EM Training of Hidden Markov Models for Shape Recognition Using Cyclic Strings
Shape descriptions and the corresponding matching techniques must be robust to noise and invariant to transformations for their use in recognition tasks. Most transformations are relatively easy to handle when contours are represented by strings. However, starting point invariance is difficult to achieve. One interesting possibility is the use of cyclic strings, which are strings with no starting and final points. Here we present the use of Hidden Markov Models for modelling cyclic strings and their training using Expectation Maximization. Experimental results show that our proposal outperforms other methods in the literature.
Keywordshidden markov models cyclic strings shape recognition
Unable to display preview. Download preview PDF.
- 2.Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77(2) (1989)Google Scholar
- 4.Arica, N., Yarman-Vural, F.: A shape descriptor based on circular hidden Markov model. In: ICPR, vol. I, pp. 924–927 (2000)Google Scholar
- 6.Bicego, Murino, Figueiredo: Similarity-based classification of sequences using hidden Markov models. Pattern Recognition 37, 2281–2291 (2004)Google Scholar
- 12.Latecki, L., Lakämper, R., Eckhardt, U.: Shape descriptors for non-rigid shapes with a single closed contour. In: CVPR, June 13-15, pp. 424–429. IEEE, Los Alamitos (2000)Google Scholar
- 13.Sharvit, D., Chan, J., Tek, H., Kimia, B.B.: Symmetry-based indexing of image databases. In: Workshop on Content-Based Access of Image and Video Libraries, pp. 56–62 (1998)Google Scholar