Title: Content Based Information Retrieval in Forensic Image Databases
1- Content Based Information Retrieval in Forensic
Image Databases -
2Outline
- Introduction
- Techniques for searching in image databases
- Feature selection and indexing
- Examples of real image databases
- Conclusions and future work
3Introduction
- Many forensic databases of images
- - fingerprints
- - shoeprints
- - tool marks
- - cartridge cases
- - logos on pills containing MDMA
- - hand writing
- - video and 3D-information
- - numerous other databases in laboratories
4Problem
- Selecting the right images based on forensic
knowledge and retrieve only the images that are
relevant, but do not miss images that are
relevant. - Constraints
- The algorithm has to work fast
- The images in database might be captured in
different ways
5Techniques
- Text strings by user (first generation)
- Features as texture, color, shape selected by an
algorithm - Recognize important features for the forensic
field the mark, and use semantics (e.g..
Fingerprints) - Match using relevancy
- Use index for faster searches
- View images in web browser or computer screen and
user can iterate
6Data entry
- Images are captured using a camera or scanner
- The administrative data is combined by a user or
another database - The user also classifies
- The computer selects features
- The user approves the features
- The user searches
7Feature selection
- Pre-processing step (eg. Wavelets for filtering
out the relevant information) - Select the features (color, texture, shape, or
anything else that is important) - Manual interaction with user, who selects the
parts that are relevant
8Color
- Just text green, red, blue
- By color histograms
- By color spaces that are invariant to lighting
9Texture
- Different frequencies in the image
- Difficult to express in words
- Granularity, directionality and repetitiveness
- Vectors often high frequencies in image
10Shape
- Shape are object identities in a meaningful form.
- squares, rectangles and circles
- 1. area, local elements of its boundary
- 2. transformation approach transform a shape
into another shape - Goal make it geometric invariant
11Structure
- Gestalt of an image
- Line drawings versus pictures
- deriving a set of edges, corners and their
location in image space
12Others
- Motion (in video)
- Contents semantics often used in forensic image
databases - 3D-features
13Matching / ranking
- Metric model
- Euclidean distance, City-block distance,
- Minkowsky distance, Earths Movers distance
- Advantage easy to compute
- can be used in indexes
- Disadvantage Human Visual System
- sometimes works different
-
14Other matching methods
- Transformational distances how much effort is
needed to convert a shape into another shape
15Indexing
- Used for improving speed of searching
- Classical indexing text strings with hashes
- Geometrical hashes
- Many other methods in development that are
mathematically complex (eg. SS-trees, R-trees) - Active indexes
16Performance
17Other performance measures
- Average number of examples needed to obtain a
certain degree of satisfaction - Average number of iterations to obtain a
satisfactory result - Computational complexity
18Commercial Databases that exist
- Fingerprint
- Faces
- Cartridge cases
- Shoeprints
- Tool marks
- Images of web
19Fingerprints
- Syntactic ridge patterns and minutiae - string
of primitives.The pre-defined classes are
modelled as a set of grammars from the training
samples - Structural features based on minutiae are
extracted and then represented using a graph data
structure. - Neural network approach the feature vector is
constructed and classified by a neural network
classifier. - Statistical approaches statistical classifiers
are used instead of neural classifiers.
20Faces
- Determine invariant points of face in the image
- Use these points for matching
- Other method is using Principal Components
Analysis - Gabor filters are used for being invariant for
illumination
21Experiments with our databases
- Pixel-wise approach compare all pixels
- Feature-based approach compare the features in
the images
22Toolmarks
- Toolmarks are caused by friction between a
surface and a tool - Eg impression marks / striation marks
23Crimes
- Burglaries (screwdrivers, crowbars, pliers)
- Homicides
- Other crimes
- The toolmark can be identified by a forensic
expert
24Example
25Database of burglary cases
- In the Netherlands these are collected by the
police. - Links can be made between burglaries and tools of
a suspect - Comparison of striation marks time consuming
26Striation Marks
- Different angles of tool to surface will cause
different striation marks - One tool with one striation marks, means eight
comparisons at least for the examiner.
27Database
28Real life Striation marks / side light
293D structured light
- Project different line patterns on a toolmark
- Acquire these images with a camera
- Calculate the depth of the surface
30OMECA
With micromirror device
31Correlation methods
- Continuation of Previous research in 1995 for
side light - User interactive signature selection
- Calculating the standard deviation of the
difference after normalization steps
32Selecting a part and previewing
33Slope compensation of striation mark
34Slope in z-direction
Compensate by selecting the edges and normalize
35Experiment
- 6 screwdrivers
- Striation marks of 45 degrees to the surface
- Both gray values / 3D values
36Results Gray values
37Results Structured Light
38Conclusion
- 3D will result in Higher correlation factors
- Less sensitive to the lighting of the surface
- Fast for capturing
39Future Research
- Testing on Larger Database
- Preselection on the shape of the blade
- Using 3D-images of the blade of the tool
40Introduction
- Forensic firearm comparison
- cartridge case specific marks caused by
feeding, extraction and ejection mechanism of the
firearm. - Firing pin and breech-face-marks
41Manual Comparison
42Ballistic Imaging Systems
- IBIS
- Drugfire
- MRT GE/2
- CIBLE
- Fireball
43Images for testing
44Database
45Comparison
46Overview database
47Content based retrieval
- Images with noise
- Images that are rotated or shifted
- Difference in light source
- Difference in cartridge case metal
- Wear of firearm
- Wear of cartridge case
- Marks between two shots differ for mechanical
statistical reasons
48Matching pairs
- From practical cases
- matches between cartridge case found at the scene
of crime and from the firearm - 49 cases
- 19 different firearms (2-5 cases per firearm)
49Preprocessing step
- Since there are some light variations
- equalization / normalization / circle
50Alternative polar coordinates
51Rank on variance
52Rotation sensitivity
53Multiresolution Approach
- Why multiresolution / wavelet transform
- Split
- background
- noise
- observed object
54A trous
- Means with holes interlaced convolution at
decreasing resolution - no aliasing
- scaling function B3-spline
- original image is sum of wavelet planes
55Scales
1 2
3 4
56Brute force registration
- Rotate and translate the cartridge case
- In our tests 360 degrees and 20 pixels in x and
y-direction - Computationally very expensive !
57Experiments
58Firing pin
- Influence of marks and shapes in firing pin had
to be reduced to 50 percent for the raw images - For log polar images to 20 percent
59Computation with brute force
- Computationally very intensive
- 3 computers worked 91 days for computing these
numbers
60Rotation and translation invariant
- log-polar transform of the Fourier magnitude
- Suppose translation and rotation and some
scaling -
61Polar Coordinates
Rectangular Log-Polar
62Polar coordinates
- Mapping of Fourier magnitudes into polar
coordinates - logarithmic transformation of r-axis transforms
scaling into a shift - polar mapping followed by log-transform of r-axis
log-polar transform
63Crosscorrelation of Triple invariant Image
descriptors
64Faster preselection
- Based on tracking research
- Good features are located by examining the
minimum eigenvalue of each 2 by 2-gradient
matrix. - The features are tracked by a Newton-Raphson
method of minimizing the difference between the
two windows - Multiresolution tracking allows for even large
displacements between images.
65KLT tracking method
66KLT
- The number of points tracked is a measure for the
ranking on the list - In our test 41 were in the top positions for
side light - 49 are in the top five percent
- Rotation and translation are followed
67Conclusions
- If the user follows the protocol and the marks
are clear, good results are possible and fast
algorithms are possible - Brute force registration works, however it is
computationally very intensive
68Conclusions (2)
- Brute force registration of third scale gives
good results - Log polar transform in third scale appears to
work for 41 out of 49 images
69Conclusions (3)
- KLT-method works for side and ring light images
for pre selection - Further refinement by selection of areas that
should be compared - Relevance feedback of correlation should be used
70Future Research
- Optical correlators
- Other databases of images
- Other algorithms of correlation
71Introduction
- Drugs department of our institute
- Illicitly produced drugs
- MDMA / amphetamine
- Database of these pills for linking manufacturers
72Introduction (2)
- In database
- image- diameter- shape- weight- chemical
composition
73Introduction (3)
- Logos contain all kind of figures
- Description is also in database
74Requirements correlation
- Many kind of trademark images
- Fantasy images
- Pill itself may be damaged
- Other shapes of the pill
- Position of the pill
- Pill in top position
- 2D-image of 3D shape
75Correlation Methods
- Color
- Texture
- Shape (needed for logos)
- Other types of primitive features
- To search on these features descriptors are
necessary
76Shape retrieval
- Global features
- Aspect ratio, circularity, moments invariants
- Local features
- Sets of consecutive boundary segments
- Other methods
- Elastic deformation of shapes / wavelets etc.
77Implementations
- Commercial databases
- QBIC / Virage / Excalibur
- Imatch
- Others
- MPEG-7
- Log polar correlation
- Photobook / Chabot / Visualseek / MARS / Zomax /
Surfimage
78Trademarks
- Trademarks are similar
- However the 3D-shape is not involved
- Project with University of Amsterdam on Drugs
pills and trademarks (ZOMAX)
79Correlation Methods MPEG-7
- Due to be approved in September 2001
- Video streams
- Will have effects on CBIR activities
- Test systems for members available
80Correlation Methods MPEG-7 shape
- Object bounding box
- Region Based Shape
- Contour Based Shape
81Contour Based Shape
- The number of peaks in the image
- The highest peak height
- The eccentricity
- Contour curvature vector
82Test database
- Of cases from 1991
- Over 600 images are stored in the database
- One drugs pill is entered in the database under
20 different positions of 15 degrees rotation. - Comparison of results based on this drugs pill
83Test images
84Results QBIC
85Results Imatch
86Results with QBIC
87Results with Imatch
88Results with Log Polar
89Results with MPEG-7
90Improvement Pre-processing
- Labeling pill / logo
- Split by subtraction
91MPEG-7 after processing
92Conclusions and discussion
- Color features appear to work better, however
these do not always work for our case - Light conditions might influence results
- Log Polar correlation takes long
- MPEG-7 Curvature Space representation fast
and most in top positions after pre-processing - 3D acquisition of the drugs pill could work better
93Future developments
- Probably more MPEG-7 - standardization
- Optical computers or parallel processors might
make more complex methods possible - 3D images and search methods
- Third generation databases might take over ten
years, since first the HVS has to be understood