400 likes | 549 Views
UNSD Workshop – Minsk - Dec 2008. Supporting National Censuses. Top Image Systems Data Capture platform for Censuses. Amir Angel Director of Government Projects. Agenda. Who we are? TIS’s Platform for Censuses Questions & Answers Demo.
E N D
UNSD Workshop – Minsk - Dec 2008 Supporting National Censuses Top Image SystemsData Capture platform for Censuses Amir Angel Director of Government Projects
Agenda • Who we are? • TIS’s Platform for Censuses • Questions & Answers • Demo
Number of people “Counted” by TIS in Censuses world wide 1,374,026,304 3
Turkey 1997 & 2000 • Brazil 2000 • Kenya 2000 • South Africa 2001 • Slovak Republic 2001 • Hong Kong 2001 • India 2002 • Ireland 2002 • Italy 2002 • Cyprus 2002 • Slovenia 2006 (Census of real estates) • Ireland 2006 • Hong Kong 2006 • South Africa 2007 (Community Survey) • Thailand NSO 2008 (Community Survey) TIS’s Experience in Censuses Projects Largest market share worldwide in census projects information capture
TIS’s Experience in Censuses Projects • 2010 Round • Projects Won: • Scottish Census 2011 • Belarus 2009
Overview - Top Image Systems • Founded 1991 • Data Extraction solutions. Specialized in Censuses Projects. • Since 1996, traded on NASDAQ (TISA) • Since 2006, traded on TASE (TISA) • 2 acquisitions in 2007 • ~250 employees
Local offices in: Europe United Kingdom, Germany, Italy, Spain, France, Benelux Asia Japan, Singapore, Hong Kong, Shanghai, Guangzhou (R&D) and Australia USA North & Latin America Israel R&D Headquarters • Present in app. 40 countries • Strong partner network worldwide • Around 800 installed systems worldwide
eFlow platform for Censuses Top Image SystemsData Capture platform for Censuses
The evolution of data capture in census projects eFLOW From OCR into IDR Solution
TIS’s Census Data Capture Solution Census Data base Suggest a Single platform for all enterprise content
How does eflow read data? Top Image SystemsData Capture platform for Censuses
01010 1010101010101010 0101 1010101010101010101 10101010101010101010 1 101010101010101010 0 1010101010101010 1010 1 1010101010 001 101 101010101010101010 1 The Process Flow – Processing Center Output Input Electronic Archive eDocs and Facsimile Compl et ion RECOG N T I O N CLASSIFY EXPORT Database Host/ERP/Custom Scanned Documents Workflow Process Email Structured & unstructured information Exception
Process integrality, implementing a work flow according to the client needs MFlexibilityctivator Export Scanning OCR Validation 13
01010 1010101010101010 0101 1010101010101010101 10101010101010101010 1 101010101010101010 0 1010101010101010 1010 1 1010101010 001 101 101010101010101010 1 The Process Flow Output Input Electronic Archive eDocs and Facsimile Compl et ion RECOG N T I O N CLASSIFY EXPORT Database Host/ERP/Custom Scanned Documents Workflow Process Email Structured & unstructured information Exception
Advanced approaches • Automatic EFI Matching • Improving template recognition station speed via the “Force EFI” mechanism, a unique barcode posted on each page • Questioner integrity
01010 1010101010101010 0101 1010101010101010101 10101010101010101010 1 101010101010101010 0 1010101010101010 1010 1 1010101010 001 101 101010101010101010 1 The Process Flow Output Input Electronic Archive eDocs and Facsimile Compl et ion RECOG N T I O N CLASSIFY EXPORT Database Host/ERP/Custom Scanned Documents Workflow Process Email Structured & unstructured information Exception
Multiple Data Types ICR OMR OCR
Recognition engines/technologies embedded in the platform RICOH (Japanese) PENPOWER (Chinese) LIGATURE JUSTICR ABBYY KADMOS OCE INLITE EXPERVISION OMNIPAGE A2IA TIS NESTOR 20
ICR B ICR A ICR C *oshua Jo*hu* J*sh*a VotingMethod Joshua Virtual Engine example to increase recognition
Automatic approaches • Auto Coding • Coding tasks and data validations performed on the data capture platform: a ‘cost-effective’ solution • Use one of the statistic software's in the market like ACTR (Canadian statistical software for coding some fields) • Use Approximate Search tools for improving results via DB (Exorbyte) • Dynamic Dictionary update • Lookup and dictionaries via DB
ROI Original TIFF EFI DIF Form Out • Reduce network traffic • Reduce storage media
01010 1010101010101010 0101 1010101010101010101 10101010101010101010 1 101010101010101010 0 1010101010101010 1010 1 1010101010 001 101 101010101010101010 1 The Process Flow Output Input Electronic Archive eDocs and Facsimile Compl et ion RECOG N T I O N CLASSIFY EXPORT Database Host/ERP/Custom Scanned Documents Workflow Process Email Structured & unstructured information Exception
Unique Tiling stations – Checking for false positives • Identify false positives • Alpha & Numeric fields • Highlight for verifications • Quality control for ICR
Analysis Of Current Form • Dictionaries • Owner name to actual address • Address Database • Date Of Birth : should match with Age • Higher Education : Which 12th year of high school • Age Of Mum : Child cannot be older than mum • Religion : Detailed action • Married : if not married shouldn’t have wife • And more…
Coding Computer Assisted Coding by statistical experts as part of the data capture system (2nd level repair).
01010 1010101010101010 0101 1010101010101010101 10101010101010101010 1 101010101010101010 0 1010101010101010 1010 1 1010101010 001 101 101010101010101010 1 The Process Flow Output Input Electronic Archive eDocs and Facsimile Compl et ion RECOG N T I O N CLASSIFY EXPORT Database Host/ERP/Custom Scanned Documents Workflow Process Email Structured & unstructured information Exception
Customized Exported DataExamples SQL XML CSV Tab Delimited
Monitoring and Management
Modules • Statistical Data base • Statistical report to monitor the daily, weekly, monthly rate per user/station • Quality checking using
Post Census Usage • Building of new Database for Census • Agricultural Census • Real Estate Census • On going Surveys • Tax Office • Tourism Board • Immigration Department • Urban Development Board
Summery • Data capture and IDR platform (paper, electronic, mobile) and not a recognition product • Proven solution in census data capture! no need to invest time and money in new technology and vendor, minimizing the risk • Extensive experience in the design, development and implementation of real census and other high volume form processing projects. Largest market share worldwide in the processing of census projects, • Huge experience based on long researches in the Census arena • Maximum flexibility, redundancy and robust platform ensuring you meet project timetable to release census results.