电子信息工程专业英语翻译清华出版社English for IT and EE-12

第二章

信息科学与电子工程专业英语

Technical EnglishFor Information Science and Electronic Engineering

第二章

信息科学与电子工程专业英语

Unit 12Biometrics Technology

第二章

信息科学与电子工程专业英语

Part IFingerprint Identification

第二章

New Wordsverification 确认 module 模块

biometrics 生物统计学ridge 脊 minutia 细节(minutiae) orientation 方向 translation 平移

immutable 不可变更的furrow 沟，皱纹，辙 bifurcation 分叉 registration 对准 Euclidean distance 欧几里德距离

robust 稳健的，鲁棒的pool 共享，汇聚

authentication 认证，确认field-test 现场测试，实地测试

forensic 法医的，司法取证the literature 文献(总称)

subset 子集indexing mechanism 索引机制3

第二章

1Among all the biometric techniques, fingerprint-basedidentification is the oldest. Everyone is known to have unique,

immutable fingerprints. A fingerprint is made of a series ofridges and furrows on the surface of the finger.

一系列峰谷

4

第二章

1The uniqueness of a fingerprint can be determined by thepattern of ridges and furrows as well as the minutiae points.

Minutiae points are local ridge characteristics that occur ateither a ridge bifurcation or a ridge ending.

指纹的细节点是指纹局部凸起处的 一些特性，这些特性出现在凸起的 分叉处或是凸起的截止处。

5

第二章

2Fingerprint matching techniques can be placed into twocategories: minutiae-based and correlation based. Minutiae-

based techniques first find minutiae points and then map theirrelative placement on the finger as shown in Figure 12.1.

6

第二章

2However, there are some difficulties when using this approach.It is difficult to extract the minutiae points accurately when

the fingerprint is of low quality. Also this method does nottake into account the global pattern of ridges and furrows.

峰谷的整体形状

7

第二章

2The correlation-based method is able to overcome some of thedifficulties of the minutiae-based approach. However, it has

some of its own shortcomings. Correlation-based techniquesrequire the precise location of a registration point and are affected by image translation and rotation. 图像平移

8

第二章

3Fingerprint matching based on minutiae has problems inmatching different sized (unregistered) minutiae patterns.

Local ridge structures cannot be completely characterized byminutiae.

9

第二章

3We can try a different representation of fingerprints that willcapture more local information and yield a fixed length code

for the fingerprint. The matching will then hopefully become arelatively simple task of calculating the Euclidean distance between the two codes.

10

第二章

4It is important to develop algorithms that are more robust tonoise in fingerprint images and deliver increased accuracy in

real-time.1

研发对于指纹图像中噪声更稳健 并能实时提供更高精度的算法是 重要的。

11

第二章

4A commercial fingerprint-based authentication sys

temrequires a very low false rejection rate (FRR) for a given false

acceptance rate (FAR).2

商用指纹(身份)认证系统对 给定的错误接受率要求具有很 低的错误拒绝率。

12

第二章

4This is very difficult to achieve with any single technique. Wecan pool evidence from various matching techniques to

increase the overall accuracy of the system. In a realapplication, the sensor, the acquisition system and the variation in performance of the system over time is critical.3 To evaluate the system performance, field-test on a limited number of users over a period of time is necessary.

为了评价系统性能，我们 有必要对少数使用者在一 段时间内进行现场试验

在实际应用中，传感器、 采集系统、性能随时间的 变化是关键因素。13

第二章

5Large volumes of fingerprints are collected and storedeveryday in a wide range of applications including forensics,

access control, and driver license registration. An automaticrecognition of people based on fingerprints requires that the input fingerprint be matched with a large number of fingerprints in a database.

14

第二章

5To reduce the search time and computational complexity, it isdesirable to classify these fingerprints in an accurate and

consistent manner so that the input fingerprint is required tobe matched only with a subset of the fingerprints in the database.4

为了缩短搜索时间、降低计算复杂度， 要以准确而一致的方式将这些指纹分 类，从而使输入的指纹只需与数据库 某一子集中的指纹进行比对。15