کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
536006 | 870429 | 2011 | 11 صفحه PDF | دانلود رایگان |
![عکس صفحه اول مقاله: Offline handwritten Amharic word recognition Offline handwritten Amharic word recognition](/preview/png/536006.png)
This paper describes two approaches for Amharic word recognition in unconstrained handwritten text using HMMs. The first approach builds word models from concatenated features of constituent characters and in the second method HMMs of constituent characters are concatenated to form word model. In both cases, the features used for training and recognition are a set of primitive strokes and their spatial relationships. The recognition system does not require segmentation of characters but requires text line detection and extraction of structural features, which is done by making use of direction field tensor. The performance of the recognition system is tested by a dataset of unconstrained handwritten documents collected from various sources, and promising results are obtained.
Research highlights
► Two HMM-based models for Amharic word recognition in handwritten text are proposed.
► A set of primitive strokes and their spatial relationships are used as features.
► Feature-level concatenation performs better than HMM-level concatenation of characters.
Journal: Pattern Recognition Letters - Volume 32, Issue 8, 1 June 2011, Pages 1089–1099