DocumentCode
2500218
Title
Consensus Network Based Hypotheses Combination for Arabic Offline Handwriting Recognition
Author
Prasad, Rohit ; Kamali, Matin ; Belanger, David ; Rosti, Antti-Veikko ; Matsoukas, Spyros ; Natarajan, Prem
Author_Institution
Raytheon BBN Technol., Cambridge, MA, USA
fYear
2010
fDate
23-26 Aug. 2010
Firstpage
2861
Lastpage
2864
Abstract
Offline handwriting recognition (OHR) is an extremely challenging task because of many factors including variations in writing style, writing device and material, and noise in the scanning and collection process. Due to the diverse nature of the above challenges, it is highly unlikely that a single recognition technique can address all the characteristics of real-world handwritten documents. Therefore, one must consider designing different systems, each addressing specific challenges in the handwritten corpus, and then combining the hypotheses from these diverse systems. To that end, we present an innovative approach for combining hypotheses from multiple handwriting recognition systems. Our approach is based on generating a consensus network using hypotheses from a diverse set of handwriting recognition systems. Next, we decode the consensus network for producing the best possible hypothesis given an error criterion. Experimental results on an Arabic OHR task show that our combination algorithm outperforms the NIST ROVER technique and results in a 7% relative reduction in the word error rate over the single best OHR system.
Keywords
document image processing; handwriting recognition; Arabic offline handwriting recognition; consensus network; handwriting recognition systems; hypotheses combination; real-world handwritten documents; Decoding; Error analysis; Handwriting recognition; Hidden Markov models; Lattices; NIST; Speech recognition; OCR; ROVER; consensus network; handwriting; system combination;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition (ICPR), 2010 20th International Conference on
Conference_Location
Istanbul
ISSN
1051-4651
Print_ISBN
978-1-4244-7542-1
Type
conf
DOI
10.1109/ICPR.2010.701
Filename
5597041
Link To Document