Statistical Biometric Methods

2016

visibility

…

description

23 pages

link

1 file

Abstract: Biometric systems have been researched intensively by many organization. It overcomes the conventional security systems by identify ―who you are‖. This paper discusses the current image based biometric systems. It first gives some information about why biometric is needed and what should people look for in biometric systems. Several popular image based biometric systems have been examined in this paper. The technique used in each system for data acquisitions, feature extraction and classifiers are briefly discussed. The biometric systems included are face, fingerprint, hand geometry, hand vein, iris, retina and signature; here also describe the statistical approaches of biometrics. The paper concludes by examining the benefits of multi-modal biometric systems, it is found that there is no one good biometric systems each have its advantages and disadvantages and the performance of each biometric system is summarized.

Figures (26)

Same as many recognition systems, a general biometric system can consists of following sections, data collection, transmission, signal processing storage and decision [3], see Figure 1. It can considered that each section function independently, and errors can be introduced at each point in an additive way. Figure 1. Generalized biometric system. Data collection consists of sensors to obtain the raw biometric of the subject, and can output one or multidimensional signal. Usually, data are obtained in a normalized fashion, fingerprints are moderately pressed and rotation is minimized, faces are obtained in frontal or

One of the oldest biometric techniques is the fingerprint identification. Fingerprints were used as a means of positively identifying a person as an author of the document and are used in law enforcement. Fingerprint recognition has a lot of advantages, a fingerprint is compact, unique for every person, and stable over the lifetime. A predominate approach to fingerprint technique is the uses of minutiae [8], see Figure 2. Figure 2. Minutiae, ridge endings and ridge bifurcations.

Figure 3. Typical fingerprint feature extraction algorithm. The feature extraction first binarizes the ridges in a fingerprint image using masks that are capable of adaptively accentuating local maximum gray-level values along a direction normal to ridge direction [10]. Minutiae are determined as points that have one neighbor or more than two neighbors in skeletonized image [10].

Figure 4. The ROC curve comparison. Other enhancement algorithm such as_ preprocessing, mathematic algorithm and etc, have been discussed by [12], [13] and [14].

The Local Features are also known as Minutia Points. They are the tiny, unique characteristics of fingerprint ridges that are used for positive identification. It is possible for two or more individuals to have identical global features but still have different and unique fingerprints because they have local features - minutia points - that are different from those of others.

Fingerprint classification is a technique to assign a fingerprint into one of the several pre-specified types already established in the literature which can provide an indexing mechanism. Fingerprint classification can be viewed as a coarse level matching of the fingerprints. An input fingerprint is first matched at a coarse level to one of the pre-specified types and then, at a finer level, it is compared to the subset of the database containing that type of fingerprints only. We have developed an algorithm to classify fingerprints into five classes, namely, whorl, right loop, left loop, arch, and tented arch.

Table 2. Measurements for feature extraction. Figure 6. a) Location of measurement point for feature extraction, b) details of the deviation measurement.

Figure 5. Prototype design a) platform and camera, b) placement of user’s hand, c) photograph taken

Table 3. Thermographic image procedures It is noted that significant horizontal positional noise during docking for different registration process [17]. The proposed matching approach compares medial axis and coding algorithm, constrained sequential correlation. It is a variation on the traditional correlation methods used for template matching. The reference or library signature is first dilated by a hexagonal structuring element. The test signature is then superimposed on this reference buffer and the percentage of pixels contained within the buffer determined. Due to horizontal translation error, test signature is sequentially translated horizontally and compared against the reference buffer [17]. The horizonta translation is limit to + 30 pixels. The highest match percentage is said to be the forward similarity, where reverse similarity is obtained by dilate the test signature and reference signature is sequentially correlated until the maximum measure is obtained. By setting the forward and reverse minimum percentage to 75% and 60% respectively, the resultant FRR is 7.5% and FAR is 0%. If forward

Figure 7. Left is original captured image, right is vein structure after prune the medial axis percentage is lowered to 70%, FRR improved down to 5% and FAR remains the same [17].

interpolation and modified median filter to obtain hand vein in region of interest (ROI) [18]. The Gaussian low pass filter is a3 x 3 spatial filter with equation, Due to heavy computation load [18] introduce a way of enhancing the algorithm. Both the coefficients for the Gaussian low pass filter and the low pass filter are designed to have 7-tap CSD (canonical signed digit) codes at the maximum. Also, for the normalization, the decimation method is used. It is said that, CSD code is an effective code for designing a FIR filter without a multiplier. The proposed preprocessing algorithm follows the same steps as the conventional method, except that the coefficients for each filter are made of CSD codes. The general CSD code is equal to,

Figure 8. (a) Iris image (b) iris localization (c) unwrapped texture image (d) texture image after enhancement Another biometric non-invasive system is the use of color ring around the pupil on the surface of the eye. Iris contains unique texture and is complex enough to be used as a biometric signature. Compared with other biometric features such as face and fingerprint, iris patterns are more stable and reliable. It is unique to people and stable with age [19]. Figure 8, shows a typical example of an iris and extracted texture image.

Figure 9. a) Dougman system, top 8 circular band, bottom iris code b) demodulation code

Figure 7. Retinal scanned image The light source must be directed through the cornea of the eye, and operation of the retina scanner is not easy. However, in healthy individuals, the vascular pattern in the retina does not change over the course of an individual’s life [24]. Although retina scan is more susceptible to some diseases than the iris scan, but such diseases are relatively rare. Due to its inherent properties of not user-friendly and expansive, it is rarely used today. A typical retinal scanned image is shown in Figure 7.

Retina: kind of living passport or a living password that one need not remember but one always carries along. The iris’s random patterns are unique to each individual — a human “bar code” or living passport. No two irises are alike. Each person has a distinct pattern of filaments, pits and striations in the colored rings surrounding the pupil of each eye. This pattern is stable throughout life. Unlike fingerprints, iris “prints” are not su bject to environmental damage. An internal organ, the iris is protected by the cornea. Because these structures are identified with a hig away. transparent, the iris can be easily h degree of certainty up to three feet

Fast algorithm for Euclidean distance transform is applied. For each candidate vessel point, the resulting distance map contains the distance to its nearest background pixel and the position of that background pixel [25]. The pruning operation uses two measures, ¢ and d, to quantify the likelihood of a vessel candidate being a center line pixel of a curvilinear band of limited width, see Figure 8. Figure 8. Quantities for testing curvilinear bands. where p and n represent a vessel candidate and one of the eight neighbors from its neighborhood N,, respectively, e, and e, are their corresponding nearest background pixel. The two measures are defined by,

Figure 9. Proposed approach versus global thresholding. Signature:

Figure 10. a) Directional matrix b) Signature c) Apply matrix to obtain direction vector = [5 45 7]

Figure 11. Function x(t) after wavelet transform. Each zero-crossing of the detail curve at the 4" level of resolution (this level was chosen empirically, by trial and error), three parameters are extracted: its abscissa, the integral between consecutive zero-crossings,

The aim in multivariate decision tree construction is to find a way to determine the coefficients of the attributes. In this chapter, we will discuss how to determine these set of coefficients by using methods based on neural networks. When neural networks are used in decision trees, at each node of the decision tree, there is a neural network trained with its corresponding data. Once the weights of the neural networks are found, they can be used to classify a test example. Figure15 Linear perceptron model for multivariate decision trees A model for a linear perceptron is shown in Figure 0.1 (Bishop, 1996). xox; x2 ... x, form the input layer of the neural network whereas the node on top is the output node

A multilayer perceptron model for decision making at a node is shown in Figure 0.1. figure 16Multilayer perceptron model with one hidden layer

Figurel7 A nonlinear split to Choosing Car problem Multilayer perceptron models differ from other multivariate models in its nonlinear nature. With this model one can have nonlinear split at a decision node. In Figure 0.2, an example nonlinear split is shown to solve the problem Choosing Car. The Hybrid Model: