A neural network based handwritten Meitei Mayek alphabet optical character recognition system

Laishram, Romesh; Singh, Pheiroijam Bebison; Singh, Thokchom Suka Deba; Anilkumar, Sapam; Singh, Angom Umakanta

doi:10.1109/iccic.2014.7238510

Cited by 19 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A Neural Network BasedHandwritten Meitei MayekAlphabetOpticalCharacterRecognition System [1] Handwrittencharacter recognition is apart of optical character (OCR) system.OCR canbeappliedtoboth printed textandhandwritten documents. Inthispaperwe discussedthehandwrittencharacter recognition ofMeiteiMayek (Manipuri script Scanning NeuralNetwork for TextLineRecognition [5] This paper describessegmentationfree text linerecognitionapproachusing multilayer perceptron(MLP) and hiddenmarkovmodels (HMMs).Aline canningneural networktrainedwith characterlevel contextualinformation andaspecialgarbageclass-isusedtoextractclassprobabilities at every pixel succession.The outputofthis scanningneural networkisdecoded byHMMs toprovide characterlevel recognition.…”

Section: Literature Surveymentioning

confidence: 99%

A Review on Text Detection and Character Recognition for Printed Document

2016

IJAERD

View full text Add to dashboard Cite

Abstract-Textrecognitioninimagesisaresearcharea which attemptstodevelopa computersystem withtheabilityto automaticallyread thetextfrom images.Thesedaysthere isa hugedemand in storing theinformation availableinpaper documents formatin toacomputerstoragediskandthen later reusingthisinformationbysearchingprocess.Onesimple wayto store informationfrom thesepaperdocumentsin tocomputer system istofirstscanthedocumentsandthenstorethemas images.Buttoreusethisinformationitisverydifficulttoread theindividualcontentsandsearchingthecontentsformthese documentslineby-lineand word-by-word.Thechallenges involved in thisthefontcharacteristicsofthecharactersin paper documentsand qualityofimages.Duetothesechallenges, computer isunable torecognize thecharacters while reading them.Thusthereisaneedofcharacterrecognitionmechanisms toperform DocumentImageAnalysiswhichtransforms documentsin paperformattoelectronicformat.In this paperwe havediscussmethodfortextrecognitionfrom images.

show abstract

Section: Literature Surveymentioning

confidence: 99%