Name
Abstract | ||
|---|---|---|
Writer independent handwriting recognition systems are limited in their accuracy, primarily due the large variations in writing styles of most characters. Samples from a single character class can be thought of as emanating from multiple sources, corresponding to each writing style. This also makes the inter-class boundaries, complex and disconnected in the feature space. Multiple kernel methods have emerged as a potential framework to model such decision boundaries effectively, which can be coupled with maximal margin learning algorithms. We show that formulating the problem in the above framework improves the recognition accuracy. We also propose a mechanism to adapt the resulting classifier by modifying the weights of the support vectors as well as that of the individual kernels. Experimental results are presented on a data set of 16,000 alphabets collected from 470 writers using a digitizing tablet. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/ICDAR.2009.212 | ICDAR-1 |
Keywords | Field | DocType |
handwritten character recognition,image recognition,learning (artificial intelligence),optimisation,feature space,handwritten character recognizer,inter-class boundary,maximal margin learning algorithm,multiple kernel method,support vector,Multiple Kernel Learning,Online Handwriting,Writer Adaptation | Graphics tablet,Feature vector,Pattern recognition,Computer science,Multiple kernel learning,Support vector machine,Handwriting recognition,Speech recognition,Artificial intelligence,Classifier (linguistics),Kernel method,Hidden Markov model | Conference |
Citations | PageRank | References |
4 | 0.41 | 10 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Naveen Chandra Tewari | 1 | 4 | 0.41 |
| Anoop M. Namboodiri | 2 | 255 | 26.36 |