{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T17:52:50Z","timestamp":1754157170122,"version":"3.41.2"},"reference-count":43,"publisher":"Emerald","issue":"2","license":[{"start":{"date-parts":[[2008,6,13]],"date-time":"2008-06-13T00:00:00Z","timestamp":1213315200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008,6,13]]},"abstract":"<jats:sec><jats:title content-type=\"abstract-heading\">Purpose<\/jats:title><jats:p>Image classification or more specifically, annotating images with keywords is one of the important steps during image database indexing. However, the problem with current research in terms of image retrieval is more concentrated on how conceptual categories can be well represented by extracted, low level features for an effective classification. Consequently, image features representation including segmentation and low\u2010level feature extraction schemes must be genuinely effective to facilitate the process of classification. The purpose of this paper is to examine the effect on annotation effectiveness of using different (local) feature representation methods to map into conceptual categories.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-heading\">Design\/methodology\/approach<\/jats:title><jats:p>This paper compares tiling (five and nine tiles) and regioning (five and nine regions) segmentation schemes and the extraction of combinations of color, texture, and edge features in terms of the effectiveness of a particular benchmark, automatic image annotation set up. Differences between effectiveness on concrete or abstract conceptual categories or keywords are further investigated, and progress towards establishing a particular benchmark approach is also reported.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-heading\">Findings<\/jats:title><jats:p>In the context of local feature representation, the paper concludes that the combined color and texture features are the best to use for the five tiling and regioning schemes, and this evidence would form a good benchmark for future studies. Another interesting finding (but perhaps not surprising) is that when the number of concrete and abstract keywords increases or it is large (e.g. 100), abstract keywords are more difficult to assign correctly than the concrete ones.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-heading\">Research limitations\/implications<\/jats:title><jats:p>Future work could consider: conduct user\u2010centered evaluation instead of evaluation only by some chosen ground truth dataset, such as Corel, since this might impact effectiveness results; use of different numbers of categories for scalability analysis of image annotation as well as larger numbers of training and testing examples; use of Principle Component Analysis or Independent Component Analysis, or indeed machine learning techniques for low\u2010level feature selection; use of other segmentation schemes, especially more complex tiling schemes and other regioning schemes; use of different datasets, use of other low\u2010level features and\/or combination of them; use of other machine learning techniques.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-heading\">Originality\/value<\/jats:title><jats:p>This paper is a good start for analyzing the mapping between some feature representation methods and various conceptual categories for future image annotation research.<\/jats:p><\/jats:sec>","DOI":"10.1108\/07378830810880351","type":"journal-article","created":{"date-parts":[[2008,6,21]],"date-time":"2008-06-21T07:04:32Z","timestamp":1214031872000},"page":"255-273","source":"Crossref","is-referenced-by-count":0,"title":["Sensitivity analysis of mapping local image features into conceptual categories"],"prefix":"10.1108","volume":"26","author":[{"given":"Chih\u2010Fong","family":"Tsai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David C.","family":"Yen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"140","reference":[{"doi-asserted-by":"crossref","unstructured":"Barnard, K., Duygulu, P., Guru, R., Gabbur, P. and Forsyth, D. (2003a), \u201cThe effects of segmentation and feature choice in a translation model of object recognition\u201d, Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, Madison, Wisconsin, June 16\u201022, pp. 675\u201082.","key":"key2022021019564538900_b1","DOI":"10.1109\/CVPR.2003.1211532"},{"unstructured":"Barnard, K., Duygulu, P., Forsyth, D., deFreitas, N., Blei, D. and Jordan, M.I. (2003b), \u201cMatching words and pictures\u201d, Journal of Machine Learning Research, Vol. 3, pp. 1107\u201035.","key":"key2022021019564538900_b2"},{"unstructured":"Blei, D. and Jordan, M.I. (2003), \u201cModeling annotated data\u201d, Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval, Toronto, Canada, July 28\u2010August 1, pp. 127\u201037.","key":"key2022021019564538900_b3"},{"doi-asserted-by":"crossref","unstructured":"Borgman, C.L. (2001), \u201cWhere is the librarian in the digital library?\u201d, Communications of the ACM, Vol. 44 No. 5, pp. 66\u20107.","key":"key2022021019564538900_b4","DOI":"10.1145\/374308.374344"},{"doi-asserted-by":"crossref","unstructured":"Boutell, M., Luo, J., Shen, X. and Brown, C.M. (2004), \u201cLearning multi\u2010label scene classification\u201d, Pattern Recognition, Vol. 37 No. 9, pp. 1757\u201071.","key":"key2022021019564538900_b5","DOI":"10.1016\/j.patcog.2004.03.009"},{"doi-asserted-by":"crossref","unstructured":"Canny, J. (1986), \u201cA computational approach to edge detection\u201d, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 8 No. 6, pp. 679\u201098.","key":"key2022021019564538900_b6","DOI":"10.1109\/TPAMI.1986.4767851"},{"doi-asserted-by":"crossref","unstructured":"Carson, C., Belongie, S., Greenspan, H. and Malik, J. (2002), \u201cBlobworld: image segmentation using expectation\u2010maximization and its application to image querying\u201d, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24 No. 8, pp. 1026\u201038.","key":"key2022021019564538900_b7","DOI":"10.1109\/TPAMI.2002.1023800"},{"doi-asserted-by":"crossref","unstructured":"Chapelle, O., Haffner, P. and Vapnik, V.N. (1999), \u201cSupport vector machines for histogram\u2010based image classification\u201d, IEEE Transactions on Neural Networks, Vol. 10 No. 5, pp. 1055\u201064.","key":"key2022021019564538900_b8","DOI":"10.1109\/72.788646"},{"doi-asserted-by":"crossref","unstructured":"Chang, E., Kingshy, G., Sychay, G. and Wu, G. (2003), \u201cCBSA: content\u2010based soft annotation for multimodal image retrieval using Bayes point machines\u201d, IEEE Transactions on Circuits and Systems for Video Technology, Vol. 13 No. 1, pp. 26\u201038.","key":"key2022021019564538900_b9","DOI":"10.1109\/TCSVT.2002.808079"},{"doi-asserted-by":"crossref","unstructured":"Enser, P.G.B. (2000), \u201cVisual image retrieval: seeking the alliance of concept\u2010based and content\u2010based paradigms\u201d, Journal of Information Science, Vol. 26 No. 4, pp. 199\u2010210.","key":"key2022021019564538900_b10","DOI":"10.1177\/016555150002600401"},{"doi-asserted-by":"crossref","unstructured":"Fan, J., Gao, Y., Luo, H. and Xu, G. (2004), \u201cAutomatic image annotation by using concept\u2010sensitive salient objects for image content representation\u201d, Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval, Sheffield, UK, July 25\u201029, pp. 361\u20108.","key":"key2022021019564538900_b11","DOI":"10.1145\/1008992.1009055"},{"unstructured":"Feng, H.M. and Chua, T.\u2010S. (2004), \u201cA learning\u2010based approach for annotating large on\u2010line image collection\u201d, Proceedings of the International Conference on Multimedia Modeling, Brisbane, Australia, January 5\u20107, pp. 249\u201056.","key":"key2022021019564538900_b12"},{"unstructured":"Givers, T. and Smeulders, A.W.M. (1996), \u201cA comparative study of several color models for color image invariant retrieval\u201d, Proceedings of the First International Workshop on Image Databases and Multi Media search, Amsterdam, The Netherlands, August 22\u201023, pp. 17\u201026.","key":"key2022021019564538900_b13"},{"doi-asserted-by":"crossref","unstructured":"Goh, K.\u2010S., Chang, E.Y. and Li, B. (2005), \u201cUsing one\u2010class and two\u2010class SVMs for multiclass image annotation\u201d, IEEE Transactions on Knowledge and Data Engineering, Vol. 17 No. 10, pp. 1333\u201046.","key":"key2022021019564538900_b14","DOI":"10.1109\/TKDE.2005.170"},{"doi-asserted-by":"crossref","unstructured":"Iqbal, Q. and Aggarwal, J.K. (2002), \u201cRetrieval by classification of images containing large manmade objects using perceptual grouping\u201d, Pattern Recognition, Vol. 35 No. 7, pp. 1463\u201079.","key":"key2022021019564538900_b15","DOI":"10.1016\/S0031-3203(01)00139-X"},{"doi-asserted-by":"crossref","unstructured":"Jeon, J., Lavrenko, V. and Manmatha, R. (2003), \u201cAutomatic image annotation and retrieval using cross\u2010media relevance models\u201d, Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval, Toronto, Canada, July 28\u2010August 1, pp. 119\u201026.","key":"key2022021019564538900_b16","DOI":"10.1145\/860435.860459"},{"doi-asserted-by":"crossref","unstructured":"Ko, B., Lee, H.\u2010S. and Byun, H. (2000), \u201cImage retrieval using flexible image subblocks\u201d, Proceedings of the ACM Symposium on Applied Computing, Como, Italy, March 19\u201021, pp. 574\u20108.","key":"key2022021019564538900_b17","DOI":"10.1145\/338407.338502"},{"unstructured":"Li, R. and Leow, W.K. (2003), \u201cFrom region features to semantic labels: a probabilistic approach\u201d, Proceedings of the International Conference on Multimedia Modeling, Taipei, Taiwan, January 7\u201010, pp. 402\u201020.","key":"key2022021019564538900_b18"},{"doi-asserted-by":"crossref","unstructured":"Li, B., Goh, K. and Chang, E.Y. (2003), \u201cConfidence\u2010based dynamic ensemble for image annotation and semantics discovery\u201d, Proceedings of the ACM International Conference on Multimedia, Berkeley, California, November 2\u20108, pp. 528\u201038.","key":"key2022021019564538900_b19","DOI":"10.1145\/957013.957051"},{"doi-asserted-by":"crossref","unstructured":"Long, F., Zhang, H.J. and Feng, D.D. (2003), \u201cFundamentals of content\u2010based image retrieval\u201d, in Feng, D.D. and Zhang, H. (Eds), Multimedia Information Retrieval and Management: Technological Fundamentals and Applications, Springer\u2010Verlag, Berlin.","key":"key2022021019564538900_b20","DOI":"10.1007\/978-3-662-05300-3_1"},{"unstructured":"Ma, W.\u2010Y. and Zhang, H.J. (1999), \u201cContent\u2010based image indexing and retrieval\u201d, in Furht, B. (Ed.), Handbook of Multimedia Computing, CRC Press, Boca Raton, FL.","key":"key2022021019564538900_b21"},{"doi-asserted-by":"crossref","unstructured":"Manjunath, B.S. and Ma, W.Y. (1996), \u201cTexture features for browsing and retrieval of large image data\u201d, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 18 No. 8, pp. 837\u201042.","key":"key2022021019564538900_b22","DOI":"10.1109\/34.531803"},{"doi-asserted-by":"crossref","unstructured":"Mehtre, B.M., Kankanhalli, M.S. and Lee, W.F. (1997), \u201cShape measures for content based image retrieval: a comparison\u201d, Information Processing & Management, Vol. 33 No. 3, pp. 319\u201037.","key":"key2022021019564538900_b23","DOI":"10.1016\/S0306-4573(96)00069-6"},{"unstructured":"Mojsilovic, A. and Rogowitz, B. (2001), \u201cCapturing image semantics with low\u2010level descriptors\u201d, Proceedings of the IEEE International Conference on Image Processing, Thessaloniki, Greece, October 7\u201010, pp. 18\u201021.","key":"key2022021019564538900_b24"},{"doi-asserted-by":"crossref","unstructured":"Park, D.K., Jeon, Y.S. and Won, C.S. (2000), \u201cEfficient use of local edge histogram descriptor\u201d, Proceedings of the ACM Multimedia Workshop, Los Angeles, CA, November 4, pp. 51\u20104.","key":"key2022021019564538900_b26","DOI":"10.1145\/357744.357758"},{"doi-asserted-by":"crossref","unstructured":"Pichler, O., Teuner, A. and Hosticka, B.J. (1996), \u201cA comparison of texture feature extraction using adaptive gabor filtering, pyramidal and tree structured wavelet transforms\u201d, Pattern Recognition, Vol. 29 No. 5, pp. 733\u201042.","key":"key2022021019564538900_b27","DOI":"10.1016\/0031-3203(95)00127-1"},{"doi-asserted-by":"crossref","unstructured":"Puzicha, J., Buhmann, J.M., Rubner, Y. and Tomasi, C. (1999), \u201cEmpirical evaluation of dissimilarity measures for color and texture\u201d, Proceedings of the International Conference on Computer Vision, Corfu, Greece, September 20\u201025, pp. 1165\u201072.","key":"key2022021019564538900_b28","DOI":"10.1109\/ICCV.1999.790412"},{"doi-asserted-by":"crossref","unstructured":"Qiu, G., Feng, X. and Fang, J. (2004), \u201cCompressing histogram representations for automatic colour photo categorization\u201d, Pattern Recognition, Vol. 37 No. 11, pp. 2177\u201093.","key":"key2022021019564538900_b29","DOI":"10.1016\/j.patcog.2004.03.006"},{"doi-asserted-by":"crossref","unstructured":"Randen, T. and Hus\u00f8y, J.H. (1999), \u201cFiltering for texture classification: a comparative study\u201d, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 21 No. 4, pp. 291\u2010310.","key":"key2022021019564538900_b30","DOI":"10.1109\/34.761261"},{"doi-asserted-by":"crossref","unstructured":"Rui, Y., Huang, T.S. and Chang, S.\u2010F. (1999), \u201cImage retrieval: current techniques, promising directions and open issues\u201d, Journal of Visual Communication and Image Representation, Vol. 10 No. 1, pp. 39\u201062.","key":"key2022021019564538900_b31","DOI":"10.1006\/jvci.1999.0413"},{"doi-asserted-by":"crossref","unstructured":"Shi, J. and Malik, J. (2000), \u201cNormalized cuts and image segmentation\u201d, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22 No. 8, pp. 888\u2010905.","key":"key2022021019564538900_b32","DOI":"10.1109\/34.868688"},{"doi-asserted-by":"crossref","unstructured":"Smeulders, A.W.M., Worring, M., Santini, S., Gupta, A. and Jain, R. (2000), \u201cContent\u2010based image retrieval at the end of the early years\u201d, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22 No. 12, pp. 1349\u201080.","key":"key2022021019564538900_b33","DOI":"10.1109\/34.895972"},{"doi-asserted-by":"crossref","unstructured":"Song, Y. and Zhang, A. (2003), \u201cAnalyzing scenery images by monotonic tree\u201d, ACM Multimedia Systems, Vol. 8 No. 6, pp. 495\u2010511.","key":"key2022021019564538900_b34","DOI":"10.1007\/s00530-002-0067-y"},{"doi-asserted-by":"crossref","unstructured":"Tsai, C.\u2010F. (2007), \u201cA review of image retrieval methods for digital cultural heritage resources\u201d, Online Information Review, Vol. 31 No. 2, pp. 185\u201098.","key":"key2022021019564538900_b35","DOI":"10.1108\/14684520710747220"},{"doi-asserted-by":"crossref","unstructured":"Tsai, C.\u2010F., McGarry, K. and Tait, J. (2006a), \u201cCLAIRE: a modular support vector image indexing and classification system\u201d, ACM Transactions on Information Systems, Vol. 24 No. 3, pp. 353\u201079.","key":"key2022021019564538900_b36","DOI":"10.1145\/1165774.1165777"},{"doi-asserted-by":"crossref","unstructured":"Tsai, C.\u2010F., McGarry, K. and Tait, J. (2006b), \u201cQualitative evaluation of automatic assignment of keywords to images\u201d, Information Processing & Management, Vol. 42 No. 1, pp. 136\u201054.","key":"key2022021019564538900_b37","DOI":"10.1016\/j.ipm.2004.11.001"},{"doi-asserted-by":"crossref","unstructured":"Vailaya, A., Figueiredo, M.A.T., Jain, A.K. and Zhang, H.\u2010J. (2001), \u201cImage classification for content\u2010based indexing\u201d, IEEE Transactions on Image Processing, Vol. 10 No. 1, pp. 117\u201030.","key":"key2022021019564538900_b38","DOI":"10.1109\/83.892448"},{"unstructured":"Vasconcelos, N. and Lippman, A. (2000), \u201cFeature representations for image retrieval: beyond the color histogram\u201d, Proceedings of the International Conference on Multimedia and Expo, New York City, USA, July 30\u2010August 2, Vol. 2, pp. 899\u2010902.","key":"key2022021019564538900_b39"},{"unstructured":"Weber, R., Schek, H.\u2010J. and Blott, S. (1998), \u201cA quantitative analysis and performance study for similarity\u2010search methods in high\u2010dimensional spaces\u201d, Proceedings of the International Conference on Very Large Data Bases, New York City, USA, August 24\u201027, pp. 194\u2010205.","key":"key2022021019564538900_b40"},{"doi-asserted-by":"crossref","unstructured":"Wong, W.\u2010T. and Hsu, S.\u2010H. (2006), \u201cApplication of SVM and ANN for image retrieval\u201d, European Journal of Operational Research, Vol. 173, pp. 938\u201050.","key":"key2022021019564538900_b41","DOI":"10.1016\/j.ejor.2005.08.002"},{"unstructured":"Zhao, R. and Grosky, W.I. (2000), \u201cFrom features to semantics: some preliminary results\u201d, Proceedings of the IEEE International Conference on Multimedia & Expo, New York City, New York, July 30\u2010August 2, pp. 679\u201082.","key":"key2022021019564538900_b42"},{"unstructured":"Zhou, X.S. and Huang, T.S. (2000), \u201cImage retrieval: feature primitives, feature representation, and relevance feedback\u201d, Proceedings of the IEEE CVPR Workshop on Content\u2010Based Access for Image and Video Libraries, Hilton Head, South Carolina, June 12, pp. 10\u201014.","key":"key2022021019564538900_b43"},{"unstructured":"Pagano, R.R. (2001), Understanding Statistics in the Behavioral Sciences, 6th ed., Wadsworth\/Thomson Learning, Belmont, CA.","key":"key2022021019564538900_frg25"}],"container-title":["Library Hi Tech"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.emeraldinsight.com\/doi\/full-xml\/10.1108\/07378830810880351","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/07378830810880351\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/07378830810880351\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T23:33:21Z","timestamp":1753400001000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/lht\/article\/26\/2\/255-273\/261428"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,6,13]]},"references-count":43,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2008,6,13]]}},"alternative-id":["10.1108\/07378830810880351"],"URL":"https:\/\/doi.org\/10.1108\/07378830810880351","relation":{},"ISSN":["0737-8831"],"issn-type":[{"type":"print","value":"0737-8831"}],"subject":[],"published":{"date-parts":[[2008,6,13]]}}}