AutomaticContactImporterfromBusinessCardsforAndroid

PiyushSharmaKacynFujii spiyush@stanford.edukhfujii@stanford.edu Description Recently, smartphones have become extremely popular in thegeneralpopulationas ofAugust 2013,145 million people inthe UnitedStatesownsmartphones[1]. Ofthese, Android phonesmake up 51.6%of the smartphone marketshare [1]and haveincreasinglypowerfulprocessors andcameras. Thisallowsfor the creationofstandaloneAndroidapplicationsthatcancaptureandprocessimages. Optical character recognition, or OCR, involves the conversion of images to machinereadable text [2]. Commercial applications of OCR have been developed since the 1950s [3] and include texttospeech, businessdocumentreaders,billprocessingsystems,andmanyotherapplications. Our projectistoimplementOCRalgorithmsusing theAndroidplatform usingOpenCVtoreadinformation from business cards. The image of the business card will first be taken using the Android camera, then processed using an OCR engine likeTesseract. Oncethe contactinformationofthe business cardowner is extracted, this information will then be added into the phone users contact book. This standalone Android application would remove the need to manually enter information from business cards intoones contactslist. Algorithm The input from the camera needs to be alignedtogetafrontalviewof thebusinesscard forOCR. Other preprocessing might include binarization and morphological operations to remove any stray foreground pixels (if needed). The image would then be fed to an OCR engine to recognize individual characters, which then need to be combined using spatial cues and heuristics into name and phone numbers. For example, a wordwithnonumber locatedontopof ablock oftext is likelyto be thename,anda wordwith all numbers is likely a phonenumber. This information can thenbeaddedto thephones contactlistusing AndroidAPIs.PleaserefertoFigure1. TheabovesystemwillbeimplementedonAndroidusingOpenCV.

Milestones AlignmentandPreprocessing ImplementationofalightweightOCR,oruseTesseract[4] Algorithmtoextractnameandphonenumberfromtherecognizedcharacters UsingAndroidAPIstoautomaticallyaddacontact

Figure1:SystemOverview

References [1]ComScore:WindowsPhonenowat3.2%marketshare,Androidat51.6%intheUnitedStates. WinBeta.Accessed21October2013. http://www.winbeta.org/news/comscorewindowsphonenow32marketshareandroid516unitedstates [2] Impedovo, S., L. Ottaviano, and S. Occhinegro. "Optical character recognitiona survey." InternationalJournalofPatternRecognitionandArtificialIntelligence5.01n02(1991):124. [3] Srihari, Sargur N., and Stephen W. Lam. "Character recognition." Formal Description Techniques, IV(FORTE'91.1992. [4] Smith, Ray. "An overview of the Tesseract OCR engine." Document Analysis and Recognition, 2007.ICDAR2007.NinthInternationalConferenceon.Vol.2.IEEE,2007.