pixels. In addition to the linear complexity, our algorithm is inherently parallel and allows fast execution on multicore systems. During the expectation-maximization iterations of estimating the unknown parameters in the Gaussian functions, we impose two lower bounds to truncate the eigenvalues of the covariance matrices, which enables the proposed algorithm to control the regularity of superpixels. Experiments on a wellknown segmentation dataset show that our method can efficiently produce superpixels that adhere to object boundaries better than the current state-of-the-art methods. Superpixel segmentation partitions an image into perceptually coherent segments of similar size, namely, superpixels. It is becoming a fundamental preprocessing step for various computer vision tasks because superpixels significantly reduce the number of inputs and provide a meaningful representation for feature extraction. We present a pixel-related Gaussian mixture model (GMM) to segment images into superpixels. GMM is a weighted sum of Gaussian functions, each one corresponding to a superpixel, to describe the density of each pixel represented by a random variable. Different from previously proposed GMMs, our weights are constant, and Gaussian functions in the sums are subsets of all the Gaussian functions, resulting in segments of similar size and an algorithm of linear complexity with respect to the number of pixels. In addition to the linear complexity, our algorithm is inherently parallel and allows fast execution on multi-core systems. During the expectation-maximization iterations of estimating the unknown parameters in the Gaussian functions, we impose two lower bounds to truncate the eigenvalues of the covariance matrices, which enables the proposed algorithm to control the regularity of superpixels. Experiments on a well-known segmentation dataset show that our method can efficiently produce superpixels that adhere to object boundaries better than the current state-of-the-art methods. Superpixel segmentation partitions an image into perceptually coherent segments of similar size, namely, superpixels. It is becoming a fundamental preprocessing step for various computer vision tasks because superpixels significantly reduce the number of inputs and provide a meaningful representation for feature extraction. We present a pixel-related Gaussian mixture model (GMM) to segment images into superpixels. GMM is a weighted sum of Gaussian functions, each one corresponding to a superpixel, to describe the density of each pixel represented by a random variable. Different from previously proposed GMMs, our weights are constant, and Gaussian functions in the sums are subsets of all the Gaussian functions, resulting in segments of similar size and an algorithm of linear complexity with respect to the number of pixels. In addition to the linear complexity, our algorithm is inherently parallel and allows fast execution on multicore systems. During the expectation-maximization iterations of estimating the unknown parameters in the Gaussian functions, we impose two lower bounds to truncate the eigenvalues of the covariance matrices, which enables the proposed algorithm to control the regularity of superpixels. Experiments on a wellknown segmentation dataset show that our method can efficiently produce superpixels that adhere to object boundaries better than the current state-of-the-art methods.Superpixel segmentation partitions an image into perceptually coherent segments of similar size, namely, superpixels. It is becoming a fundamental preprocessing step for various computer vision tasks because superpixels significantly reduce the number of inputs and provide a meaningful representation for feature extraction. We present a pixel-related Gaussian mixture model (GMM) to segment images into superpixels. GMM is a weighted sum of Gaussian functions, each one corresponding to a superpixel, to describe the density of each pixel represented by a random variable. Different from previously proposed GMMs, our weights are constant, and Gaussian functions in the sums are subsets of all the Gaussian functions, resulting in segments of similar size and an algorithm of linear complexity with respect to the number of pixels. In addition to the linear complexity, our algorithm is inherently parallel and allows fast execution on multicore systems. During the expectation-maximization iterations of estimating the unknown parameters in the Gaussian functions, we impose two lower bounds to truncate the eigenvalues of the covariance matrices, which enables the proposed algorithm to control the regularity of superpixels. Experiments on a wellknown segmentation dataset show that our method can efficiently produce superpixels that adhere to object boundaries better than the current state-of-the-art methods. |
| Author | Li Cao Jianguo Liu Zhihua Ban |
| Author_xml | – sequence: 1 givenname: Zhihua orcidid: 0000-0002-3209-4916 surname: Ban fullname: Ban, Zhihua – sequence: 2 givenname: Jianguo orcidid: 0000-0002-3620-3905 surname: Liu fullname: Liu, Jianguo – sequence: 3 givenname: Li surname: Cao fullname: Cao, Li |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/29994528$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kU1Lw0AQhhep2A-9C4Lk6CV1J7vZ7B6laC20KLQ9h91kUlbyZTaB-u9NSfXgwdMO7PPOMM9MyaisSiTkFugcgKrH3ep9HlCQ80Aywai4IBNQHHxKeTDqaxpGfgRcjcnUuQ9KgYcgrsg4UErxMJATwrddjU1tj5h7WzwUWLa6tVXp7Z0tD95Sd85ZXXobe2y7Br1NlWJ-TS4znTu8Ob8zsn953i1e_fXbcrV4WvsJA9X6GQI1gnNmKBgeKIgMgDRhIlioRQImkJmkSNOo56MEIBVaZybMTCSzhCk2Iw9D37qpPjt0bVxYl2Ce6xKrzsUBFZJxkDLq0fsz2pkC07hubKGbr_hn0x6gA5A0lXMNZr8I0PgkM-5lxieZ8VlmHxF_Iokd7LSNtvl_wbshaBHxd07_2R-AsW_wS3-y |
| CODEN | IIPRE4 |
| CitedBy_id | crossref_primary_10_32604_cmc_2024_046094 crossref_primary_10_1007_s11042_018_6774_y crossref_primary_10_3390_rs14153731 crossref_primary_10_1158_0008_5472_CAN_19_0573 crossref_primary_10_1007_s00521_023_08579_w crossref_primary_10_3390_s23021002 crossref_primary_10_1007_s00521_022_07315_0 crossref_primary_10_1109_TCSVT_2022_3221925 crossref_primary_10_1016_j_engappai_2023_107776 crossref_primary_10_1109_TIM_2025_3529072 crossref_primary_10_1007_s00371_020_01852_2 crossref_primary_10_1515_phys_2020_0101 crossref_primary_10_1109_TFUZZ_2019_2930030 crossref_primary_10_1016_j_sigpro_2019_02_015 crossref_primary_10_1109_TIP_2020_3002078 crossref_primary_10_3390_app9112276 crossref_primary_10_1038_s41598_024_68409_4 crossref_primary_10_1109_ACCESS_2021_3134887 crossref_primary_10_1007_s10851_023_01156_9 crossref_primary_10_1109_TIP_2019_2897941 crossref_primary_10_1080_21642583_2023_2185915 crossref_primary_10_1109_ACCESS_2024_3466906 crossref_primary_10_1016_j_scs_2021_103252 crossref_primary_10_1587_transinf_2019EDL8134 crossref_primary_10_1007_s11042_019_08438_8 crossref_primary_10_1016_j_isprsjprs_2024_01_002 crossref_primary_10_1007_s11042_018_6366_x crossref_primary_10_1109_TIM_2022_3165263 crossref_primary_10_1177_01423312241284660 crossref_primary_10_1109_TFUZZ_2022_3220925 crossref_primary_10_1155_2021_5538927 crossref_primary_10_32604_iasc_2022_024746 crossref_primary_10_3390_rs12071219 crossref_primary_10_1049_iet_ipr_2020_1179 crossref_primary_10_3390_s22186861 crossref_primary_10_1109_LGRS_2024_3454973 crossref_primary_10_3390_drones8040142 crossref_primary_10_1002_ima_22609 crossref_primary_10_1145_3652509 crossref_primary_10_1016_j_dsp_2023_103968 crossref_primary_10_1109_ACCESS_2024_3430931 crossref_primary_10_1109_TGRS_2024_3392971 crossref_primary_10_1049_iet_ipr_2020_0402 crossref_primary_10_1109_TIP_2020_2983554 crossref_primary_10_3390_app132413109 crossref_primary_10_3390_rs15051194 crossref_primary_10_1007_s11517_021_02352_8 crossref_primary_10_1109_TGRS_2025_3539732 crossref_primary_10_1007_s13369_021_05958_0 crossref_primary_10_1109_TGRS_2023_3294884 crossref_primary_10_1016_j_cma_2022_115066 crossref_primary_10_1007_s00158_019_02301_y crossref_primary_10_1109_TGRS_2022_3168126 crossref_primary_10_1109_TBME_2019_2957535 crossref_primary_10_1007_s11760_020_01647_x crossref_primary_10_1016_j_sigpro_2021_107990 crossref_primary_10_1109_TGRS_2022_3161139 crossref_primary_10_1016_j_infrared_2022_104400 crossref_primary_10_1109_ACCESS_2021_3081919 crossref_primary_10_1016_j_ress_2021_107885 crossref_primary_10_1587_transinf_2019EDP7322 crossref_primary_10_1109_JPHOTOV_2022_3215890 crossref_primary_10_1109_TBDATA_2024_3423719 crossref_primary_10_1016_j_ibmed_2024_100168 crossref_primary_10_1049_ipr2_12744 crossref_primary_10_1109_ACCESS_2020_2973286 crossref_primary_10_1109_TMM_2022_3141606 crossref_primary_10_1088_2051_672X_ad4571 crossref_primary_10_1016_j_patcog_2023_109673 crossref_primary_10_1016_j_matpr_2020_08_618 crossref_primary_10_1016_j_neucom_2021_08_039 crossref_primary_10_1007_s42979_021_00879_z crossref_primary_10_1016_j_crmeth_2023_100636 crossref_primary_10_1109_TCSVT_2022_3216303 crossref_primary_10_1016_j_cag_2020_12_002 crossref_primary_10_1080_08839514_2022_2094408 crossref_primary_10_1109_TIP_2021_3108403 crossref_primary_10_1007_s11042_021_11261_9 crossref_primary_10_1117_1_JRS_14_026521 crossref_primary_10_1007_s11042_023_14439_5 crossref_primary_10_1360_SSI_2022_0408 crossref_primary_10_3390_electronics12163481 crossref_primary_10_1016_j_ymssp_2023_110113 crossref_primary_10_1016_j_imavis_2022_104596 |
| Cites_doi | 10.1109/TPAMI.2010.161 10.1109/CVPR.2016.77 10.1109/ICCV.2005.112 10.1109/ICIP.2015.7351706 10.1007/s10044-014-0406-6 10.1023/B:VISI.0000022288.19776.77 10.1007/s11263-012-0588-6 10.1049/el.2014.3379 10.1109/TIP.2015.2401516 10.1007/s11554-016-0652-5 10.1145/1276377.1276390 10.1007/978-3-540-74936-3_26 10.1016/j.image.2017.04.007 10.1109/TGRS.2015.2441954 10.1109/ICME.2012.184 10.1109/TPAMI.2016.2552172 10.1109/CVPR.2014.49 10.1109/TPAMI.2004.1273918 10.1109/TMM.2014.2305571 10.1007/978-3-319-10602-1_49 10.1109/TIP.2015.2451011 10.1109/TIP.2014.2302892 10.1109/34.87344 10.5244/C.27.54 10.1016/j.patcog.2015.01.002 10.1007/978-1-4899-7488-4_196 10.1007/s11263-014-0744-2 10.1109/ICPR.2014.181 10.1016/j.neucom.2014.04.037 10.1109/TCSVT.2015.2430631 10.1109/CVPR.2011.5995323 10.1109/CVPR.2008.4587471 10.1109/TIP.2014.2300823 10.1109/ICIP.2015.7351017 10.1016/j.jvcir.2016.08.001 10.1109/ICCV.2011.6126393 10.1109/TPAMI.2009.96 10.1109/CRV.2014.25 10.1109/ICCV.2003.1238308 10.1109/34.868688 10.1109/TPAMI.2012.120 10.1109/ICIAFS.2014.7069599 10.1109/CVPR.2015.7299002 10.1109/TPAMI.2012.47 10.1109/CVPR.2015.7298913 10.1109/CVPR.2015.7298931 10.1109/34.1000236 |
| ContentType | Journal Article |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7X8 |
| DOI | 10.1109/TIP.2018.2836306 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | PubMed MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE/IET Electronic Library url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Engineering |
| EISSN | 1941-0042 |
| EndPage | 4117 |
| ExternalDocumentID | 29994528 10_1109_TIP_2018_2836306 8360143 |
| Genre | orig-research Journal Article |
| GroupedDBID | --- -~X .DC 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABFSI ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P RIA RIE RNS TAE TN5 VH1 AAYOK AAYXX CITATION RIG NPM Z5M 7X8 |
| ID | FETCH-LOGICAL-c319t-fe10b6443b01b42917b118b5c635a6c1b28f80e0d7c317c11d6aafb5fb78fc393 |
| IEDL.DBID | RIE |
| ISSN | 1057-7149 1941-0042 |
| IngestDate | Fri Jul 11 07:14:46 EDT 2025 Wed Feb 19 02:09:29 EST 2025 Thu Apr 24 23:08:24 EDT 2025 Tue Jul 01 02:03:17 EDT 2025 Wed Aug 27 02:49:00 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 8 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c319t-fe10b6443b01b42917b118b5c635a6c1b28f80e0d7c317c11d6aafb5fb78fc393 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0002-3620-3905 0000-0002-3209-4916 |
| PMID | 29994528 |
| PQID | 2068341887 |
| PQPubID | 23479 |
| PageCount | 13 |
| ParticipantIDs | crossref_primary_10_1109_TIP_2018_2836306 ieee_primary_8360143 pubmed_primary_29994528 crossref_citationtrail_10_1109_TIP_2018_2836306 proquest_miscellaneous_2068341887 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2018-08-01 |
| PublicationDateYYYYMMDD | 2018-08-01 |
| PublicationDate_xml | – month: 08 year: 2018 text: 2018-08-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | IEEE transactions on image processing |
| PublicationTitleAbbrev | TIP |
| PublicationTitleAlternate | IEEE Trans Image Process |
| PublicationYear | 2018 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| References | ref57 ref13 ref56 ref12 ref15 neubert (ref59) 2012 ref14 ref53 ref52 ref55 ref11 ref54 ref10 ref17 ref16 ref19 ref18 ref51 ref50 ref46 ref48 ref47 ref42 ref41 ref44 ref43 veksler (ref32) 2010 moore (ref35) 2010 ref49 ref8 vedaldi (ref26) 2008 ref7 neubert (ref27) 2012 van den bergh (ref40) 2012 ref4 ref3 ref6 ref5 li (ref9) 2015 zhang (ref24) 2017; 27 ref37 ref36 ref31 ref30 ren (ref45) 2015 ref2 ref39 li (ref33) 2015 ref38 schick (ref58) 2012 avidan (ref34) 2007; 26 ref23 ref25 ref20 ref22 ref21 ref28 ref29 li (ref1) 2012 |
| References_xml | – ident: ref57 doi: 10.1109/TPAMI.2010.161 – ident: ref55 doi: 10.1109/CVPR.2016.77 – ident: ref30 doi: 10.1109/ICCV.2005.112 – ident: ref47 doi: 10.1109/ICIP.2015.7351706 – ident: ref19 doi: 10.1007/s10044-014-0406-6 – ident: ref49 doi: 10.1023/B:VISI.0000022288.19776.77 – ident: ref56 doi: 10.1007/s11263-012-0588-6 – ident: ref46 doi: 10.1049/el.2014.3379 – ident: ref2 doi: 10.1109/TIP.2015.2401516 – start-page: 970 year: 2015 ident: ref33 article-title: Edge-based split-and-merge superpixel segmentation publication-title: Proc ICIAP – ident: ref48 doi: 10.1007/s11554-016-0652-5 – year: 2012 ident: ref59 article-title: Superpixels and their application for visual place recognition in changing environments – volume: 26 start-page: 10 year: 2007 ident: ref34 article-title: Seam carving for content-aware image resizing publication-title: Trans Graph doi: 10.1145/1276377.1276390 – ident: ref41 doi: 10.1007/978-3-540-74936-3_26 – ident: ref28 doi: 10.1016/j.image.2017.04.007 – ident: ref5 doi: 10.1109/TGRS.2015.2441954 – ident: ref37 doi: 10.1109/ICME.2012.184 – ident: ref53 doi: 10.1109/TPAMI.2016.2552172 – ident: ref52 doi: 10.1109/CVPR.2014.49 – ident: ref31 doi: 10.1109/TPAMI.2004.1273918 – start-page: 1 year: 2012 ident: ref27 article-title: Superpixel benchmark and comparison publication-title: Proc Forum Bildverarbeitung – start-page: 13 year: 2012 ident: ref40 article-title: SEEDS: Superpixels extracted via energy-driven sampling publication-title: Proc ECCV – ident: ref36 doi: 10.1109/TMM.2014.2305571 – ident: ref42 doi: 10.1007/978-3-319-10602-1_49 – start-page: 789 year: 2012 ident: ref1 article-title: Segmentation using superpixels: A bipartite graph partitioning approach publication-title: Proc CVPR – ident: ref11 doi: 10.1109/TIP.2015.2451011 – ident: ref15 doi: 10.1109/TIP.2014.2302892 – ident: ref51 doi: 10.1109/34.87344 – ident: ref29 doi: 10.5244/C.27.54 – start-page: 705 year: 2008 ident: ref26 article-title: Quick shift and kernel methods for mode seeking publication-title: Proc ECCV – ident: ref4 doi: 10.1016/j.patcog.2015.01.002 – ident: ref18 doi: 10.1007/978-1-4899-7488-4_196 – ident: ref7 doi: 10.1007/s11263-014-0744-2 – ident: ref13 doi: 10.1109/ICPR.2014.181 – ident: ref20 doi: 10.1016/j.neucom.2014.04.037 – start-page: 2117 year: 2010 ident: ref35 article-title: 'Lattice Cut'-Constructing superpixels using layer constraints publication-title: Proc CVPR – ident: ref23 doi: 10.1109/TCSVT.2015.2430631 – ident: ref8 doi: 10.1109/CVPR.2011.5995323 – ident: ref16 doi: 10.1109/CVPR.2008.4587471 – ident: ref3 doi: 10.1109/TIP.2014.2300823 – ident: ref39 doi: 10.1109/ICIP.2015.7351017 – ident: ref21 doi: 10.1016/j.jvcir.2016.08.001 – start-page: 211 year: 2010 ident: ref32 article-title: Superpixels and supervoxels in an energy optimization framework publication-title: Proc ECCV – ident: ref25 doi: 10.1109/ICCV.2011.6126393 – volume: 27 start-page: 1502 year: 2017 ident: ref24 article-title: A simple algorithm of superpixel segmentation with boundary constraint publication-title: IEEE Trans Circuits Syst Video Technol – start-page: 1356 year: 2015 ident: ref9 article-title: Superpixel segmentation using linear spectral clustering publication-title: Proc CVPR – year: 2015 ident: ref45 publication-title: gSLICr SLIC superpixels at over 250 Hz – ident: ref12 doi: 10.1109/TPAMI.2009.96 – ident: ref38 doi: 10.1109/CRV.2014.25 – ident: ref22 doi: 10.1109/ICCV.2003.1238308 – ident: ref17 doi: 10.1109/34.868688 – start-page: 930 year: 2012 ident: ref58 article-title: Measuring and evaluating the compactness of superpixels publication-title: Proc ICPR – ident: ref10 doi: 10.1109/TPAMI.2012.120 – ident: ref44 doi: 10.1109/ICIAFS.2014.7069599 – ident: ref54 doi: 10.1109/CVPR.2015.7299002 – ident: ref6 doi: 10.1109/TPAMI.2012.47 – ident: ref43 doi: 10.1109/CVPR.2015.7298913 – ident: ref14 doi: 10.1109/CVPR.2015.7298931 – ident: ref50 doi: 10.1109/34.1000236 |
| SSID | ssj0014516 |
| Score | 2.5680523 |
| Snippet | Superpixel segmentation partitions an image into perceptually coherent segments of similar size, namely, superpixels. It is becoming a fundamental... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 4105 |
| SubjectTerms | Computational complexity Covariance matrices Erbium expectation-maximization Feature extraction Gaussian mixture model Image color analysis Image segmentation parallel algorithms Shape Superpixel |
| Title | Superpixel Segmentation Using Gaussian Mixture Model |
| URI | https://ieeexplore.ieee.org/document/8360143 https://www.ncbi.nlm.nih.gov/pubmed/29994528 https://www.proquest.com/docview/2068341887 |
| Volume | 27 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1bS8MwFD7onvTB6bzNGxV8EeyWXpM-iqhTmAgq-FaSNJHh7Ma2wvDXe5J2ZYiKD4VCkzTJSfp96bkBnPnUk5zRzPUzlrlhIANXcBG4CVPaU0TGwsbp7j_EvZfw_jV6XYGL2hdGKWWNz1TH3FpdfjaShflV1jUOB4jvq7CKB7fSV6vWGJiEs1azGVGXIu1fqCRJ0n2-ezQ2XKyDUBoHJrfREgTZnCq_00sLMzdN6C86WFqXvHeKmejIz2-xG_87gk3YqPimc1kukC1YUXkLmhX3dKqdPW3B-lJgwm0In4qxmowHczV0ntTbR-WglDvWwsC55cXUOF86_cHcaCAck1FtuAMvN9fPVz23yq_gStx4M1crjwjkQ4EgnkBc8qjA44aIJJIQHktP-EwzokhGsTyVnpfFnGsRaUGZlkES7EIjH-VqHxyNTzmOFi8WZthQKLmxWyVUkyTTtA3dxZSnsgo-bnJgDFN7CCFJikJKjZDSSkhtOK9rjMvAG3-U3TZTXZerZrkNpwupprhpjCaE52pUTLFyzBC-8QPbhr1S3HVlxOckjHx28HOjh7BmXl3aAB5BYzYp1DHykpk4sQvyC_6m3c4 |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwzV1PTxQxFH8heEAPIKCyilgTPXiY3c7fdg4cjAK7whITloTb2HZaQ1hmN-xORD8LX4Xv5munOyFEvZF4mGSSaZuZvtf3fm_eP4B3EQuV4KwMopKXQRKrOJBCxkHOtQk1VZl0dbqHx1n_NPlylp4twU2bC6O1dsFnumtvnS-_nKja_irr2YQD1O8-hPJQ__yBBtpsd_AZqfk-ivb3Rp_6ge8hEChkrnlgdEgl6vxY0lCi7A2ZREgtU4WKVmQqlBE3nGpaMhzPVBiWmRBGpkYyblRsSy2hgH-EOCONmuyw1kdhW9w6X2rKAoaGxsIJSvPeaPDVRo3xLirvLLbdlO4oPdfF5e-A1im2_TW4XWxJE89y0a3nsqt-3asW-b_u2VNY9YiafGyOwDos6WoD1jy6Jl52zTbgyZ3Si5uQnNRTfTU9v9ZjcqK_X_oUrIq4GApyIOqZTS8lw_Nr62Mhtmfc-BmcPsiXPIflalLpLSAGnwrcXbx4UuJCiRI2MpcyQ_PSsA70FiQulC-vbrt8jAtnZtG8QKYoLFMUnik68KGdMW1Ki_xj7KYlbTvOU7UDbxdcVKBYsL4eUelJPcPJGUeAgiqkAy8a9monIwLJkzTiL_-86BtY6Y-GR8XR4PjwFTy2r9FEPG7D8vyq1q8Rhc3ljjsMBL49NCf9BiPnO1A |
| 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=Superpixel+Segmentation+Using+Gaussian+Mixture+Model&rft.jtitle=IEEE+transactions+on+image+processing&rft.au=Ban%2C+Zhihua&rft.au=Liu%2C+Jianguo&rft.au=Cao%2C+Li&rft.date=2018-08-01&rft.issn=1941-0042&rft.eissn=1941-0042&rft_id=info:doi/10.1109%2FTIP.2018.2836306&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1057-7149&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1057-7149&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1057-7149&client=summon |