Scene Text Extraction in HSI Color Space using K-means Algorithm and Modified Cylindrical Distance

• Autorzy: Saric M. , Dujmic H. , Russo M.

Warianty tytułu

PL

Ekstrakcja tekstu z obrazu w przestrzeni kolorów typu HSI z wykorzystaniem klasteryzacji k-means i zmodyfikowanych współrzędnych cylindrycznych

• Języki publikacji: EN

Abstrakty

EN

Text extraction, that is segmentation of characters from background, is especially important step that greatly determines final recognition performance. Particular focus is put on this task for scene text which is characterized with wide set of degradations like complex backgrounds, uneven illumination, viewing angle etc. In this paper we introduce text extraction method based on k-means clustering with modified cylindrical distance in HSI color space. Performance of this distance is analyzed depending on different degrees of chroma reliability. For purpose of result comparison, K-means text extraction is also performed with cylindrical distance in HSI color space and Euclidean distance in RGB color space. Complementarity of tested distances is also analyzed showing possible direction for further performance improvement.

PL

W artykule opisano metodę ekstrakcji tekstu z obrazu w oparciu o klasteryzację k-means oraz przestrzeń kolorów typu HSI we współrzędnych cylindrycznych. Poprawność dystansowania została poddana analizie w zależności od różnego stopnia rzetelności kolorów. Wyniki działania algorytmu ekstrakcji tekstu k-means zostały porównane dla współrzędnych cylindrycznych w przestrzeni kolorów typu HSI oraz współrzędnych Euklidesowego w przestrzeni kolorów typu RGB.

Słowa kluczowe

EN

K-mean; text extraction; cylindrical distance

PL

ekstrakcja tekstów; klasteryzacja; współrzędne cylindryczne

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2013
• Tom: R. 89, nr 5
• Strony: 117--121
• Opis fizyczny: Bibliogr. 23 poz., rys., tab., wykr.

Twórcy

autor

Saric M.

• University of Split

autor

Dujmic H.

• University of Split

autor

Russo M.

• University of Split

Bibliografia

• [1] Tang, Y.Y., Lee, S.W., Suen, C.Y., Automatic document processing: a survey, Pattern Recognition, vol. 29, no. 12, p. 1931–1952.
• [2] Iwanowski, M., Automatic car number plate detection using morphological image processing, Przeglad Elektrotechniczny (Electrical Review), vol. 81, pp. 58-61, 2005.
• [3] Watanabe, Y., Sono, K., Yokomizo, K., Okada, Y., Translation camera on mobile phone, in Proceedings of International Conference on Multimedia and Expo, 2003, pp. 177-180.
• [4] Saric, M., Dujmic, H., Papic,V., Rozic, N., Radic, J., Player Number Recognition in Soccer Video using Internal Contours and Temporal Redundancy, in Proceedings of the 10th WSEAS International Conference on Automation & Information (ICAI'09) 2009, pp. 175-180.
• [5] Jung, K., Kim, K., Jain, A., Text Information Extraction in Images and Video: A Survey, Pattern Recognition, vol. 37, no. 5, pp. 977-997, 2004.
• [6] Razzak, M.I., Mirza, A.A., Ghost Character Recognition Theory and Arabic Script Based Languages Character Recognition, Przeglad Elektrotechniczny (Electrical Review), vol. 87, no. 11, pp. 234-238, 2011.
• [7] Brodic, D., Methodology for the evaluation of the algorithms for text segmentation based on errors type, Przeglad Elektrotechniczny (Electrical Review), vol. 88, no. 1b, pp. 259-263, 2012.
• [8] Mancas-Thillou, C., Gosselin, B., Natural Scene Text Understanding, Vision Systems: Segmentation and Pattern Recognition, Vienna, Austria: I-Tech Education and Publishing, 2007, ch. 16, pp. 307-332.
• [9] Gatos, B., Pratikakis, I.,Kepene, K., Perantonis, S. J., Text detection in indoor/outdoor scene images, Proc. First Workshop of Camera-based Document Analysis and Recognition, 2005, p. 127–132.
• [10] Lienhart, R., Effelsberg, W., Automatic text segmentation and text recognition for video indexing, Technical Report, University of Mannheim, 1998.
• [11] Karatzas, D., Antonacopoulos, A., Colour text segmentation in web images based on human perception, Image and Vision Computing, vol. 25, no. 5, pp. 564-577, 2007.
• [12] Mancas-Thillou, C., Gosselin, B., Color text extraction with selective metric-based clustering, Computer Vision and Image Understanding, vol. 107, no. 1-2, pp. 97-107, 2007.
• [13] Garcia. C., Apostolidis, X., Text detection and segmentation in complex color images, in Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing, 2000, p. 2326–2330.
• [14] Mancas-Thillou, C., Natural Scene Text Understanding, PhD Thesis, Faculté Polytechnique de Mons, 2006.
• [15] Saric, M., Dujmic, H., Rozic, N., Including of continuous model for discriminating chromatic and achromatic pixels in cylindrical distance, Automatika, vol. 51, no. 3, pp. 241-254, 2010.
• [16] Tseng, D.C., Chang, C.M., Color segmentation using perceptual attributes, in Proc. of the 11th Internat. Conf. on Pattern Recognition, 1992, pp. 228-231.
• [17] Plataniotis, K.N., Venetsanopoulos, A.N., Color image processing and applications, Springer-Verlag New York, 2000.
• [18] Vadivel, A., Sural, S., Majumdar, A.K., Human color perception in the HSV space and its application in histogram generation for image retrieval, in Proc. SPIE, Color Imaging X: Processing, Hardcopy, and Applications, 2005, p. 598–609.
• [19] Romani, S., Sobrevilla, P., Montseny, E., On the reliability degree of hue and saturation values of a pixel for color image classification, in Proceedings of IEEE Internat. Conf. on Fuzzy Systems, 2005, pp. 306-311.
• [20] Aptoula. E., Lefévre, S., On the morphological processing of hue, Image and Vision Computing, vol. 27, no. 9, 2009.
• [21] Shahab, A., Shafait, F., Dengel, A., ICDAR 2011 Robust Reading Competition Challenge 2: Reading Text in Scene Images, in Proc. 11th International Conference of Document Analysis and Recognition, 2011, pp. 1491-1496.¸
• [22] Perez, F., Koch, C., Toward color image segmentation in analog VLSI: algorithm and hardware, International Journal of Computer Vision, vol. 12, no. 1, pp. 17-42, 1994.
• [23] S. Romani, P. Sobrevilla, and Montseny.E., "On the reliability degree of hue and saturation values of a pixel for color image classification," in Proceedings of IEEE Internat. Conf. on Fuzzy Systems, 2005, pp. 306-311.