Document Images and E-Discovery

1
Document Images and E-Discovery

• David Doermann, UMIACS
• May 4, 2009

2
Goals of This Lecture

• To help you understand
• Why you may want to acquire document images?
• How you acquire them?
• What you get when you do?
• What you can do with them?
• Why it is not as easy as you may think to
  organize them?
• Discuss some of the issues for those doing
  E-Discovery.

3
Assumptions

• We have some need to access a set of documents
• Archiving?
• Litigation?
• FOIA Request
• Often have (massive) Heterogeneous Collections
• Different languages
• Different layouts
• Different sources
• We are lucky if metadata is consistent and
  Uniform.

4
Why acquire Document Images?

• Paperless Solution
• Efficient transfer
• Organization
• Convenience
• Access to a variety of content
• Universal reader email, attachments, spread
  sheets
• Dont need original applications
• Prevent Change?
• Easier to certify?

5
How do we acquire?

• Scanning?
• High speed, automated, multiform books, etc
• Digital Copiers
• Corporate Memory
• Application Output
• Print to Image
• Mass Conversion
• Cameras?
• Cell Phones?
• QipIt, ScanR, Hotcard
• All have implications for use

6
Where do we find them?

• Internet
• Email Attachments
• Online Proceedings
• Electronic Fax
• Mass Digitization Repositories

7
What you can do with them?

• Can we Access it?
• Search
• Browse
• Read
• Index and Retrieve them?
• In their basic form not really!
• We can
• View
• Print
• Not much else
• Why?

8
What is an image?

• Pixel representation of intensity map
• No explicit content, only relations
• Image analysis
• Attempts to mimic human visual behavior
• Draw conclusions, hypothesize and verify

Image databases Use primitive image analysis to
represent content Transform semantic queries into
image features color, shape, texture spatial
relations
9
Document Images

• A collection of dots called pixels
• Arranged in a grid and called a bitmap
• Pixels often binary-valued (black, white)
• But grayscale or color is sometimes needed
• 300 dots per inch (dpi) gives the best results
• But images are quite large (1 MB per page)
• Faxes are normally 100-200 dpi
• Usually stored in TIFF or PDF format
• Yet we want to be able to process them like text
  files!

10
Document Image Database

• Collection of scanned images
• Need to be available for indexing and retrieval,
  abstracting, routing, editing, dissemination,
  interpretation

11
(No Transcript)
12
Other Documents
13
(No Transcript)
14
(No Transcript)
15
Indexing Page Images(Traditional Conversion)
Page Image
Structure Representation
Document
Page Decomposition
Scanner
Text Regions
Character or Shape Codes
Optical Character Recognition
16
Document Image Analysis

• General Flow
• Obtain Image - Digitize
• Preprocessing
• Feature Extraction
• Classification
• General Tasks
• Logical and Physical Page Structure Analysis
• Zone Classification
• Language ID
• Zone Specific Processing
• Recognition
• Vectorization

17
Document Analysis

• What you need to do before you can treat images
  as e-documents.
• Document Image Analysis
• Page decomposition
• Optical character recognition
• Traditional Indexing with Conversion
• Confusion matrix
• Shape codes
• Doing things Without Conversion
• Duplicate Detection, Classification,
  Summarization, Abstracting
• Keyword spotting, etc

18
(No Transcript)
19
Why is document analysis difficult?

• 2D Array of values
• Represents a Symbolic Language
• Many Variations in symbols
• AaAAAAAAAA
• 3-4 times larger then normal digital images
• And this is just machine printed Latin Text!

20
Page Analysis(assume are looking for text)

• Skew correction
• Based on finding the primary orientation of lines
• Image and text region detection
• Based on texture and dominant orientation
• Structural classification
• Infer logical structure from physical layout
• Text region classification
• Title, author, letterhead, signature block, etc.

21
Page Layer Segmentation

• Document image generation model
• A document consists many layers, such as
  handwriting, machine printed text, background
  patterns, tables, figures, noise, etc.

22
Page Segmentation

• Typically based on Spatial Proximity
• White space
• Margins
• Differences in Content Type
• Can be very sensitive to noise
• Distinguish between
• Top Down What know what should be there
• Bottom up We know what is there locally

23
Image Detection
24
Text Region Detection
25
More Complex Example
Printed text Handwriting Noise
Before MRF-based postprocessing
After MRF-based postprocessing
26
Application to Page Segmentation
Before enhancement
After enhancement
27
Language Identification

• Language-independent skew detection
• Accommodate horizontal and vertical writing
• Script class recognition
• Asian script have blocky characters
• Connected scripts cant be segmented easily
• Language identification
• Shape statistics work well for western languages
• Competing classifiers work for Asian languages
• What about handwriting?

28
Optical Character Recognition

• Pattern-matching approach
• Standard approach in commercial systems
• Segment individual characters
• Recognize using a neural network classifier
• Hidden Markov model approach
• Experimental approach developed at BBN
• Segment into sub-character slices
• Limited lookahead to find best character choice
• Useful for connected scripts (e.g., Arabic)

29
OCR Accuracy Problems

• Character segmentation errors
• In English, segmentation often changes m to
  rn
• Character confusion
• Characters with similar shapes often confounded
• OCR on copies is much worse than on originals
• Pixel bloom, character splitting, binding bend
• Uncommon fonts can cause problems
• If not used to train a neural network

30
Improving OCR Accuracy

• Image preprocessing
• Mathematical morphology for bloom and splitting
• Particularly important for degraded images
• Voting between several OCR engines helps
• Individual systems depend on specific training
  data
• Linguistic analysis can correct some errors
• Use confusion statistics, word lists, syntax,
• But more harmful errors might be introduced

31
OCR Speed

• Neural networks take about 10 seconds a page
• Hidden Markov models are slower
• Voting can improve accuracy
• But at a substantial speed penalty
• Easy to speed things up with several machines
• For example, by batch processing - using desktop
  computers at night

32
Problem Logical Page Analysis (Reading Order)

• Can be hard to guess in some cases
• Newspaper columns, figure captions, appendices,
• Sometimes there are explicit guides
• Continued on page 4 (but page 4 may be big!)
• Structural cues can help
• Column 1 might continue to column 2
• Content analysis is also useful
• Word co-occurrence statistics, syntax analysis

33
Retrieval of OCRd Text

• Requires robust ways of indexing
• Statistical methods with large documents work
  best
• Key Evaluations
• Success for high quality OCR (Croft et al 1994,
  Taghva 1994)
• Limited success for poor quality OCR (1996 TREC,
  UNLV)
• Clustering successful for gt 85 accuracy (Tsuda
  et al, 1995)

34
N-Grams

• Powerful, Inexpensive statistical method for
  characterizing populations
• Approach
• Split up document into n-character pairs fails
• Use traditional indexing representations to
  perform analysis
• DOCUMENT -gt DOC, OCU, CUM, UME, MEN, ENT
• Advantages
• Statistically robust to small numbers of errors
• Rapid indexing and retrieval
• Works from 70-85 character accuracy where
  traditional IR fails

35
Matching with OCR Errors

• Above 80 character accuracy, use words
• With linguistic correction
• Between 75 and 80, use n-grams
• With n somewhat shorter than usual
• And perhaps with character confusion statistics
• Below 75, use word-length shape codes

36
Processing Images of Text

• Characteristics
• Does not require expensive OCR/Conversion
• Applicable to filtering applications
• May be more robust to noise
• Possible Disadvantages
• Application domain may be very limited
• Processing time may be an issue if indexing is
  otherwise required

37
Keyword Spotting

• Techniques
• Work Shape/HMM - (Chen et al, 1995)
• Word Image Matching - (Trenkle and Vogt, 1993
  Hull et al)
• Character Stroke Features - (Decurtins and Chen,
  1995)
• Shape Coding - (Tanaka and Torii Spitz 1995
  Kia, 1996)
• Applications
• Filing System (Spitz - SPAM, 1996)
• Numerous IR
• Processing handwritten documents
• Formal Evaluation
• Scribble vs. OCR (DeCurtins, SDIUT 1997)

38
Shape Coding

• Approach
• Use of Generic Character Descriptors
• Make Use of Power of Language to resolve
  ambiguity
• Map Character based on Shape features including
  ascenders, descenders, punctuation and character
  with holes

39
Additional Applications

• Handwritten Archival Manuscripts
• (Manmatha, 1997)
• Page Classification
• (Decurtins and Chen, 1995)
• Matching Handwritten Records
• (Ganzberger et al, 1994)
• Headline Extraction
• Document Image Compression (UMD, 1996-1998)

40
Some UMD Research

• Multilingual OCR
• Evaluation
• Duplicate detection
• .

41
Detection

• Stamps, Logos, Signatures
• These content regions benefit from detection
  based approach
• Saliency Measures adapt to interclass variation
• Logos location, density, symmetry, size
• Signature flow, oscillations
• Standard classifiers SVM, Fisher, Decision
  Trees.

42
Shape matching
(a)
(b)
Illustration of signature matching using shape
contexts and local-neighborhood-graph
43
Image content categorization

• Distinguishing between text and non-text
  documents
• We constructed a 4,500 image database by crawling
  Web images from Google Image search engine using
  a wide variety of text keywords

44
Page Segmentation
45
Clutter Detection and Removal
Clutter as one single connected component
46
(No Transcript)
47
Is Indexing Enough?

• Many applications benefit from image based
  indexing
• Less discriminatory features
• Features may therefore be easier to compute
• More robust to noise
• Often computationally more efficient
• Many classical IR techniques have application for
  DIR
• Structure as well as content are important for
  indexing
• Preservation of structure is essential for
  in-depth understanding

48

• What else is useful?
• Document Metadata? Logos? Signatures?
• Where is research heading?
• Cameras to capture Documents?
• What massive collections are out there?
• Tobacco Litigation Documents
• 49 million page images
• Google Books
• Other Digital Libraries

49
What next for E-Discovery?(questions to ask)

• Now you want to use the images
• What Meta data is required?
• How was the collection created?

50
Observations

• Structure is a great indicator of content
• Locating Letters, Financial Forms, etc
• Be careful of what you assume about the
  collection
• Handwriting present?
• Noise, Scanning resolution?
• Is there implicit information in the layout?

51
Litigation Specific Issues

• Volume Scanning Separated from Metadata
• Document Determination
• Multiple Edits/Prints of the same document
  (Duplicate Determination)
• Much harder for images
• May have unique BATES numbers
• Cost of scanning or adding manual metadata?
• When is an image sufficient?
• Probably not for handwriting analysis

52
Summary

• Nothing Magic about getting access to images
• Metadata is typically required, and automation
  can be made more difficult by quality
• No substitute for eyes on the imageand most
  systems are set up with this in mind

53
E-Discovery Issues?