Abstract
To manipulate the layout analysis problem for complex or irregular document image, a Unified HMM-based Layout Analysis Framework is presented in this paper. Based on the multi-resolution wavelet analysis results of the document image, we use HMM method in both inner-scale image model and trans-scale context model to classify the pixel region properties, such as text, picture or background. In each scale, a HMM direct segmentation method is used to get better inner-scale classification result. Then another HMM method is used to fuse the inner-scale result in each scale and then get better final segmentation result. The optimized algorithm uses a stop rule in the coarse to fine multi-scale segmentation process, so the speed is improved remarkably. Experiments prove the efficiency of proposed algorithm.
Similar content being viewed by others
References
Pavlidis, T., Zhou, J., Page segmentation and classification, Computer Vision Graphics Image Processing, 1992, 54(6): 482–496.
Wong, K. Y., Casey, R. G., Wahl, F. M., Document analysis system, IBM Journal Res. Develop, 1982, 26(6): 647–656.
Nagy, G., Seth, S., Hierarchical representation of optically scanned documents, in 7th Proceedings of ICPR, vol. 1. Montreal, Canada, 1984, 347–349.
Fletcher, L. A., Kasturi, R. A., A robust algorithm for text string separation from mixed text/graphics images, IEEE Transactions on PAMI, 1988, 10(6): 910–918.
O’Gorman, L., The document spectrum for page layout analysis, IEEE Transactions on Pattern Analysis Machine Intelligence, 1993, 15: 1162–1173.
Kida, H., Document recognition system for office automation, in Proceedings 8th ICPR, 1986, 446–448.
Ha, J., Haralick, R. M., Phillips, I. T., Document page decomposition using bounding boxes of connected components of Black Pixels, Document Recognition II, Proceedings of the SPIE’95, San Jose, California, 1995, 140–151.
Ittner, D. J., Baird, H. S., Language-free layout analysis, in Proc. 2nd Int. Conf. Document Analysis Recog. (ICDAR), 1993, 336–340.
Pavlidis, T., Page segmentation by white streams, in Proc. 1st Int. Conf. Document Analysis and Recognition (ICDAR), 1991, 945–953.
Jain, A. K., Zhong, Y., Page segmentation using texture analysis, Pattern Recognition, 1996, 29(5): 743–770.
Chen, J.-L., Kundu, A., Unsupervised texture segmentation using multichannel decomposition and hidden Markov model, IEEE Trans. on Image Processing, 1995, 4(5): 603–619.
Sauvola, J., Pietikainen, M., Page segmentation and classification using fast feature extraction and connectivity analysis, in Proceedings of the 3rd ICDAR, Montreal, Canada, 1995, 1127–1131.
Jain, A., Bhattacharjee, S., Text segment using Gabor filters for automatic document processing, Machine Vision and Applications, 1992, 5(3): 169–184.
Etemad, K., Doermann, D., Chellappa, R., Multiscale segmentation of unstructured document pages using soft decision integration, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(1): 92–96.
Choi, H., Baraniuk, R., Multiscale document segmentation using wavelet domain hidden Markov models, in Proceedings of SPIE Document Recognition and Retrieval VII, Volumen 3967, San Jose, Califorina, 2000, 234–247.
Cheng, H., Bouman, C. A., Allebach, J. P., Multiscale document segmentation, in IS&T 50th Annual Conference, Cambridge, MA, May 18–23, 1997, 417–425.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Chen, M., Ding, X. & Wu, Y. Unified HMM-based layout analysis framework and algorithm. Sci China Ser F 46, 401–408 (2003). https://doi.org/10.1360/02yf0135
Received:
Issue Date:
DOI: https://doi.org/10.1360/02yf0135