Name
Abstract | ||
|---|---|---|
Hidden Markov Models (HMMs) are now widely used in off-line handwriting recognition and, in particular, in Arabic handwritten word recognition. In contrast to the conventional approach, based on Gaussian mixture HMMs, we have recently proposed to directly fed columns of raw, binary pixels into Bernoulli mixture HMMs. In this work, column bit vectors are extended by means of a sliding window of adequate width to better capture image context at each horizontal position of the word image. Using these windowed Bernoulli mixture HMMs, very good results are reported on the well-known IfN/ENIT database of Arabic handwritten Tunisian town names. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1109/ICFHR.2010.88 | Frontiers in Handwriting Recognition |
Keywords | Field | DocType |
hidden markov models,windowed bernoulli mixture hmms,arabic handwritten tunisian town,gaussian mixture hmms,arabic handwritten word recognition,word image,bernoulli mixture hmms,enit database,better capture image context,off-line handwriting recognition,hidden markov model,handwriting recognition,arabic,sliding window,hmm,databases,prototypes,image segmentation,pixel,speech recognition | Sliding window protocol,Pattern recognition,Computer science,Word recognition,Handwriting recognition,Image segmentation,Speech recognition,Artificial intelligence,Pixel,Hidden Markov model,Bernoulli's principle,Binary number | Conference |
ISBN | Citations | PageRank |
978-1-4244-8353-2 | 9 | 0.69 |
References | Authors | |
4 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Adria Gimenez | 1 | 30 | 4.16 |
| Ihab Khoury | 2 | 21 | 1.95 |
| alfons juan | 3 | 572 | 61.45 |