{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:22:11Z","timestamp":1777576931022,"version":"3.51.4"},"reference-count":31,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2018,2,8]],"date-time":"2018-02-08T00:00:00Z","timestamp":1518048000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>In this paper, we improve the performance of the recently proposed Direct Query Classifier (dqc). The (dqc) is a classifier based retrieval method and in general, such methods have been shown to be superior to the OCR-based solutions for performing retrieval in many practical document image datasets. In (dqc), the classifiers are trained for a set of frequent queries and seamlessly extended for the rare and arbitrary queries. This extends the classifier based retrieval paradigm to an unlimited number of classes (words) present in a language. The (dqc) requires indexing cut-portions (n-grams) of the word image and dtw distance has been used for indexing. However, dtw is computationally slow and therefore limits the performance of the (dqc). We introduce query specific dtw distance, which enables effective computation of global principal alignments for novel queries. Since the proposed query specific dtw distance is a linear approximation of the dtw distance, it enhances the performance of the (dqc). Unlike previous approaches, the proposed query specific dtw distance uses both the class mean vectors and the query information for computing the global principal alignments for the query. Since the proposed method computes the global principal alignments using n-grams, it works well for both frequent and rare queries. We also use query expansion (qe) to further improve the performance of our query specific dtw. This also allows us to seamlessly adapt our solution to new fonts, styles and collections. We have demonstrated the utility of the proposed technique over 3 different datasets. The proposed query specific dtw performs well compared to the previous dtw approximations.<\/jats:p>","DOI":"10.3390\/jimaging4020037","type":"journal-article","created":{"date-parts":[[2018,2,9]],"date-time":"2018-02-09T12:46:27Z","timestamp":1518180387000},"page":"37","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Efficient Query Specific DTW Distance for Document Retrieval with Unlimited Vocabulary"],"prefix":"10.3390","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1092-8403","authenticated-orcid":false,"given":"Gattigorla","family":"Nagendar","sequence":"first","affiliation":[{"name":"Center for Visual Information Technology, IIIT Hyderabad, Hyderabad 500 032, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Viresh","family":"Ranjan","sequence":"additional","affiliation":[{"name":"CSE Department, Stony Brook University, Stony Brook, NY 11794, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaurav","family":"Harit","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, IIT Jodhpur, Jodhpur 342037, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.","family":"Jawahar","sequence":"additional","affiliation":[{"name":"Center for Visual Information Technology, IIIT Hyderabad, Hyderabad 500 032, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2018,2,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1109\/34.824820","article-title":"Twenty Years of Document Image Analysis in PAMI","volume":"22","author":"Nagy","year":"2008","journal-title":"PAMI"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Sivic, J., and Zisserman, A. (2003, January 13\u201316). Video Google: A Text Retrieval Approach to Object Matching in Videos. Proceedings of the Ninth IEEE International Conference on Computer Vision, Nice, France.","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1007\/s10032-006-0027-8","article-title":"Word spotting for historical documents","volume":"9","author":"Rath","year":"2007","journal-title":"IJDAR"},{"key":"ref_4","unstructured":"Zeki, Y.I., and Manmatha, R. (2012, January 27\u201329). An Efficient Framework for Searching Text in Noisy Document Images. Proceedings of the 2012 10th IAPR International Workshop on Document Analysis Systems (DAS), Gold Cost, QLD, Australia."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1007\/s10032-007-0042-4","article-title":"Keyword-guided word spotting in historical printed documents using synthetic data and user feedback","volume":"9","author":"Konidaris","year":"2007","journal-title":"IJDAR"},{"key":"ref_6","unstructured":"Basilios, G., Nikolaos, S., and Georgios, L. (2009, January 26\u201329). ICDAR 2009 Handwriting Segmentation Contest. Proceedings of the 10th International Conference on Document Analysis and Recognition, Barcelona, Spain."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Sankar, K.P., and Jawahar, C.V. (2007, January 17\u201322). Probabilistic Reverse Annotation for Large Scale Image Retrieval. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, USA.","DOI":"10.1109\/CVPR.2007.383169"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Almaz\u00e1n, J., Fern\u00e1ndez, D., Forn\u00e9s, A., Llad\u00f3s, J., and Valveny, E. (2012, January 18\u201320). A Coarse-to-Fine Approach for Handwritten Word Spotting in Large Scale Historical Documents Collection. Proceedings of the 2012 International Conference on Frontiers in Handwriting Recognition (ICFHR), Bari, Italy.","DOI":"10.1109\/ICFHR.2012.151"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1023\/A:1026543900054","article-title":"The Earth Mover\u2019s Distance As a Metric for Image Retrieval","volume":"40","author":"Yossi","year":"2000","journal-title":"IJCV"},{"key":"ref_10","unstructured":"David, S., and Kruskal, J.B. (1983). Time Warps, String Edits, and Macromolecules: The Theory and Practice of Sequence Comparison, Addison-Wesley."},{"key":"ref_11","unstructured":"Rath, T.M., and Manmatha, R. (2003, January 18\u201320). Word Image Matching Using Dynamic Time Warping. Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Madison, WI, USA."},{"key":"ref_12","unstructured":"Tomasz, M., Abhinav, G., and Efros, A.A. (2011, January 6\u201313). Ensemble of exemplar-SVMs for Object Detection and Beyond. Proceedings of the 2011 International Conference on Computer Vision, Barcelona, Spain."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Cao, H., and Govindaraju, V. (2007, January 23\u201326). Vector Model Based Indexing and Retrieval of Handwritten Medical Forms. Proceedings of the Ninth International Conference on Document Analysis and Recognition, Parana, Brazil.","DOI":"10.1109\/ICDAR.2007.4378681"},{"key":"ref_14","unstructured":"Rath, T.M., and Manmatha, R. (2003, January 6). Features for Word Spotting in Historical Manuscripts. Proceedings of the Seventh International Conference on Document Analysis and Recognition, Edinburgh, UK."},{"key":"ref_15","unstructured":"Balasubramanian, A., Million, M., and Jawahar, C.V. (2006, January 13\u201315). Retrieval from Document Image Collections. Proceedings of the 7th International Workshop, DAS 2006, Nelson, New Zealand."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Kovalchuk, A., Wolf, L., and Dershowitz, N. (2014, January 1\u20134). A Simple and Fast Word Spotting Method. Proceedings of the 2014 14th International Conference on Frontiers in Handwriting Recognition (ICFHR), Heraklion, Greece.","DOI":"10.1109\/ICFHR.2014.9"},{"key":"ref_17","unstructured":"Shai, S., Yoram, S., and Nathan, S. (2007, January 20\u201324). Pegasos: Primal Estimated sub-GrAdient Solver for SVM. Proceedings of the 24th International Conference on Machine Learning, Corvalis, OR, USA."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ranjan, V., Harit, G., and Jawahar, C.V. (2015, January 5\u20139). Document Retrieval with Unlimited Vocabulary. Proceedings of the 2015 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.","DOI":"10.1109\/WACV.2015.104"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Nagendar, G., and Jawahar, C.V. (2015, January 18\u201321). Fast Approximate Dynamic Warping Kernels. Proceedings of the Second ACM IKDD Conference on Data Sciences, Bangalore, India.","DOI":"10.1145\/2732587.2732592"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Nagendar, G., and Jawahar, C.V. (2015, January 23\u201326). Efficient word image retrieval using fast DTW distance. Proceedings of the 2015 13th International Conference on Document Analysis and Recognition (ICDAR), Tunis, Tunisia.","DOI":"10.1109\/ICDAR.2015.7333887"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Sudholt, S., and Fink, G.A. (2016, January 23\u201326). PHOCNet: A Deep Convolutional Neural Network for Word Spotting in Handwritten Documents. Proceedings of the 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), Shenzhen, China.","DOI":"10.1109\/ICFHR.2016.0060"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Krishnan, P., Dutta, K., and Jawahar, C.V. (2016, January 23\u201326). Deep Feature Embedding for Accurate Recognition and Retrieval of Handwritten Text. Proceedings of the 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), Shenzhen, China.","DOI":"10.1109\/ICFHR.2016.0062"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2552","DOI":"10.1109\/TPAMI.2014.2339814","article-title":"Word Spotting and Recognition with Embedded Attributes","volume":"36","author":"Jon","year":"2014","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Sfikas, G., Giotis, A.P., Louloudis, G., and Gatos, B. (2015, January 23\u201326). Using attributes for word spotting and recognition in polytonic greek documents. Proceedings of the 2015 13th International Conference on Document Analysis and Recognition (ICDAR), Tunis, Tunisia.","DOI":"10.1109\/ICDAR.2015.7333849"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3967","DOI":"10.1016\/j.patcog.2014.06.005","article-title":"Segmentation-free Word Spotting with Exemplar SVMs","volume":"47","author":"Gordo","year":"2014","journal-title":"Pattern Recognit."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Takami, M., Bell, P., and Ommer, P. (2014, January 24\u201326). Offline learning of prototypical negatives for efficient online Exemplar SVM. Proceedings of the 2014 IEEE Winter Conference on Applications of Computer Vision (WACV), Steamboat Springs, CO, USA.","DOI":"10.1109\/WACV.2014.6836075"},{"key":"ref_27","unstructured":"Gharbi, M., Malisiewicz, T., Paris, S., and Durand, F. (2012). A Gaussian Approximation of Feature Space for Fast Image Similarity, CSAIL Publications. MIT CSAIL Technical Report."},{"key":"ref_28","unstructured":"Meinard, M. (2007). Information Retrieval for Music and Motion, Springer."},{"key":"ref_29","unstructured":"Muja, M., and Lowe, D.G. (2009, January 5\u20138). Fast approximate nearest neighbours with automatic algorithm configuration. Proceedings of the 4th International Conference on Computer Vision Theory and Applications, Lisboa, Portugal."},{"key":"ref_30","unstructured":"Stan, S., and Philip, C. (2004, January 22). Fastdtw: Toward accurate dynamic time warping in linear time and space. Proceedings of the KDD Workshop on Mining Temporal and Sequential Data, Seattle, WA, USA."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"934","DOI":"10.1016\/j.patrec.2011.09.009","article-title":"Lexicon-free handwritten word spotting using character HMMs","volume":"33","author":"Fischer","year":"2012","journal-title":"Pattern Recognit. Lett."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/4\/2\/37\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T14:54:19Z","timestamp":1760194459000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/4\/2\/37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2,8]]},"references-count":31,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2018,2]]}},"alternative-id":["jimaging4020037"],"URL":"https:\/\/doi.org\/10.3390\/jimaging4020037","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,2,8]]}}}