Keyword Spotting from Historical Handwritten Manuscripts using CLBP and CRLBP

doi:10.23940/ijpe.24.02.p4.9198

Int J Performability Eng ›› 2024, Vol. 20 ›› Issue (2): 91-98.doi: 10.23940/ijpe.24.02.p4.9198

Previous Articles Next Articles

Keyword Spotting from Historical Handwritten Manuscripts using CLBP and CRLBP

Yousfi Douaa^a,*, Gattal Abdeljalil^b, and Djeddi Chawki^b

^aLaboratoire de Mathématiques, d’Informatique et des Systèmes (LAMIS), Echahid Cheikh Larbi Tebessi University, Tebessa, Algeria;
^bLaboratoire de Vision et d’Intelligence Artificielle (LAVIA), Echahid Cheikh Larbi Tebessi University, Tebessa, Algeria

Submitted on ; Revised on ; Accepted on
Contact: * E-mail address: douaa.yousfi@univ-tebessa.dz

Abstract

Abstract: Due to severe deterioration and writing style differences, keyword spotting from historical handwritten documents remains challenging. This paper uses query-by-example (QBE) and a segmentation-based technique to investigate keyword spotting in historical documents. To match the image of the query to those in a reference database, features extracted from word images by a set of textural features such as Local Directional Number Pattern (LDNP), Complete Local Binary Patterns (CLBP), and Completed Robust Local Binary Pattern (CRLBP) are employed. The process of classifying data involves minimizing a similarity criterion that is derived from the distance between two feature vectors. High performance is achieved by a series of evaluations utilizing various combinations of distance measurements, and these are compared with the approaches used in the ICFHR 2014 word spotting competition.

Key words: spotting, historical handwritten documents, textural features, LDNP, CLBP, CRLBP

Yousfi Douaa, Gattal Abdeljalil, and Djeddi Chawki. Keyword Spotting from Historical Handwritten Manuscripts using CLBP and CRLBP [J]. Int J Performability Eng, 2024, 20(2): 91-98.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

References

[1] Giotis A.P., Sfikas G., Gatos B., andNikou C.A Survey of Document Image Word Spotting Techniques.Pattern Recognition, 68, pp.310-332, 2017.
[2] Majumder S., Ghosh S., Malakar S., Sarkar R., andNasipuri M.A Voting-Based Technique for Word Spotting in Handwritten Document Images. Multimedia Tools and Applications, vol. 80, pp. 12411-12434, 2021.
[3] Retsinas G., Louloudis G., Stamatopoulos N., andGatos B.Efficient Learning-Free Keyword Spotting. IEEE transactions on pattern analysis and machine intelligence, vol. 41, no. 7, pp. 1587-1600, 2018.
[4] Rothacker, L. and Fink, G.A.Segmentation-Free Query-by-String Word Spotting with Bag-of-Features HMMs. In2015 13th International conference on document analysis and recognition (ICDAR), IEEE, pp. 661-665, 2015.
[5] Malakar S., Ghosh M., Sarkar R., andNasipuri M.Development of a Two-Stage Segmentation-Based Word Searching Method for Handwritten Document Images. Journal of Intelligent Systems, vol. 29, no. 1, pp. 719-735, 2018.
[6] Almazán J., Gordo A., Fornés A., andValveny E.Segmentation-Free Word Spotting with Exemplar SVMs. Pattern Recognition, vol. 47, no. 12, pp. 3967-3978, 2014.
[7] Kovalchuk A., Wolf L., andDershowitz N.A Simple and Fast Word Spotting Method. In2014 14th international conference on frontiers in handwriting recognition, IEEE, pp. 3-8, 2014.
[8] Yousfi D., Gattal A., Djeddi C., Siddiqi I., andBensefia A.Keyword Spotting in Modern Handwritten Documents using oBIFs. In Mediterranean Conference on Pattern Recognition and Artificial Intelligence, Cham: Springer International Publishing, pp. 240-250, 2021.
[9] Rothacker L., Sudholt S., Rusakov E., Kasperidus M., andFink G.A.Word Hypotheses for Segmentation-Free Word Spotting in Historic Document Images. In 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), IEEE, vol. 1, pp. 1174-1179, 2017.
[10] Kundu S., Malakar S., Geem Z.W., Moon Y.Y., Singh P.K., andSarkar R.Hough Transform-Based Angular Features for Learning-Free Handwritten Keyword Spotting. Sensors, vol. 21, no. 14, pp. 4648, 2021.
[11] Pratikakis I., Zagoris K., Gatos B., Louloudis G., andStamatopoulos N. ICFHR2014 Competition on Handwritten Keyword Spotting (H-KWS 2014). In2014 14th International Conference on Frontiers in Handwriting Recognition, IEEE, pp. 814-819, 2014.
[12] Rothfeder J.L., Feng S., andRath T.M. using Corner Feature Correspondences to Rank Word Images by Similarity.In 2003 Conference on Computer Vision and Pattern Recognition Workshop, IEEE, vol. 3, pp. 30-30, 2003.
[13] Daraee F., Mozaffari S., andRazavi S.M.Handwritten Keyword Spotting using Deep Neural Networks and Certainty Prediction. Computers & Electrical Engineering, vol. 92, pp. 107111, 2021.
[14] Serdouk Y., Eglin V., Bres S., andPardoen M.KeyWord Spotting using Siamese Triplet Deep Neural Networks. In2019 International Conference on Document Analysis and Recognition (ICDAR), IEEE, pp. 1157-1162, 2019.
[15] Stauffer M., Fischer A., andRiesen K.Keyword Spotting in Historical Handwritten Documents Based on Graph Matching. Pattern Recognition, vol. 81, pp. 240-253, 2018.
[16] Rivera A.R., Castillo J.R., andChae O.O.Local Directional Number Pattern for Face Analysis: Face and Expression Recognition. IEEE transactions on image processing, vol. 22, no. 5, pp. 1740-1752, 2012.
[17] Guo Z., Zhang L., andZhang D.A Completed Modeling of Local Binary Pattern Operator for Texture Classification. IEEE transactions on image processing, vol. 19, no. 6, pp. 1657-1663, 2010.
[18] Zhao Y., Jia W., Hu R.X., andMin H.Completed Robust Local Binary Pattern for Texture Classification. Neurocomputing, vol. 106, pp. 68-76, 2013.
[19] Danielsson P.E.Euclidean Distance Mapping. Computer Graphics and image processing, vol. 14, no. 3, pp. 227-248, 1980.
[20] Long D.G.The Manuscripts of Jeremy Bentham a Chronological Index to the Collection in the Library of University College, London: Based on the Catalogue by A. Taylor Milne, 1981.
[21] Gatos B., Stamatopoulos N., andLouloudis G.ICDAR2009 Handwriting Segmentation Contest. International Journal on Document Analysis and Recognition (IJDAR), vol. 14, pp. 25-33, 2011.

Keyword Spotting from Historical Handwritten Manuscripts using CLBP and CRLBP

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 0

Recommended 0