Login
Login

automatic image annotation

File:DenseCap (Johnson et al., 2016) (cropped).png

Automatic image annotation (also known as automatic image tagging or linguistic indexing) is the process by which a computer system automatically assigns metadata in the form of captioning or keywords to a digital image. This application of computer vision techniques is used in image retrieval systems to organize and locate images of interest from a database.

This method can be regarded as a type of multi-class image classification with a very large number of classes - as large as the vocabulary size. Typically, image analysis in the form of extracted feature vectors and the training annotation words are used by machine learning techniques to attempt to automatically apply annotations to new images.{{Cite journal |last=Barrat |first=Sabine |last2=Tabbone |first2=Salvatore |date=2010-05-01 |title=Modeling, classifying and annotating weakly annotated images using Bayesian network |url=https://www.sciencedirect.com/science/article/abs/pii/S1047320310000301 |journal=Journal of Visual Communication and Image Representation |volume=21 |issue=4 |pages=355–363 |doi=10.1016/j.jvcir.2010.02.010 |issn=1047-3203}} The first methods learned the correlations between image features and training annotations. Subsequently, techniques were developed using machine translation to to attempt to translate the textual vocabulary into the 'visual vocabulary,' represented by clustered regions known as blobs. Subsequent work has included classification approaches, relevance models, and other related methods.

The advantages of automatic image annotation versus content-based image retrieval (CBIR) are that queries can be more naturally specified by the user.{{cite web |url=http://i.yz.yamagata-u.ac.jp/paper/inoue04irix.pdf |title=Archived copy |website=i.yz.yamagata-u.ac.jp |access-date=13 January 2022 |archive-url=https://web.archive.org/web/20140808134447/http://i.yz.yamagata-u.ac.jp/paper/inoue04irix.pdf |archive-date=8 August 2014 |url-status=dead}} At present, Content-Based Image Retrieval (CBIR) generally requires users to search by image concepts such as color and texture or by finding example queries. However, certain image features in example images may override the concept that the user is truly focusing on. Traditional methods of image retrieval, such as those used by libraries, have relied on manually annotated images, which is expensive and time-consuming, especially given the large and constantly growing image databases in existence.

See also

References

{{Reflist}}

  • {{cite journal | last=Datta | first=Ritendra |author2=Dhiraj Joshi |author3=Jia Li |author3-link=Jia Li|author4=James Z. Wang | title=Image Retrieval: Ideas, Influences, and Trends of the New Age | journal=ACM Computing Surveys | url=http://infolab.stanford.edu/~wangz/project/imsearch/review/JOUR/ | year=2008 | doi=10.1145/1348246.1348248 | volume=40 | pages=1–60 | issue=2| s2cid=7060187 }}
  • {{cite conference|author=Nicolas Hervé |author2=Nozha Boujemaa |url=http://www-rocq.inria.fr/~nherve/nherve_civr2007.pdf |title=Image annotation : which approach for realistic databases ? |book-title=ACM International Conference on Image and Video Retrieval |year=2007 |url-status=dead |archive-url=https://web.archive.org/web/20110520140240/http://www-rocq.inria.fr/~nherve/nherve_civr2007.pdf |archive-date=2011-05-20 }}
  • {{cite conference|author=M Inoue |url=http://i.yz.yamagata-u.ac.jp/paper/inoue04irix.pdf |title=On the need for annotation-based image retrieval |book-title=Workshop on Information Retrieval in Context |year=2004 |pages=44–46 |url-status=dead |archive-url=https://web.archive.org/web/20140808134447/http://i.yz.yamagata-u.ac.jp/paper/inoue04irix.pdf |archive-date=2014-08-08 }}

Further reading

{{cleanup-section|reason=long and multiline format|date=November 2022}}

  • Word co-occurrence model

:{{cite conference |author1=Y Mori |author2=H Takahashi |author3=R Oka |name-list-style=amp | title=Image-to-word transformation based on dividing and vector quantizing images with words. | book-title=Proceedings of the International Workshop on Multimedia Intelligent Storage and Retrieval Management | year=1999 |citeseerx=10.1.1.31.1704 }}

  • Annotation as machine translation

:{{cite conference|author1=P Duygulu |author2=K Barnard |author3=N de Fretias |author4=D Forsyth |name-list-style=amp |url=http://vision.cs.arizona.edu/kobus/research/publications/ECCV-02-1/ |title=Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary |book-title=Proceedings of the European Conference on Computer Vision |year=2002 |pages=97–112 |url-status=dead |archive-url=https://web.archive.org/web/20050305174408/http://vision.cs.arizona.edu/kobus/research/publications/ECCV-02-1/ |archive-date=2005-03-05 }}

  • Statistical models

:{{cite conference |author1=J Li |author2=J Z Wang |name-list-style=amp | url=http://www-db.stanford.edu/~wangz/project/imsearch/ALIP/ACMMM06/ | title=Real-time Computerized Annotation of Pictures | book-title=Proc. ACM Multimedia | year=2006 | pages=911–920}}

:{{cite conference |author1=J Z Wang |author2=J Li |name-list-style=amp | url=http://www-db.stanford.edu/~wangz/project/imsearch/ALIP/ACM02/ | title=Learning-Based Linguistic Indexing of Pictures with 2-D MHMMs | book-title=Proc. ACM Multimedia | year=2002 | pages=436–445}}

  • Automatic linguistic indexing of pictures

:{{cite conference |author1=J Li |author2=J Z Wang |name-list-style=amp | url=http://infolab.stanford.edu/~wangz/project/imsearch/ALIP/PAMI08/ | title=Real-time Computerized Annotation of Pictures | book-title=IEEE Transactions on Pattern Analysis and Machine Intelligence | year=2008 }}

:{{cite conference |author1=J Li |author2=J Z Wang |name-list-style=amp | url=http://www-db.stanford.edu/~wangz/project/imsearch/ALIP/PAMI03/ | title=Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach | book-title=IEEE Transactions on Pattern Analysis and Machine Intelligence | year=2003 | pages=1075–1088}}

  • Hierarchical Aspect Cluster Model

:{{cite conference|author1=K Barnard |author2=D A Forsyth |url=http://kobus.ca/research/publications/ICCV-01/ |title=Learning the Semantics of Words and Pictures |book-title=Proceedings of International Conference on Computer Vision |year=2001 |pages=408–415 |url-status=dead |archive-url=https://web.archive.org/web/20070928161148/http://kobus.ca/research/publications/ICCV-01/ |archive-date=2007-09-28 }}

  • Latent Dirichlet Allocation model

:{{cite conference|author1=D Blei |author2=A Ng |author3=M Jordan |name-list-style=amp |url=http://www.ics.uci.edu/~liang/seminars/win05/papers/blei03-latent-dirichlet.pdf |archive-url=https://web.archive.org/web/20050316213517/http://www.ics.uci.edu/~liang/seminars/win05/papers/blei03-latent-dirichlet.pdf |url-status=dead |archive-date=March 16, 2005 |title=Latent Dirichlet allocation |book-title=Journal of Machine Learning Research |year=2003 |pages=3:993–1022 }}

:{{cite conference |author1=G Carneiro |author2=A B Chan |author3=P Moreno |author4=N Vasconcelos |name-list-style=amp | url=http://www.svcl.ucsd.edu/publications/journal/2007/pami/pami07-semantics.pdf | title=Supervised Learning of Semantic Classes for Image Annotation and Retrieval| book-title=IEEE Transactions on Pattern Analysis and Machine Intelligence | year=2006 | pages=394–410}}

  • Texture similarity

:{{cite conference |author1=R W Picard |author2=T P Minka |name-list-style=amp | url=http://citeseer.ist.psu.edu/picard95vision.html | title=Vision Texture for Annotation | book-title=Multimedia Systems | year=1995 }}

  • Support Vector Machines

:{{cite journal |author1=C Cusano |author2=G Ciocca |author3=R Scettini |editor-first1=Simone |editor-first2=Raimondo |editor-last1=Santini |editor-last2=Schettini |name-list-style=amp | title=Image Annotation Using SVM |journal=Internet Imaging V |volume=5304 | year=2004 | pages=330–338|bibcode=2003SPIE.5304..330C |doi=10.1117/12.526746 |s2cid=16246057 }}

  • Ensemble of Decision Trees and Random Subwindows

:{{cite conference |author1=R Maree |author2=P Geurts |author3=J Piater |author4=L Wehenkel |name-list-style=amp |

url=http://www.montefiore.ulg.ac.be/~maree/#publications | title=Random Subwindows for Robust Image Classification |

book-title=Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition | year=2005 | pages=1:34–30}}

  • Maximum Entropy

:{{cite conference |author1=J Jeon |author2=R Manmatha | url=http://ciir.cs.umass.edu/pubfiles/mm-355.pdf | title=Using Maximum Entropy for Automatic Image Annotation | book-title=Int'l Conf on Image and Video Retrieval (CIVR 2004)| year=2004 | pages=24–32}}

  • Relevance models

:{{cite conference |author1=J Jeon |author2=V Lavrenko |author3=R Manmatha |name-list-style=amp | url=http://ciir.cs.umass.edu/pubfiles/mm-41.pdf | title=Automatic image annotation and retrieval using cross-media relevance models | book-title=Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval | year=2003 | pages=119–126}}

  • Relevance models using continuous probability density functions

:{{cite conference |author1=V Lavrenko |author2=R Manmatha |author3=J Jeon |name-list-style=amp | url=http://ciir.cs.umass.edu/pubfiles/mm-46.pdf | title=A model for learning the semantics of pictures | book-title=Proceedings of the 16th Conference on Advances in Neural Information Processing Systems NIPS | year=2003 }}

  • Coherent Language Model

:{{cite conference |author1=R Jin |author2=J Y Chai |author3=L Si | url=http://www.cse.msu.edu/~rongjin/publications/acmmm04.jin.pdf | title=Effective Automatic Image Annotation via A Coherent Language Model and Active Learning | book-title=Proceedings of MM'04 | year=2004 }}

  • Inference networks

:{{cite conference |author1=D Metzler |author2=R Manmatha |name-list-style=amp | url=http://ciir.cs.umass.edu/pubfiles/mm-346.pdf | title=An inference network approach to image retrieval | book-title=Proceedings of the International Conference on Image and Video Retrieval | year=2004 | pages=42–50}}

  • Multiple Bernoulli distribution

:{{cite conference |author1=S Feng |author2=R Manmatha |author3=V Lavrenko |name-list-style=amp | url=http://ciir.cs.umass.edu/pubfiles/mm-333.pdf | title=Multiple Bernoulli relevance models for image and video annotation | book-title=IEEE Conference on Computer Vision and Pattern Recognition | year=2004 | pages=1002–1009}}

  • Multiple design alternatives

:{{cite conference|author1=J Y Pan |author2=H-J Yang |author3=P Duygulu |author4=C Faloutsos |url=http://www.informedia.cs.cmu.edu/documents/ICME04AutoICap.pdf |title=Automatic Image Captioning |book-title=Proceedings of the 2004 IEEE International Conference on Multimedia and Expo (ICME'04) |year=2004 |url-status=dead |archive-url=https://web.archive.org/web/20041209191242/http://www.informedia.cs.cmu.edu/documents/ICME04AutoICap.pdf |archive-date=2004-12-09 }}

  • Image captioning

:{{cite conference|author1=Quan Hoang Lam |author2=Quang Duy Le |author3=Kiet Van Nguyen |author4=Ngan Luu-Thuy Nguyen |url=https://link.springer.com/chapter/10.1007/978-3-030-63007-2_57 |title=UIT-ViIC: A Dataset for the First Evaluation on Vietnamese Image Captioning |book-title=Proceedings of the 2020 International Conference on Computational Collective Intelligence (ICCCI 2020) |year=2020 |doi=10.1007/978-3-030-63007-2_57 |arxiv=2002.00175 }}

  • Natural scene annotation

:{{cite conference |author1=J Fan |author2=Y Gao |author3=H Luo |author4=G Xu | url=http://portal.acm.org/ft_gateway.cfm?id=1009055&type=pdf&coll=GUIDE&dl=GUIDE&CFID=1581830&CFTOKEN=99651762 | title=Automatic Image Annotation by Using Concept-Sensitive Salient Objects for Image Content Representation | book-title=Proceedings of the 27th annual international conference on Research and development in information retrieval | year=2004 | pages=361–368}}

  • Relevant low-level global filters

:{{cite conference |author1=A Oliva |author2=A Torralba |name-list-style=amp | url=http://cvcl.mit.edu/Papers/IJCV01-Oliva-Torralba.pdf | title=Modeling the shape of the scene: a holistic representation of the spatial envelope | book-title=International Journal of Computer Vision | year=2001 | pages=42:145–175}}

  • Global image features and nonparametric density estimation

:{{cite conference|author1=A Yavlinsky, E Schofield |author2=S Rüger |name-list-style=amp |url=http://km.doc.ic.ac.uk/www-pub/civr05-annotation.pdf |title=Automated Image Annotation Using Global Features and Robust Nonparametric Density Estimation |book-title=Int'l Conf on Image and Video Retrieval (CIVR, Singapore, Jul 2005) |year=2005 |url-status=dead |archive-url=https://web.archive.org/web/20051220164354/http://km.doc.ic.ac.uk/www-pub/civr05-annotation.pdf |archive-date=2005-12-20 }}

  • Video semantics

:{{cite conference |author1=N Vasconcelos |author2=A Lippman |name-list-style=amp | url=http://www.svcl.ucsd.edu/publications/journal/2000/ip/ip00.pdf | title=Statistical Models of Video Structure for Content Analysis and Characterization | book-title=IEEE Transactions on Image Processing | year=2001 | pages=1–17}}

:{{cite conference |author1=Ilaria Bartolini |author2=Marco Patella |author3=Corrado Romani |name-list-style=amp |

url=http://dl.acm.org/citation.cfm?doid=1862344.1862364 | title=Shiatsu: Semantic-based Hierarchical Automatic Tagging of Videos by Segmentation Using Cuts | book-title=3rd ACM International Multimedia Workshop on Automated Information Extraction in Media Production (AIEMPro10) | year=2010}}

  • Image Annotation Refinement

:{{cite conference |author1=Yohan Jin |author2-link=Latifur Khan |author2=Latifur Khan |author3=Lei Wang |author4=Mamoun Awad |name-list-style=amp | url=http://portal.acm.org/citation.cfm?id=1101305&dl=GUIDE, | title=Image annotations by combining multiple evidence & wordNet | book-title=13th Annual ACM International Conference on Multimedia (MM 05) |year=2005 | pages=706–715}}

:{{cite conference |author1=Changhu Wang |author2=Feng Jing |author3=Lei Zhang |author4=Hong-Jiang Zhang |name-list-style=amp |

url=http://portal.acm.org/citation.cfm?id=1180639.1180774#, | title=Image annotation refinement using random walk with restarts | book-title =14th Annual ACM International Conference on Multimedia (MM 06) |year=2006}}

:{{cite conference |author1=Changhu Wang |author2=Feng Jing |author3=Lei Zhang |author4=Hong-Jiang Zhang |name-list-style=amp | title=content-based image annotation refinement | book-title=IEEE Conference on Computer Vision and Pattern Recognition (CVPR 07)| year=2007|doi=10.1109/CVPR.2007.383221 }}

:{{cite conference |author1=Ilaria Bartolini |author2=Paolo Ciaccia |name-list-style=amp | title=Imagination: Exploiting Link Analysis for Accurate Image Annotation | book-title=Springer Adaptive Multimedia Retrieval | year=2007|doi=10.1007/978-3-540-79860-6_3 }}

:{{cite conference |author1=Ilaria Bartolini |author2=Paolo Ciaccia |name-list-style=amp |

url=http://dl.acm.org/citation.cfm?doid=1868366.1868371 | title=Multi-dimensional Keyword-based Image Annotation and Search | book-title=2nd ACM International Workshop on Keyword Search on Structured Data (KEYS 2010)| year=2010}}

  • Automatic Image Annotation by Ensemble of Visual Descriptors

:{{cite conference |author1=Emre Akbas |author2=Fatos Y. Vural |name-list-style=amp | title=Automatic Image Annotation by Ensemble of Visual Descriptors | book-title=Intl. Conf. on Computer Vision (CVPR) 2007, Workshop on Semantic Learning Applications in Multimedia | year=2007|doi=10.1109/CVPR.2007.383484 |hdl=11511/16027 |hdl-access=free }}

  • A New Baseline for Image Annotation

:{{cite conference | author=Ameesh Makadia and Vladimir Pavlovic and Sanjiv Kumar | url=http://www.cs.rutgers.edu/~vladimir/pub/makadia08eccv.pdf | title=A New Baseline for Image Annotation | book-title= European Conference on Computer Vision (ECCV) | year=2008}}

Simultaneous Image Classification and Annotation

:{{cite conference | author=Chong Wang and David Blei and Li Fei-Fei | url=http://cs.stanford.edu/groups/vision/documents/WangBleiFei-Fei_CVPR2009.pdf | title=Simultaneous Image Classification and Annotation | book-title=Conf. on Computer Vision and Pattern Recognition (CVPR) | year=2009}}

  • TagProp: Discriminative Metric Learning in Nearest Neighbor Models for Image Auto-Annotation

:{{cite conference | author=Matthieu Guillaumin and Thomas Mensink and Jakob Verbeek and Cordelia Schmid | url=https://lear.inrialpes.fr/pubs/2009/GMVS09/GMVS09.pdf | title=TagProp: Discriminative Metric Learning in Nearest Neighbor Models for Image Auto-Annotation | book-title=Intl. Conf. on Computer Vision (ICCV) | year=2009}}

  • Image Annotation Using Metric Learning in Semantic Neighbourhoods

:{{cite conference |author1=Yashaswi Verma |author2=C. V. Jawahar |name-list-style=amp |url=http://researchweb.iiit.ac.in/~yashaswi.verma/eccv12/vj_eccv12.pdf |title=Image Annotation Using Metric Learning in Semantic Neighbourhoods |book-title=European Conference on Computer Vision (ECCV) |year=2012 |access-date=2014-02-26 |archive-url=https://web.archive.org/web/20130514202446/http://researchweb.iiit.ac.in/%7Eyashaswi.verma/eccv12/vj_eccv12.pdf |archive-date=2013-05-14 |url-status=dead }}

  • Automatic Image Annotation Using Deep Learning Representations

:{{cite conference |author1=Venkatesh N. Murthy |author2=Subhransu Maji and R. Manmatha |name-list-style=amp | url=https://people.cs.umass.edu/~smaji/papers/embeddings-icmr15s.pdf | title=Automatic Image Annotation Using Deep Learning Representations | book-title= International Conference on Multimedia (ICMR) | year=2015}}

  • Holistic Image Annotation using Salient Regions and Background Image Information

:{{cite conference |last1 = Sarin|last2= Fahrmair|name-list-style=amp|

url=https://www.jstage.jst.go.jp/article/ipsjjip/20/1/20_1_250/_pdf/-char/en| title = Leveraging Features from Background and Salient Regions for Automatic Image Annotation| book-title=

| year = 2012|first1=Supheakmungkol|volume=20|pages=250–266|conference=Journal of Information Processing|first2=Michael|last3=Wagner|first3=Matthias|last4=Kameyama|first4=Wataru}}

  • Medical Image Annotation using bayesian networks and active learning

:{{cite conference |author1 = N. B. Marvasti|author2= E. Yörük and B. Acar|name-list-style=amp|

url=https://www.researchgate.net/publication/320935564| title = Computer-Aided Medical Image Annotation: Preliminary Results With Liver Lesions in CT| book-title= IEEE Journal of Biomedical and Health Informatics

| year = 2018}}

{{Computer vision}}

Category:Applications of artificial intelligence

Category:Applications of computer vision