Name
Abstract | ||
|---|---|---|
The detection of groups of parallel lines is important in applications such as form processing and text (handwriting) extraction from rule lined paper. These tasks can be very challenging in degraded documents where the lines are severely broken. In this paper, we propose a novel model-based method which incorporates high-level context to detect these lines. After preprocessing (such as skew correction and text filtering), we use trained Hidden Markov Models (HMM) to locate the optimal positions of all lines simultaneously on the horizontal or vertical projection profiles, based on the Viterbi decoding. The algorithm is trainable so it can be easily adapted to different application scenarios. The experiments conducted on known form processing and rule line detection show our method is robust, and achieves better results than other widely used line detection methods. |
Year | DOI | Venue |
|---|---|---|
2005 | 10.1109/TPAMI.2005.89 | IEEE Trans. Pattern Anal. Mach. Intell. |
Keywords | Field | DocType |
rule line detection,known form processing,hmm decoding,index terms- line detection,document image analysis.,form registration,form processing,better result,parallel line,line detection method,rule line,feature extraction,parallel-line detection algorithm,degraded document,form identification,hidden markov model,text extraction,hidden markov models,document image analysis,document image processing,viterbi decoding,novel model-based method,model-based method,indexing terms,image quality,text analysis,degradation,markov processes,viterbi decoder,viterbi algorithm,computer graphics,context modeling,pattern recognition,filtering,decoding,markov chains,documentation,artificial intelligence,algorithms,technical report | Markov process,Computer science,Artificial intelligence,Viterbi algorithm,Computer vision,Pattern recognition,Filter (signal processing),Algorithm,Feature extraction,Parallel,Viterbi decoder,Decoding methods,Hidden Markov model | Journal |
Volume | Issue | ISSN |
27 | 5 | 0162-8828 |
Citations | PageRank | References |
25 | 1.35 | 32 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yefeng Zheng | 1 | 1391 | 114.67 |
| Huiping Li | 2 | 574 | 38.28 |
| David Doermann | 3 | 4313 | 312.70 |