Yang J., Nanni L. (eds.) State of the Art in Biometrics

Подождите немного. Документ загружается.

Gabor-Based RCM Features for Ear Recognition

229

Fig. 4. The magnitude part of gabor representation of an ear image

4.2 Gabor based RCM

We propose a new gabor-based feature mapping function to construct effective and robust

RCM.

k000174

fxyIxygxygxygxy

,, ,

(,) (,) (,) (,)=

⎡

⎤

⎣

⎦

…

(24)

Where

Ixy(,)is the pixel illumination intensity and

(,)

are the gabor representation

of the ear image. By substituting (24) into (2), we have the gabor-based region covariance

matrices in region R

C().

C dimntionality is 43 43

In our method, we represent each ear image with five RCMs extracted from five different

regions

CC(,, )… . First RCM

C()defined over the whole ear image, so it gives us a global

representation of the ear image. Four other RCMs are defined over part of the ear image, so

they give us the part-based representation of the ear image. In order to increase the

robustness of our method against illumination variations, we use both global and part-based

representations for ear images in our method. Figure 5, denotes these five regions for

12345

CCCCC,,,,.

For computing the distance between a gallery RCM and a Probe RCM, we use

GP GP GP GP

ii jj ii jj

i1 i1

GP CC CC CC CC(,)min (,) (,) (,)max(,)

ρρρρρ

⎡⎤

=−=−

⎢⎥

⎣⎦

∑∑

(25)

Where

and

are RCMs from gallery and probe sets.

State of the Art in Biometrics

230

Fig. 5. Five regions for covariance matrices of a sample ear image

Sometimes one local RCM, due to illumination variation or noise, may be affected so much

that make its corresponding distance unreliable. That is the reason why we subtracted the

most unreliable part in (25) from the summation of all distances between gallery and probe

RCMs. We used nearest neighbor classifier with the distance in (25) for our method.

5. Databases

Our method tested on two USTB databases (Yuan et al., 2005). Database 1 includes 180

images of human ear corresponding to 60 individual with three images per person. All the

images in database 1 acquired under standard condition with a little changes. Figure 6,

denotes sample ear images from database 1.

Fig. 6. Sample ear image for two persons from database 1

Database 2 includes 308 images of human ear corresponding to 77 individual with four

images per person. All the images in database 1 acquired under illumination variation and

30 degree pose variations. Figure 7, shows sample ear images from database 2.

Gabor-Based RCM Features for Ear Recognition

231

Fig. 7. Sample ear image for two persons from database 2

6. Experimental result

We performed our experimental studies comparing various ear reconigtion algorithms

including our method with PCA+RBFN method (Zhang & Mu, 2008), ICA+RBFN method

(Zhang & Mu, 2008), Hmax+SVM method (Yaqubi et al., 2008), LSBP method (Guo & Xu,

2008), four RCM-based methods (Tuzel et al., 2007; Pang et al., 2008). In order to compare

the recognition performance of our method with the above methods, we have used USTB

databases (Yuan et al., 2005) in our experiments. In database 1, from a total of 60 persons,

two images per person where randomly used for training. There are three different ways of

selecting two images for training from three images. In database 2, from a total of 77

persons, three images per person where randomly used for training. There are four different

ways of selecting three images for training from four images.

For simplicity, RCM-based methods associated with (9), (10), (11), (12) denote by RCM1,

RCM2, RCM3, RCM4 respectively. RCM3 is a subset of RCM1 with lack of intensity

component; also RCM2 is a subset of RCM4 with lack of intensity component.

Figures 8 and 9 denote the mean of the recognition rates for database 1 and 2 datasets. From

Figures 8 and 9, it can be seen that the recognition performances of four RCM-based

methods were worse than other methods, so it can be concluded that the discrimination

power, in these RCM-based methods are weak for recognition task. To find out about the

intensity parameter

Ixy(( , )) effect on the recognition rate, we compare the result of RCM1

with RCM3 and the result of RCM2 with RCM4. We can conclude that

Ixy(,)is an

important feature in RCMs and it contributes to increasing the recognition performance of

RCM-based methods. Thus, we used the illumination intensity component in our mapping

function to increase the accuracy of our method.

Table 1 shows the comparision of the standard deviation of recognition performance

between all discussed methods on database 1 and 2. From table 1, We can see that the

State of the Art in Biometrics

232

standard deviation of our method for database 1 are low. Therefore, our method showed

better performance than any other methods in database 1. The mean recognition rates of our

method in database 1 and 2 are 93.33% and 87.98% respectively. Due to the pose variations

in database 2 images, the recognition performance of our method, in terms of average

accuracies, outperforms any other methods, except LSBP and ICA methods.

93.33

89.44

88.33

83.33

72.77

74.42

68.33

66.1

75.55

100

Fig. 8. Mean Recognition rates of different methods on database 1 (%)

87.98

89.6

87.98

79.54

69.47

66.55

57.78

56.15

70.44

100

Fig. 9. Mean Recognition rates of different methods on database 2 (%)

Gabor-Based RCM Features for Ear Recognition

233

Methods

Standard Deviation

Database 1 Database 2

Our method 1.67 5.23

LSBP 1.92 4.74

ICA+RBFN 3.33 4.15

PCA+RBFN 3.53 3.07

max

+SVM 1.93 2.70

RCM1 2.58 2.22

RCM2 3.33 4.80

RCM3 2.55 2.72

RCM4 2.54 3.06

Table 1. Standard deviations of the recognition rates

Eventually, these results prove that using Gabor features, as main features in constructing

RCMs, will improve the discrimination ability for recognizing ear images, and it shows

better recognition rate in proportion to previous methods.

7. Conclusion

In this chapter, we proposed gabor-based region covariance matrices for ear recognition. In

this method we form region covariance matrix by using gabor features, illumination

intensity component, and pixel location and utlize it as an efficient ear descriptor. We

compared our method with PCA+RBFN method (Zhang & Mu, 2008), ICA+RBFN method

(Zhang & Mu, 2008), Hmax+SVM method (Yaqubi et al., 2008), LSBP method (Guo & Xu,

2008), and four RCM-based methods (Tuzel et al., 2007; Pang et al., 2008), using two USTB

databases.

Unlike the previous RCM-based methods which have very low recognition rates when

being applied to ear recognition, our RCM-based method, which used gabor features as a

main feature for constructing RCM, showed better result in ear recognition. Potential results

showed that our method achieved improvement, in terms of recognition rate, in proportion

to other methods. Our method obtains the average accuracy of 93.33% and 87.98%,

respectively, on the databases 1 and 2 for ear recognition.

8. References

Abdi, H. & Williams, L. J. (2010), Principal component analysis. Wiley Interdisciplinary

Reviews: Computational Statistics

, Vol. 2, No. 4, pp. 433–459.

Bertillon, A. (1890).

La Photograhie Judiciaire, avec un appendice sur la classification et

l’Identification Anthropometriques

, Gauthier-Villars.

Comon, P. (1994). Independent Component Analysis, A New Concept?.

Signal Processing.

Vol. 36, No. 3, pp. 287-314.

State of the Art in Biometrics

234

Daugman, J.G., (1985). Uncertainty Relation for Resolution in Space, Spatial Frequency and

Orientation Optimized by Two-Dimensional Visual Cortical Filters.

Journal of

Optical Soc. Am.

, Vol. 2, No. 7, pp. 1160-1169.

Forstner, W., & Moonen B. (1999). A metric for covariance matrices.

In Dept geodesy

Geoinform, Stuttgart University

. Stuttgart, Germany: Tech. Rep.

Forsyth, D. A., & Ponce J. (2002).

Computer Vision: A Modern Approach. Prentice Hall.

Guo, Y., & Xu., Zh. (2008). Ear recognition using a new local matching approach.

Proceedings

of IEEE International Conference on Image Processing

Iannarelli, A. 1989.

Ear Identification, Forensic Identification Series, Paramount Publishing

Company, Fremont, California.

Jones, J., & Palmer L. (1987). An evaluation of the two-dimensional Gabor filter model of

simple receptive fields in cat striate cortex.

J. Neurophys. Vol. 58, No. 6, pp. 1233–1258.

Lee, T.S. (2003). Image Representation Using 2D Gabor Wavelets.

IEEE Trans. Pattern

Analysis and Machine Intelligence

, Vol. 18, No. 10, pp. 959-971.

Pang Y., Yuan Y., & Li, X. (2008). Gabor–based region covariance matrices for face

recognition.

IEEE Trans. On Circuits and Systems for Video Technology, Vol. 18, No. 7,

pp. 989–993.

Porikli, F. (2005). Integral Histogram: A fast way to extract histograms in Cartesian spaces.

Proceedings of CVPR. 2005.

Riesenhuber, M. & Poggio, T. (1999). Hierarchical models of object recognition in cortex.

Nat.

Neurosci.

, Vol. 2, No. 11, pp. 1019–25.

Schiele, B., & Crowley J. L. (2000). Recognition without correspondence using

multidimensional receptive field histograms.

Int. J. Comput. Vis. Vol. 36, No. 1, pp.

31–52.

Stone, J. (2005). Independent Component Analysis: A Tutorial Introduction.

The Knowledge

Engineering Review archive.

Vol. 20, No. 2, June 2005.

Tuzel, O., Porikli, F., & Meer, P. (2006). Region covariance: A fast descriptor for detection

and classification.

Proceedings of Eur. Comput. Vision Conference, pp. 589–600.

Tuzel, O., Porikli, F., & Meer, P. (2007). Human detection via classification on Riemannian

manifolds.

Proceedings of IEEE Comput. Vision Pattern Recog. Conference, pp. 1–8.

Veksler, O. (2003). Fast variable window for stereo correspondence by integral images.

Proceedings of CVPR. 2003.

Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple

features.

Proceeding of IEEE Conference on Computer Vision and Pattern Recognition,

Kauai, HI. Vol. 1, pp. 511–518.

Xu, L. (1994). Theories of Unsupervised Learning, PCA and Its Nonlinear Extension.

Proceedings of IEEE International Conference on Neural Network. Olando. USA. pp.

1254-1257.

Yaqubi, M., Faez, K., & Motamed, S. (2008). Ear recognition using features inspired by visual

cortex and support vector machine technique.

Proceedings of IEEE International

Conference on Computer and Communication Engineering

, Kula Lampur, Malaysia.

Yuan, Li, Mu, Zhichun, & Zhengguang, Xu. (2005). Using ear biometrics for personal

recognition.

International Workshop on Biometric Recognition Systems. IWBRS 2005,

pp. 221–228.

Zhang, H., & Mu, Zh. (2008). Compound Structure Classifier System For Ear Recognition.

Proceedings of the IEEE International Conference on Automation and Logistics, Qingdao,

China.

Bi-Modality Anxiety Emotion Recognition

with PSO-CSVM

Ruihu Wang

1,2

and Bin Fang

Chongqing University of Arts and Sciences,

Chongqing University,

China

1. Introduction

In Human Computer Interaction (HCI) community, the ultimate goal which we are striving

to achieve is to create a natural, harmony way of bi-directional communication between

machine and human. As we well known, many machine intelligence applications are based

on machine vision technology, for instance, industrial detection, face recognition, medical

image computer aided diagnose (MICAD), fingerprint recognition, and so on. In terms of

artificial intelligence, it is built upon digital image processing and video frame analyzing to

extract feature information to recognize some interesting objects. Moreover, a high-level

machine learning system should be capable of identifying human emotion states and make

interactions accordingly. Multimodal human emotion recognition involving facial

expression and motion recognition could be applied to intelligent video surveillance system

to provide an early warning mechanism in case of potential unsafe action occurring. There is

no doubt that the ever increasing various kinds of crimes in our modern society which make

the living environment around us even worse, demand for an intelligent and automatic

security precautions measures to offer people a more convenient, relaxed living conditions.

Meanwhile, automatic intelligent video-based surveillance system has received a lot of

interest in the computer vision and human computer interaction community in recent years.

CMU’s Video Surveillance and Monitoring (VSAM) project [26] and MIT AI Lab’s Forest of

Sensors project [27] are examples of recent research efforts in this field. As a matter of fact,

the safeguard has to keep watch on lots of screens in control center in real application. The

video displayed on the screens are captured from cameras which are distributed in various

security-sensitive areas such as elevator, airports, railway station or public places. However,

because of human’s inherent information processing limitation, it is impossible to pick up all

of the useful information from the monitors at the same time properly and spontaneously.

That means some potentially dangerous information could be missed out. We expect the

human computer interaction system is able to take the information-processing burden off

the human. An ideal and effective intelligent surveillance system should work automatically

without or with minimal human intervention. In addition, we believe that an intelligent

surveillance system should be capable of preventing and predict criminal occurring by

biometric recognition, rather than identifying the suspect after attacks happened. Figure 1

shows some pictures in which the subjects are under the anxiety or stress emotion state

when she interviewed with human resource manager, not criminal nevertheless.

State of the Art in Biometrics

236

Fig. 1. Anxiety or stress emotion representation

A number of universities and research groups, commercial companies are conducting

meaningful projects and have made significant progress in visual surveillance monitoring

system. The Safehouse Technology Pty Ltd in Australia developed The Clarity Visual

Surveillance System (CVSS)[28], which provides security professionals with the next

generation in visual surveillance management. Although state-of-the-art computer vision

technology and artificial intelligence algorithm were used, the system did not integrate

affective computing methods in it yet. Picard defined “Affective Computing” as: computing

that relates to, arises from, or deliberately influences emotions. Affective computing

expands human-computer interaction by including emotional communication together with

appropriate means of processing affective information [29]. In affective computing research,

a variety of input signals like visual, verbal, touch/wearable computing, etc, have been used

into emotion communication frequently in most cases. However, visual channel signal,

which involves facial expression and gesture motion would be considered only in our

surveillance system. It is a typical non-intrusive, intelligent analyzing technology and easily

to be implemented. It does not require the subject to comply with some requirement he/she

probably won’t to meet, for example, iris recognition, fingerprint recognition and wearable

device. In a survey of hundreds of US security executives, Buxton[1] pointed out that system

which could process the video from the increasing number of cameras were “one of the top

items in demand”. We believe that visual surveillance based on emotion perception and

recognition is the next generation of intelligent monitoring system. More importantly, this

system can be capable of supervising individuals in specific environment to carry out data

analysis and recommend possible interventions.

2. Previous work

Psychological research findings suggest that humans make judgment action depend on the

combined visual modalities of face and body more effective than any other channel [18].

Since Paul Ekman and Frisen[3] divided human emotion into six primary categories:

happiness, sadness, disgust, angry, surprise, fear, there has been a great amount of research

on facial expression recognition. Eckman revealed that the facial expression showed the

inside emotional state and the specific sense at that time, which was hardly controlled by

human artificially. In automatic facial expression recognition, feature extraction and

classifier design are two major procedures. As shown in Table 1, the most frequently being

used feature extraction method is Gabor wavelet feature. A subset of these filters is chosen

using AdaBoost, which is transmitted for training SVM as a reduced feature representation.

A wide range of surveillance systems have been developed for different applications. G. Lu,

X. Li, H. Li proposed a surveillance system for nurses to distinguish the neonatal pain

expression from non-pain expression automatically using Gabor wavelet transform and

support vector machine. They reported 85.29% recognition rate of pain versus non-pain [2].

The Safe-house Technology Pty Ltd in Australia developed Clarity Visual Surveillance

System. It employs state-of-the-art computer vision algorithm and artificial intelligence,

whereas it did not involve affective computing technology and emotion recognition in it yet.

Bi-Modality Anxiety Emotion Recognition with PSO-CSVM

237

Bouchrika introduced gait analysis for visual surveillance considering that the identification

of the individuals who are suspected of committing crimes is more important than predict

when a crime is about to happen [15]. P. Rani, N.Sarkar and J.Adams built an anxiety-

recognition system capable of interpreting the information contained in physiological

signals processes to predict the probable anxiety state [17]. In [18] H.Kage et.al introduced

pattern recognition technologies for video surveillance and physical security. Their system

detects the occurrence of a relevant action via image motion analysis. Optical-flow is used to

analyze motion and AdaBoost is been for face detection. In [18], H.Gunes and M.Piccardi

presented an approach to automatic visual recognition of expressive face and upper-body

gestures from video sequences which are suitable for human communicative behavior. They

defined some rules for facial expression and body motion recognition respectively to make

right decision firstly. Min-max analysis method is used to detect the eyebrows, eyes, mouth

and chin by evaluating the topographic gray level relief. Body feature is extracted by using

traditional image processing methods such as background subtraction and dilation.

In order to improve the accuracy of classifiers and provide fast, pertinent response, many

researchers proposed optimized approaches. Typically Genetic Algorithm or Particle Swarm

Optimization is often used for feature selection and parameters optimization [19,20,21,22].

In our work, the key problems are facial expression, head motion and hand gesture analysis.

We also care more about run-time consumption which impacts the recognition efficiency.

Feature Extraction Methods Classifier design

Optimized Feature

Selection

Gabor wavelet[2,4,5,6,10,16]

Optical Flow[7], PCA[12]

FLD, Eigenfaces[9],

AdaBoost[10,12,13],LBP[13]

Hide Markov Model [11]

Support Vector Machine[2,6,7,8],

Artificial Neural Network[4,5],

Bayesian Network[6,16],

AdaBoost[12,13]

AdaSVM[6],

MIFS[16]

Table 1. Overview of methods used in facial expression recognition

3. Methods

3.1 System framework

A visual automated surveillance system consists of three main phases: face and body motion

detection, facial feature and motion feature extraction, classification and recognition, as

shown in Figure 2. By means of sensitive facial expression extraction, the subject’s intention

and prospective behaviour are analyzed to report any suspicious expression or activities to

the control central. The system would be able to reduce potential crimes by recognizing

suspicious individuals’ emotion state ahead of security threats happening.

The front end inputs involve three different parts: (1)static facial image database input;

(2)static face image database input, and (3) real face image detection captured by cameras

using image sequence analysis. All of these three channels have to be passed through the

facial expression feature extraction procedure. AdaBoost, Optical Flow and Gabor feature

can be used to extract facial expression feature. In the middle of the system framework, both

automatic facial expression recognition and human motion recognition are implemented

through classifier learning and test, which involve PSO-SVMs feature extraction and

parameters optimization. In our system, we use cascaded SVM architecture combined with

particle swarm optimization algorithm to train and test SVM to get an optimized classifier

which runs faster in computational-consuming conditions.

State of the Art in Biometrics

238

Fig. 2. System Framework Schematic of Human Motion Recognition

Fig. 3. Bi-Modality Fusion Affective recognition