UNSD Workshop

1
Supporting National Censuses
Top Image SystemsData Capture platform for
Censuses
Amir Angel Director of Government Projects

• UNSD Workshop Minsk - Dec 2008

2
Agenda

• Who we are?
• TISs Platform for Censuses
• Questions Answers
• Demo

3
Number of people Counted by TIS in Censuses
world wide
1,374,026,304
3
4
TISs Experience in Censuses Projects

• 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)

Largest market share worldwide in census projects
information capture
5
TISs Experience in Censuses Projects

• 2010 Round
• Projects Won
• Scottish Census 2011
• Belarus 2009

6
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

7
Local offices in

• Europe United Kingdom, Germany,
  Italy, Spain, France, Benelux
• Asia Japan, Singapore, Hong Kong,
  Shanghai,
• Guangzhou (RD) and Australia
• USA North Latin America
• Israel RD Headquarters
• Present in app. 40 countries
• Strong partner network worldwide
• Around 800 installed systems worldwide

8
eFlow platform for Censuses
Top Image SystemsData Capture platform for
Censuses
9
The evolution of data capture in census projects
eFLOW
From OCR into IDR Solution
10
TISs Census Data Capture Solution
Census Data base
Suggest a Single platform for all enterprise
content
11
How does eflow read data?
Top Image SystemsData Capture platform for
Censuses
12
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
13
Process integrality, implementing a work flow
according to the client needs
MFlexibilityctivator
Scanning
OCR
Validation
Export
13
14
Flexibility
15
Flexibility
16
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
17
Advanced approaches

• Automatic EFI Matching
• Improving template recognition station speed via
  the Force EFI mechanism, a unique barcode
  posted on each page
• Questioner integrity

18
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
19
Multiple Data Types
ICR
OMR
OCR
20
Recognition engines/technologies embedded in the
platform
20
21
Virtual Engine example to increase recognition
22
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

23
Form Out

• Reduce network traffic
• Reduce storage media

24
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
25
Completion Station Page Mode
26
Field Group Mode Completion
27
Business Logic Validation
28
Unique Tiling stations Checking for false
positives

• Identify false positives
• Alpha Numeric fields
• Highlight for verifications
• Quality control for ICR

29
Implementing Edits
30
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 shouldnt have wife
• And more

31
Coding
Computer Assisted Coding by statistical experts
as part of the data capture system (2nd level
repair).
32
(No Transcript)
33
Custom stations approach
34
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
35
Customized Exported DataExamples
SQL
XML
CSV
Tab Delimited
36
Controller
37
Monitoring and Management
38
Modules

• Statistical Data base
• Statistical report to monitor the daily, weekly,
  monthly rate per user/station
• Quality checking using

39
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

40
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.