(VALSE webinar, 2016.1.13) - - PowerPoint PPT Presentation

基于统计模型的现场指纹处理 (VALSE webinar, 2016.1.13)

冯建江 清华大学 自动化系 http://ivg.au.tsinghua.edu.cn/~jfeng/

内 容

• 1. 背景介绍
• 2. 现场指纹方向场估计
• 3. 现场指纹检测与分割

Human identification in forensics

• Police often face two human identification problems:
• Biometric (especially fingerprint) is the only choice:

– Criminal is not willing to tell the true name(s) – Criminal will not leave their ID cards at scenes

Background check (Who is this guy?) Crime investigation (Who did this?)

Two identification problems

Crime investigation by matching unknown latent to known tenprints Background check by matching unknown tenprint to known tenprints

Mature technology available Open problem

Why latent identification is more difficult?

Crime investigation by matching unknown latent to known tenprints Background check by matching unknown tenprint to known tenprints

• 1. Just one finger
• 2. Quality of latent is very low

This is obvious Why?

Capture tenprints

10 rolled fingerprints 10 plain fingerprints

Capture latent prints

• Fingerprints from crime scene are called “latent” fingerprints

because these fingerprints are invisible, and some special processing steps are needed to make them visible.

• There are many latent processing methods. Selection of a

specific method depends on residue type, surface type, age…

• Powder dusting is a very common technique.
• 1. Dust by powder
• 2. Take photograph
• 3. Lift by tape

Rolled, plain & latent

• These are 3 types of prints from the same finger.
• Compared to rolled and plain fingerprints, quality of latent is very low.
• This poses a big challenge to feature extraction.

Feature extraction: plain vs latent

From NIST-27 Recall: 5/12 Precision: 5/110 From FVC2002 DB1 Recall: 39/45 Precision: 39/39

Same algorithm: VeriFinger Feature: minutia point

Feature extraction for latent

• Because of the poor performance
• f algorithms, until now, feature

extraction for latents has been manually performed by experts.

• Manual feature extraction is time

consuming & expensive.

• Recently, researchers have paid

increasing attention to develop more powerful feature extraction algorithms.

现场指纹识别流程

指纹 检测 指纹 分割 指纹 数据库 方向场 估计 特征 提取 学术界研究重点 特征 匹配 现场指纹处理

Orientation field (OF) estimation is critical

Latent fingerprint Ridge orientation field Enhanced ridge image Minutiae

Existing methods for OF estimation

• Most methods have 2 steps:

– Local estimation: gradient, DFT – OF regularization: low pass filtering, global parametric model

• For plain and rolled fingerprints,

these algorithms work very well.

Chapter 3

OF estimation for latent

Gradient +FOMFE Manual Why human performs much better than the algorithm?

Even without seeing the fingerprint, we are sure that this OF must be wrong. Because we have prior knowledge on fingerprint. Fingerprint experts are good at extracting features in latent because they are very familiar with fingerprints.

Use prior knowledge

• We can develop a better OF estimation algorithm by

using prior knowledge of fingerprints.

• We do not know how prior

knowledge on fingerprint is represented in expert’s brain.

• How to represent, learn, and use prior knowledge?

Basic Ideas

Inspired by spelling check technique, we represent prior knowledge using dictionary. To model the statistics of fingerprints accurately, we use a set of localized dictionaries. To utilize contextual information, dictionaries are overlapping.

Represent prior knowledge via dictionary

zzzzzz abxxde Ixlsoa dsfwws iuytrs yyuooj work biometric topic talk add together Invalid Valid Words Orientation patches

Error correction via dictionary

beaiteful beautiful charactorestic characteristic

4 roughly aligned fingerprints (arch, right loop, left loop, whorl). We observed:

• 1. Orientation patches

at the corresponding location in different fingerprints are similar;

• 2. Orientation patches

at different locations are dissimilar.

• 3. Orientation patches

in the center are more diverse

Why localized dictionaries

Why localized dictionaries

Histogram of orientations at each location Variance of orientations at each location

The observations are also validated using statistics estimated from 398 registered orientation fields.

Contextual information

“There is no such thing as a frea lunch” freak, free, flea, area? frea free If we know the context, we can resolve the ambiguity. ?

Flowchart of OF estimation

Finger coordinate system

• Premise of using localized

dictionaries is defining a finger coordinate system and designing an algorithm to estimate it from fingerprints.

• Origin (finger center) is

geometric center of a frontal finger.

• axes (finger direction) is

normal to finger joint and points to fingertip.

• Easy to define in photograph of

finger, not easy in fingerprint.

Finger center & direction

Red arrows: finger center and direction for arch, loop, and whorl fingerprints Green disk and triangle: singular points

Pose of latent

Pose estimation: face vs finger

Assume face and fingerprint are upright (only center will be estimated)

Pose estimation: learning

Uncertainty about finger center

Assume fingerprint is upright

Most informative patch Entropy: 3.5 bits Least informative patch Entropy: 8.5 bits

• Given a prototype, we are uncertain about finger center
• The uncertainty can be measured by entropy

Entropy of all prototypes

Entropy:

Pose estimation: finger center

Pose estimation: finger direction

Analogous to detecting rotated face in an image

Pose estimation: results

Dictionary lookup

• Goal: find correct orientation patch in as few

as possible candidates

• 3 important designs

– Similarity measure – Patch size – Diversity rule

Size of localized dictionaries

Image value at (, ) is standard deviation of orientation in training samples Image value at (, ) is the size

• f localized dictionary at (, )

Larger orientation deviation corresponds to larger dictionary size.

Dictionary lookup: similarity measure

• Similarity measure should be robust to severe noise.
• The similarity between two patches is defined as

⁄ . : # orientation elements in the initial orientation patch. : # similar orientation elements (difference ≤ 10°).

similarity: 42/75 Initial orientation patch Dictionary orientation patch

Red indicates similar

• rientation elements

Dictionary lookup: diversity

Context-based correction: energy function

After dictionary lookup, we obtain a list of candidate orientation patches Φ,, Φ,, … , Φ, for an initial orientation patch Θ. We use loopy belief propagation to find a set of candidates (shown as red patches),

, , … , , which minimizes energy function ().

Context-based correction: compatibility

• Adjacent patches are overlapped.
• Compatibility between adjacent orientation patches is measured

by the similarity of orientations in the overlapping blocks. High compatibility Low compatibility

Experiments

• Evaluated on NIST Special Database 27, which

has 258 latents and mated rolled fingerprints.

• 2 types of quantitative evaluation

– Accuracy of orientation field estimation – Accuracy of matching enhanced fingerprint

OF error on NIST-27

• Data: NIST-27 and 3 subsets, good (88), bad (85), ugly (85)
• Measure: average Root Mean Square Deviation (RMSD)

from the manually marked orientation fields

Francesco Turroni, Davide Maltoni, Raffaele Cappelli, Dario Maio: Improving Fingerprint Orientation Extraction. IEEE TIFS 2011.

OF error on FVC-onGoing

• FVC-onGoing FOE benchmark is an online evaluation for OF estimation algorithms.
• 2 datasets: good quality (10), bad quality (50); Ground-truth OF marked by human.
• Measure: RMSD between ground-truth and estimated OF

Matching accuracy

Clear gap between GlobalDict and 2 traditional algorithms (FOMFE, STFT) Clear gap between LocalDict and GlobalDict

• Incorporate OF algorithm into a complete fingerprint recognition system, and

evaluate the final matching accuracy.

• To make matching problem more realistic and challenging, 27,000 rolled fingerprints

in NIST SD14 were used as background database.

• Fingerprint is enhanced using OF by 6 methods.
• Same minutiae extraction and matching algorithm (VeriFinger) was used.

基于统计模型的 指纹检测、分割与增强

现场指纹分割

在字典法查询以后，检查每个位置的置信度，基于置信度图 分割：

NIST-27实验结果

实验结果：匹配性能

对多现场指纹的检测

顺序检测，每次移除对前一个姿态投票的方向元：

实验结果：检测

对基于三种方法采集的多现场指纹库进行检测，统计检测的 召回率和查准率：

总结

• 指纹增强对于识别低质量指纹很重要，而

指纹方向场估计是增强的关键。

• 提出局部字典模型对指纹方向场统计特性

进行建模；取得目前最好的方向场估计性 能（NIST27和FVC-onGoing）。

• 对该方法进行扩展，可用于多现场指纹的

检测和分割。

References

1. Jianjiang Feng, Jie Zhou, Anil K. Jain, "Orientation field estimation for latent fingerprint enhancement", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 4, pp. 925-940, 2013. 2. Xiao Yang, Jianjiang Feng, Jie Zhou, "Localized dictionaries based orientation field estimation for latent fingerprints", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 5, pp. 955-969, 2014. 3. Xiao Yang, Jianjiang Feng, Jie Zhou, Shutao Xia, “Detection and segmentation of latent fingerprints”, IEEE International Workshop on Information Forensics and Security (WIFS), pp.1-6, Nov. 2015.