This paper present ahandwrit30 recognitec systg tt dealswit unconst2S)8S handwrit ing and large vocabularies. Thesyst5 is based on t) segmentmen)2S20)8S2[[--) paradigm where words arefirst loosely segmentm int charact)8 or pseudocharact)8 and td final segmentgmen isobt[5SO duringtr recognitog process, which is carriedout wit a lexicon. Charactr - are modeled by multO0] hidden Markov models (HMMs), which areconcat5)8S-- t build up word models. The lexicon is organized as at3] st[]O)8S0 and duringtr decoding words wit similar prefixes share th same stput To avoid an explosion of tf search space duet te presence of multS20 charact - models, a lexicon-driven level building algorit) (LDLBA)is usedt decode t) lexicaltxi andt choose at each levelt] more likely models. Bigram probabilitpr relata t ta variat5) ofwrit#[ st yleswit)-- tt words areinsert[ bet ween tn levels of t) LDLBAt improvet2 recognit52 accuracy. TofurtS[ speed up tp recognit8-- process, someconst2S[ t are addedt limit tm searche#ort t to more likelypart of t) search space. Experimenti result on adat[#2 of 4674 unconst#[)83 words showt3# t3 proposed recognit)8 systo achieves recognit3# rato from 98% for a 10word vocabularyt 71% for a 30,000-word vocabulary and recognit3S tcog from 9 mst o 18.4 s, resp ect) ely.

Many off-line handwritten word recognition systems have been proposed since the early nineties. Most systems reported high recognition rates, however, they overlooked a very important factor in the process; speed factor. In this paper we explore the potential for speeding up an off--line handwritten word recognition system via concurrency. The goal of the system is to achieve both full accuracy and high speed when taking into account large vocabularies. This has been accomplished by integrating the recognition process with multiprocessing and distributed computing concepts. Experimental results showed that the multiprocessing environment is very promising in enhancing a sequential off-line handwritten word recognition system performance.

Contents 1 Introduction 5 2 State of the art 7 2.2 State of the Art . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.3 Structure of a CWR System . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 2.3.1 Normalization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 2.3.2 The segmentation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 2.3.3 Feature extraction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 2.3.4 Lexicon reduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 2.3.5 The data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 2.3.6 The recognition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 2.3.7 Human Reading Inspired Systems . . . . . . . . . . . . . . . . . . . . . . . . . 17 2.3.8 Holistic approaches . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

A new paradigm, which models the relationships between handwriting and topic categories, in the context of medical forms, is presented. The ultimate goals are (i) the recognition of medical handwriting, and (ii) the use of such information for practical applications such as a medical form search engine. Medical forms have diverse, complex and large lexicons consisting of English, Medical and Pharmacology corpus. Our technique shows that a few recognized characters, returned by handwriting recognition, can be used to construct a linguistic model capable of representing a medical topic

This paper present ahandwrit30 recognitec systg tt dealswit unconst2S)8S handwrit ing and large vocabularies. Thesyst5 is based on t) segmentmen)2S20)8S2[[--) paradigm where words arefirst loosely segmentm int charact)8 or pseudocharact)8 and td final segmentgmen isobt[5SO duringtr recognitog process, which is carriedout wit a lexicon. Charactr - are modeled by multO0] hidden Markov models (HMMs), which areconcat5)8S-- t build up word models. The lexicon is organized as at3] st[]O)8S0 and duringtr decoding words wit similar prefixes share th same stput To avoid an explosion of tf search space duet te presence of multS20 charact - models, a lexicon-driven level building algorit) (LDLBA)is usedt decode t) lexicaltxi andt choose at each levelt] more likely models. Bigram probabilitpr relata t ta variat5) ofwrit#[ st yleswit)-- tt words areinsert[ bet ween tn levels of t) LDLBAt improvet2 recognit52 accuracy. TofurtS[ speed up tp recognit8-- process, someconst2S[ t are addedt limit tm searche#ort t to more likelypart of t) search space. Experimenti result on adat[#2 of 4674 unconst#[)83 words showt3# t3 proposed recognit)8 systo achieves recognit3# rato from 98% for a 10word vocabularyt 71% for a 30,000-word vocabulary and recognit3S tcog from 9 mst o 18.4 s, resp ect) ely.

for search engines

I thank the Almighty for providing me with this opportunity to serve Him and make a contribution through His infinite wisdom. I thank my parents for their perseverance and unconditional support, without which I could never have accomplished this endeavor. I would also like to thank other members of my family including my cousin Muneer who has been watching my back from day one. I want to extend my deep appreciation to Dr. Venu Govindaraju, the chair of my dissertation committee. He has been an advisor and a mentor. His persistent guidance, omnipresent motivation and overall support have been the foundation of this thesis. He introduced me to the area of handwriting recognition and encouraged me to address the open challenge of retrieval from handwritten documents. I want to show my gratitude to Dr. Peter Scott, member of my dissertation committee. His course Computer Vision and Image Processing indeed laid a solid foundation for iv this research. His guidance and advise has been always helpful. In addition, I had the opportunity to be his Teaching Assistant for three semesters and his passion for teaching was a great motivation.

Abstract not found