Hermite and Gabor transforms for noise reduction and handwriting classification in ancient manuscripts
Tóm tắt
In this paper, we propose a biologically inspired, global and segmentation free methodology for manuscript noise reduction and classification. Our method consists of developing well-adapted tools for writing enhancement, background noise, text and drawing separation and handwritten patterns characterization with orientation features. We have used here analysis of handwritten images in the spectral domain by frequency decompositions (Hermite transforms) and Gabor filtering for selective text information extraction. We have tested our approach of writing classification on ancient manuscripts corpus, mainly composed of 18th century authors’ documents. The current results are very promising: they show that our biologically inspired methodology can be efficiently used for handwriting analysis without any a priori grapheme segmentation.
Tài liệu tham khảo
Bahlmann C., Burkhardt H. (2004). The writer independent online handwriting recognition system flog on hand and cluster generative statistical dynamic time warping. IEEE Trans. PAMI 26(3): 299–310
Bensefia A., Paquet T., Heutte L. (2005). Handwritten document analysis for automatic writer recognition. Electron. Lett. Comput. Vision Image Anal. 5(2): 72–86
Bres, S.: Contributions à la quantification des critères de transparence et d’anisotropie par une approche globale. Ph.D. Thesis, Lyon (1994)
Bulacu, M., Schomaker, L.: Writer style from oriented edge fragments. In: Proceedings of the CAIP Computer Analysis of Images and Patterns, Groningen, The Netherlands, pp. 460–469 (2003)
Catalin, I.T., Zhang, B., Srihari, S.N.: Discriminatory power of handwritten words for writer recognition. In: Proceedings of the International Conference on pattern Recognition, IEEE Computer Society, Cambridge, UK, pp. 638–643 (2004)
Cha, S.H., Srihari, S.: Multiple feature integration for writer verification. In: Proceedings of the 7th International Workshop on Frontiers in Handwriting Recognition, IWFHR VII, Amsterdam, pp. 333–342 (2000)
Chetverikov, D., Liang, J., Komuves, J., Haralick, R.M.: Zone classification using texture features. In: Proceedings of the 13th International Conference on Pattern Recognition, vol. 3, pp. 676–680 (1996)
Eglin, V., Volpilhac-Auger, C.: Caractérisation multi-échelle des tracés manuscrits en vue de la catégorisation de scripteurs. In: Proceedings of the CIFED, La Rochelle, France, pp. 106–114 (2004)
Franke K., Koppen M. (2001). A computer-based system to support forensic studies on handwritten documents. Int. J. Doc. Anal. Recognit. 3: 218–231
Fu, A.W.-C., Keogh, E., Yung, L., Lau, H., Ratanamahatana, C.A.: Scaling and time warping in time series querying. In: Proceedings of the 31st VLDB Conferecne (2005)
Gallica: digital library of the BNF: http://gallica.bnf.fr
Jain A.K., Bhattacharjee S. (1992). Text segmentation using Gabor filters for automatic document processing. Mach. Vision Appl. 5(3): 169–184
Keogh, J.: Exact indexing of Dynamic Time Warping. In: VLDB, pp. 406–417 (2002)
Kuckuck, W.: Writer recognition by spectra analysis. In: Proceedings of the International Conference in Security through Science Engineering, pp. 1–3 (1980)
Lebourgeois, F., Trinh, E., Allier, B., Eglin, V., Emptoz, H.: Document image analysis solutions for digital libraries. In: Proceedings of the DIAL, Palo Alto, pp. 20–32 (2004)
Lebourgeois F., Trinh E., Emptoz H. (2003). Compression and accessibility with the images of digitized documents—application to the Debora project, numerical document. Flight 7(3–4): 103–127
Leedham, G., Varma, S., Patnkar, A., Govindaraju, V.: Separating text and background in degraded document images- a comparison of global thresholding techniques for multi-stage thresholding. In: Proceedings of the 8th International Workshop on Frontiers in Handwriting Recognition, Niagara-on-the-Lake, Canada, pp. 244–249 (2002)
Martens J.-B. (1990). The Hermite transform—theory. IEEE Trans. Acoust. Speech Signal Processing 38(9): 1595–1606
Marti, U.V., Messerli, R., Bunke, H.: Writer identification using text line based features. In: Proceedings of the ICDAR’01, Seattle (WA, USA), pp. 101–105 (2002)
Nishida, H., Suzuki, T.: A multiscale approach to restoring scanned color document images with show-through effects. In: Proceedings of the 7th International Conference on Document Analysis and Recognition, pp. 584–88 (2003)
Nosary, A., Paquet, T., Heutte, L.: Reconnaissance de textes manuscrits par adaptation au scripteur, CIFED’, pp. 365–374 (2002)
Ratanamahatana, C.A., Keogh, E.: Everything you know about dynamic time warping is wrong. In: Proceedings of the 3rd Workshop on Mining Temporal and Sequential Data, in Conjunction with the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2004), Seattle (WA, USA) (2004)
Rath T., Manmatha R. (2003). Word image matching using dynamic time warping. In: Proceedings of the CVPR, vol. 2: 521–527
Rivero-Moreno, C.J., Bres, S.: Conditions of similarity between Hermite and Gabor filters as models of the human visual system. In: Petkov, N., Westenberg, M.A. (eds.) Computer Analysis of Images and Patterns. Lectures Notes Computer Science, (CAIP 2003) Groningen, The Netherlands, Vol. 2756, 762–769 (2003)
Said H.E.S., Peake G.S., Tan T.N., Baker K.D.: Writer identification from non-uniformly skewed handwriting Images. In: Proceedings of the British Machine Vision Conference, pp. 478–489 (1998)
Sharma S. (1998). Show-through cancellation in scans of duplex printed documents. IEEE Trans. Image Process 10(5): 736–754
Srihari, S.N., Beal, M.J., Bandi, K., Shah, V.: A statistical model for writer identification. In: Proceedings of the 8th International Conference on Document Analysis and Recognition, pp. 626–630 (2005)
Srihari S.N., Cha S.-H., Arora H., Lee S. (2002). Individuality of handwriting. J. Forensic Sci. 47(4): 1–17
Strouthopoulos C., Papamarkos N. (1998). Text Identification for document image analysis using a neural network. Image Vision Comput. 16: 879–896
Tan C.L., Cao R., Shen P. (2002). Restoration of archival documents using a wavelet technique. Proc. Pattern Anal. Mech. Intell. IEEE Trans. 4(10): 1399–1404
Tonazzini A., Vezzosi S., Bedini L. (2004). Analysis and recognition of highly degraded printed characters. Int. J. Doc. Anal. Recognit. 6: 236–247
Tonazzini A., Bedini L., Salerno E. (2004). Independant component analysis for document restoration. Int. J. Doc. Anal. Recognit. 7: 17–21
Volpilhac-Auger, C., Eglin, V.: La problématique des ouvrage manuscrit ancien: vers une authentification des écritures des secrétaires de Montesquieu, Journée sur la valorisation des documents et numérisation des collections, Ecole Normale Supérieure de Lyon, Lyon, le 7 mars (2002)
Weldon, T.P., Higgins, W.E.: Algorithm for designing multiple Gabor filters for segmenting multi-textured images. In: Proceedings of the International Conference on Image Processing, Chicago, IL, pp. 4–7 (1998)
Yang, F., Lishman, R.: Land cover change detection using Gabor filter texture. In: Proceedings of the 3rd International Workshop on Texture Analysis and Synthesis, pp. 1024–1029 (2003)
Yi, B.-K., Jagadish, H.V., Faloutsos, C.: Effcient retrieval of similar time sequences under time warping. In: Proceedings of the 14th International Conference on Data Engineering (1998)
Zois E.N., Anastassopoulos V. (2000). Morphological waveform coding for writer identification. Pattern Recognit. 33(3): 385–398