522

IEEE Transactions on Consumer Electronics, Vol. 58, No. 2, May 2012

An Embedded Real-Time Finger-Vein Recognition System for Mobile Devices Zhi Liu and Shangling Song Abstract — With the development of consumer electronics, the demand for simple, convenient, and high-security authentication systems for protecting private information stored in mobile devices has steadily increased. In consideration of emerging requirements for information protection, biometrics, which uses human physiological or behavioral features for personal identification, has been extensively studied as a solution to security issues. However, most existing biometric systems have high complexity in time or space or both, and are thus not suitable for mobile devices. In this paper, we propose a real-time embedded finger-vein recognition system for authentication on mobile devices. The system is implemented on a DSP platform and equipped with a novel finger-vein recognition algorithm. The proposed system takes only about 0.8 seconds to verify one input fingervein sample and achieves an equal error rate (EER) of 0.07% on a database of 100 subjects. The experimental results demonstrate that the proposed finger-vein recognition system is qualified for authentication on mobile devices. 1 Index Terms — finger-vein recognition; biometrics; mobile devices; DSP

I. INTRODUCTION Private information is traditionally provided by using passwords or Personal Identification Numbers (PINs), which are easy to implement but is vulnerable to the risk of exposure and being forgotten. Biometrics, which uses human physiological or behavioral features for personal identification, has attracted more and more attention and is becoming one of the most popular and promising alternatives to the traditional password or PIN based authentication techniques [1]. Moreover, some multimedia content in consumer electronic appliances can be secured by biometrics [2]. There is a long list of available biometric patterns, and many such systems have been developed and implemented, including those for the face, iris, fingerprint, palmprint, hand shape, voice, signature, and gait. Notwithstanding this great and increasing variety of biometrics patterns, no biometric has yet been developed that is perfectly reliable or secure. For example, fingerprints and palmprints are usually frayed; voice, signatures, hand shapes and iris images are easily forged; face 1 This work was supported in part by the National Natural Science Foundation of China (No.60902068), Shandong Provincial Natural Science Foundation (No.2009ZRB019RX) and Technology Development Program of Shandong Province (No. 2010GGX10125). Zhi Liu is with the School of Information Science and Engineering, Shandong University, Jinan, 250100, China (e-mail: [email protected]).

Contributed Paper Manuscript received 11/27/11 Current version published 06/22/12 Electronic version published 06/22/12.

recognition can be made difficult by occlusions or face-lifts [3]; and biometrics, such as fingerprints and iris and face recognition, are susceptible to spoofing attacks, that is, the biometric identifiers can be copied and used to create artifacts that can deceive many currently available biometric devices. The great challenge to biometrics is thus to improve recognition performance in terms of both accuracy and efficiency and be maximally resistant to deceptive practices. To this end, many researchers have sought to improve reliability and frustrate spoofers by developing biometrics that are highly individuating; yet at the same time, present a highly complex, hopefully insuperable challenge to those who wish to defeat them [4]. Especially for consumer electronics applications, biometrics authentication systems need to be cost-efficient and easy to implement [5]. The finger-vein is a promising biometric pattern for personal identification in terms of its security and convenience [6]. Compared with other biometric traits, the finger-vein has the following advantages [7]: (1) The vein is hidden inside the body and is mostly invisible to human eyes, so it is difficult to forge or steal. (2) The non-invasive and contactless capture of finger-veins ensures both convenience and hygiene for the user, and is thus more acceptable. (3) The finger-vein pattern can only be taken from a live body. Therefore, it is a natural and convincing proof that the subject whose finger-vein is successfully captured is alive. We designed a special device for acquiring high quality finger-vein images and propose a DSP based embedded platform to implement the finger-vein recognition system in the present study to achieve better recognition performance and reduce computational cost. The rest of this paper is organized as follows. An overview of the proposed system is given in Section 2. The device for finger-vein image acquisition is introduced in Section 3. Our recognition method is addressed in Section 4. Experimental results are then presented in Section 5. Finally, concluding remarks are given in Section 6.

II. OVERVIEW OF THE SYSTEM The proposed system consists of three hardware modules: image acquisition module, DSP mainboard, and humanmachine communication module. The structure diagram of the system is shown in Fig. 1. The image acquisition module is used to collect finger-vein images. The DSP mainboard including the DSP chip, memory (flash), and communication port is used to execute the finger-vein recognition algorithm

0098 3063/12/$20.00 © 2012 IEEE

Z. Liu and S. Song: An Embedded Real-Time Finger-Vein Recognition System for Mobile Devices

and communicate with the peripheral device. The humanmachine communication module (LED or keyboard) is used to display recognition results and receive inputs from users.

Fig.1. The hardware diagram of the proposed system. Input finger-vein images with corresponding ID

Input finger-vein images with corresponding ID

Segmentation and Alignment

Segmentation and Alignment

Enhancement

Enhancement

Feature Extraction

Feature Extraction

Feature Templates

Matching

No

523

Our device mainly includes the following modules: a monochromatic camera of resolution 580 × 600 pixels, daylight cut-off filters (lights with the wavelength less than 800 nm are cut off), transparent acryl (thickness is 10 mm), and the NIR light source. The structure of this device is illustrated in Fig. 3. The transparent acryl serves as the platform for locating the finger and removing uneven illumination. The NIR light irradiates the backside of the finger. In [9], a light-emitting diode (LED) was used as the illumination source for NIR light. With the LED illumination source, however, the shadow of the finger-vein obviously appears in the captured images. To address this problem, an NIR laser diode (LD) was used in our system. Compared with LED, LD has stronger permeability and higher power. In our device, the wavelength of LD is 808 nm. Fig. 4 shows an example raw finger-vein image captured by using our device.

Reject

Yes

Accept

Fig. 3. Illustration of the imaging device.

Fig.2. The flow-chart of the proposed recognition algorithm.

The proposed finger-vein recognition algorithm contains two stages: the enrollment stage and the verification stage. Both stages start with finger-vein image pre-processing, which includes detection of the region of interest (ROI), image segmentation, alignment, and enhancement. For the enrollment stage, after the pre-processing and the feature extraction step, the finger-vein template database is built. For the verification stage, the input finger-vein image is matched with the corresponding template after its features are extracted. Fig. 2 shows the flow chart of the proposed algorithm. Some different methods may have been proposed for finger-vein matching. Considering the computation complexity, efficiency, and practicability, however, we propose a novel method based on the fractal theory, which will be introduced in Section 4 in detail. III. IMAGE ACQUISITION To obtain high quality near-infrared (NIR) images, a special device was developed for acquiring the images of the fingervein without being affected by ambient temperature. Generally, finger-vein patterns can be imaged based on the principles of light reflection or light transmission [8]. We developed a finger-vein imaging device based on light transmission for more distinct imaging.

Fig. 4. An example raw finger-vein image captured by our device.

IV. PROPOSED ALGORITHM A. Image Segmentation and Alignment Because the position of fingers usually varies across different finger-vein images, it is necessary to normalize the images before feature extraction and matching. The bone in the finger joint is articular cartilage. Unlike other bones, it can be easily penetrated by NIR light. When a finger is irradiated by the uniform NIR light, the image of the joint is brighter than that of other parts. Therefore, in the horizontal projection of a finger-vein image, the peaks of the projection curve correspond to the approximate position of the joints (see Fig.

524

IEEE Transactions on Consumer Electronics, Vol. 58, No. 2, May 2012

5). Since the second joint of the finger is thicker than the first joint, the peak value at the second joint is less prominent. Hence, the position of the first joint is used for determining the position of the finger.

Fig. 5. Horizontal projection of the raw image.

B. Image Enhancement The segmented finger-vein image is then enhanced to improve its contrast as shown in Fig. 7. The image is resized to 1/4 of the original size, and enlarged back to its original size. Next, the image is resized to 1/3 of the original size for recognition. Bicubic interpolation is used in this resizing procedure. Finally, histogram equalization is used for enhancing the gray level contrast of the image. C. Feature Extraction The fractal model developed by Mandelbrot [10] provides an excellent method for representing the ruggedness of natural surfaces and it has served as a successful image analysis tool for image compression and classification. Since different fractal sets with obviously different textures may share the same fractal dimension [11], the concept of lacunarity is used to discriminate among textures. The basic idea of lacunarity in many definitions is to quantify the “gaps or lacunae” presented in a given surface, which is used to quantify the denseness of a surface image. In this study, we focus on combining fractal and lacunarity measures for improving finger-vein recognition. Let f  g (i, j ), i  0,1, , k , j  0,1, , l , where f denotes an image with k  l pixels, and g  i, j  means the gray level value at the  i , j  pixel. The gray level surface of g  i , j  can be viewed as a fractal [12]. First, for g  i , j  , u0  i , j   b0  i, j   g  i, j  . Second, for   1, 2,3, , the

blanket surface is defined as follows:

 

u  i , j   max u 1  i , j   1,

Fig. 6. The segmented ROI of the finger-vein image.

The alignment module includes the following steps. First, the part between the two joints in the finger-vein image is segmented based on the peak values of the horizontal projection of the image. Second, a Canny operator with locally adaptive threshold is used to get the single pixel edge of the finger. Third, the midpoints of finger edge are determined by edge tracing so that the midline can be obtained. Fourth, the image is rotated to adjust the midline of the finger horizontally. Finally, the ROI of the finger-vein image is segmented according to the midline (see Fig. 6).

b  i , j   min b 1  i , j   1,

max

 m , n   i , j  1

min

 m , n   i , j  1

 

u 1  m, n 

b 1  m, n

(1)

which ensures that the upper surface u is above u 1 and also at a distance of at least 1 from u 1 in the vertical direction. The profile of u and b do not change when

 increases to  n . The volume of the blanket v can be computed by v 

 (u (i, j)  b (i, j))

(2)

i, j

The surface area a measured with the radius



calculated by

a   v  v 1  / 2

(3)

Let a    be the surface area of the blanket. Considering the Minkowski dimension [13], if  is sufficiently small, we have 2 D

a ( )  F  (4) where F is a constant, and D stands for the fractal dimension (FD) of the image. Two values of  , i.e. 1 and  2 ,

are

used

to

2 D

a1  F 1 Fig. 7. The procedure of our method for image enhancement.

deduce

a1

a 2

compute and



12 D

FD,

a 2  F  2

 2 2 D

2 D

then .

we

can

get

Thus,

we

can

, and take the logarithm at both

Z. Liu and S. Song: An Embedded Real-Time Finger-Vein Recognition System for Mobile Devices

sides to yield: D  2

log 2 a1  log 2 a 2 log 2 1  log 2  2

(5)

  u (i, j )  max u 1 (i, j)  1, max {u 1 (m, n), u 1 (i  2, j )} ( m,n) (i , j ) 1     b (i, j )  min b 1 (i, j )  1, min {b 1 (m, n), b 1 (i  2, j )} ( m,n) (i , j ) 1   (6)

D. Lacunarity Based on Blanket Technique Lacunarity is another concept introduced by Mandelbrot to quantify the gaps in texture images. It is a measure for spatial heterogeneity. Visually different images sometimes may have similar values for their fractal dimensions. Lacunarity estimation can help distinguish such images. Lacunarity can be defined quantitatively as the mean-square deviation of the fluctuations of mass distribution function divided by its square mean. It is also defined as the width of the mass distribution function of a set of points, given the ‘‘box size’’ [15]. Thus, a higher value of lacunarity implies more heterogeneity, as it means a wider mass distribution function, or a larger number of different mass values, of the set of points [16]. A lacunarity value is assigned for the center pixel of the image window, and the lacunarity value of each pixel in an image can be obtained by moving the W  W window throughout the whole image. In our method, lacunarity is computed based on the blanket method [17]. The image d (i, j ) is obtained according to

gray values are gv on the surface of d . The first and second moments of this distribution are then determined as

 d (i, j) p  d (i, j)  i, j

2

M 

  d (i, j)  i, j

2

p  d (i, j ) 

  M  1

2

(9)

E. Matching The blanket dimension distance HD between two fingervein patterns and the lacunarity distance H  are defined as 4

HD 

D  (i, j )  D  (i, j )   1

2

(10)

2 i, j 4

H 

  (i, j )    (i, j )   1

2

(11)

2 i, j

In our method, the dimension and lacunarity features are combined for finger-vein recognition: if HD  th1 and H   th 2 ( th1 and th 2 are thresholds), then the two fingervein patterns are considered to be from the same finger; if HD  th1 or H   th2 , they are considered to be from different fingers. V. EXPERIMENTAL RESULTS A. Dataset To the best of our knowledge, is no public finger-vein image database has yet been introduced. Therefore, we constructed a finger-vein image database for evaluation, which contains finger-vein images from 100 subjects (55% male and 45% female) from a variety of ethnic/racial ancestries. The ages of the subjects were between 21 years old and 58 years old. We collected finger-vein images from the forefinger, middle finger, and ring finger of both hands of each subject. Ten images were captured for each finger at different times (summer and winter). Therefore, there were a total of 6,000 finger-vein images in the database. Fig. 8 shows some example finger-vein images (after preprocessing) from different fingers.

(7)

Let p ( gv) be the probability of the intensity points whose

M1 

Thus, lacunarity can be computed by 2  2 1  M  M     

Peleg [14] discussed the factors affecting shrinking rate. When high gray level stands for white, the min operator of (1) will shrink the light regions corresponding to the particles, and the rate of this shrinking will only depend on the shape properties of the high gray level object. The max operator of (1), however, will shrink the background regions, and the rate of this shrinking will mainly be affected by the distribution of the high gray level object. In the case of finger-vein images, due to the directionality of the finger-vein, blanket growth can be made by directional maximizing (or minimizing) in the asymmetrical neighborhood instead of the symmetrical circular neighborhood. Considering the shape of the fingervein pattern, we modified (1) as follows, which can improve the rate of the shrinking and reveal the directional characteristics of the finger vein pattern.

d (i, j )  u (i, j )  b (i, j )

525

(8)

Fig. 8. Finger-vein images from different fingers after preprocessing

B. Performance Evaluation There are two types of errors in matching results in biometric verification. The first is false rejection, which claims a genuine pair as impostor, and the second is false acceptance, which claims an impostor pair as genuine. These two types of errors are in a trade-off relationship. In

526

IEEE Transactions on Consumer Electronics, Vol. 58, No. 2, May 2012

biometrics, the performance of a system is evaluated by the EER (equal error rate). The EER is the error rate when the FRR (false rejection rate) equals the FAR (false acceptance rate) and is, therefore, suitable for measuring the overall performance of biometric systems because the FRR and FAR are treated equally.

Fig. 10. The FAR and FRR curves of the method combining the blanket dimension and lacunarity.

(a)

(b)

C. Comparison with Previous Methods Miura et al. [19] used a database that contained 678 different infrared images of fingers. These images were obtained from persons working in their laboratory aged 20 to 40, approximately 70% of whom were male. Song’s [20] finger-vein image dataset contained 1,125 images collected using an infrared imaging device they built. Nine images were taken for each of 125 fingers. Compared with these databases, ours is larger and the data-collection interval is longer. Thus, our database is more challenging. Moreover, our system is implemented on a general DSP chip. Table 1 shows that the average times required for feature extraction and matching in our system are 343 ms and 13 ms, respectively. For the whole system, plus the time for image capturing, the time required for the authentication of a user is less than 0.8 s. Although the feature extraction in our system is a little bit more complicated than that in Song's method, our system achieves an EER of 0.07%, indicating that our method significantly outperforms previous methods.

Fig. 9. The FAR and FRR curves of the methods based on (a) blanket dimension and (b) lacunarity, respectively.

The curves of FRR and FAR were used to evaluate the performance of our proposed method. Fig. 9 shows the FAR and FRR curves corresponding to the two methods based on blanket dimension and lacunarity, respectively. From Fig. 9, it can be seen that the EER of the two methods are 0.155% and 0.146%, which are similar. However, when the two kinds of features are combined, the ERR is decreased to 0.07%, as shown in Fig. 10. Because the proposed finger-vein recognition system is targeted for application in mobile devices, according to [18] the energy efficiency of the system is very important. When the proposed system is idle, the power consumption of DSP is about 42.72 milliwatts (mW), and the power consumption of the whole system is under 70 mW in standby mode. In other words, the system can maintain a standby state for six days, with a typical mobile setting of four batteries with 2300 milliamperes per hour. In full active model, the power consumption of the aforementioned model is 1636.4 mW. On average, the actual power consumption of the proposed system is no more than 1.5 watts. The lower power consumption of the proposed system means that it is very efficient and is thus very suitable for mobile consumer electronic devices.

Method

TABLE 1 RECOGNITION RATE AND RESPONSE TIME Time Sample number EER #finger (*#image Feature (%) Matching per finger) extraction 600(*10) 0.07 343 ms 13 ms

Our method Miura’s method [19] Song’s method [20]

678(*2)

0.145

450 ms

10 ms

125(*9)

0.25

118 ms

88 ms

VI. CONCLUSION The present study proposed an end-to-end finger-vein recognition system based on the blanket dimension and lacunarity implemented on a DSP platform. The proposed system includes a device for capturing finger-vein images, a method for ROI segmentation, and a novel method combining blanket dimension features and lacunarity features for recognition. The images from 600 fingers in the dataset were taken over long time interval (i.e., from summer to winter) by a prototype device we built. The experimental results showed that the EER of our method was 0.07%, significantly lower than those of other existing methods. Our system is suitable for application in mobile devices because of its relatively low computational complexity and low power consumption.

Z. Liu and S. Song: An Embedded Real-Time Finger-Vein Recognition System for Mobile Devices

REFERENCE [1] [2] [3] [4] [5] [6] [7] [8] [9]

[10] [11] [12] [13] [14]

A. K. Jain, S. Pankanti, S. Prabhakar, H. Lin, and A. Ross, “Biometrics: a grand challenge”, Proceedings of the 17th International Conference on Pattern Recognition (ICPR), vol. 2, pp. 935-942, 2004. P. Corcoran and A. Cucos, “Techniques for securing multimedia content in consumer electronic appliances using biometric signatures,” IEEE Transactions on Consumer Electronics, vol 51, no. 2, pp. 545-551, May 2005. Y. Kim, J. Yoo, and K. Choi, “A motion and similarity-based fake detection method for biometric face recognition systems,” IEEE Transactions on Consumer Electronics, vol.57, no.2, pp.756-762, May 2011. D. Wang , J. Li, and G. Memik, “User identification based on fingervein patterns for consumer electronics devices”, IEEE Transactions on Consumer Electronics, vol. 56, no. 2, pp. 799-804, 2010. H. Lee, S. Lee, T. Kim, and Hyokyung Bahn, “Secure user identification for consumer electronics devices,” IEEE Transactions on Consumer Electronics, vol.54, no.4, pp.1798-1802, Nov. 2008. D. Mulyono and S. J. Horng, “A study of finger vein biometric for personal identification”, Proceedings of the International Symposium Biometrics and Security Technologies, pp. 134-141, 2008. Z. Liu, Y. Yin, H. Wang, S. Song, and Q. Li ,“Finger vein recognition with manifold learning”, Journal of Network and Computer Applications, vol.33, no.3, pp. 275-282, 2010. Y. G. Dai and B. N. Huang, “A method for capturing the finger-vein image using nonuniform intensity infrared light”, Image and Signal Processing, vol.4, pp.27-30, 2008. X. Sun, C. Lin, M. Li, H. Lin, and Q. Chen, “A DSP-based finger vein authentication system”, Proceedings of the Fourth International Conference on Intelligent Computation Technology and Automation, pp.333-336, 2011. B. B. Mandelbrot, Fractals: Form, Chance and Dimension, San Francisco, CA: Freeman, 1977. B. B. Mandelbrot and D. Stauffer, “Antipodal correlations and the texture (fractal lacunarity) in critical percolation clusters”, Journal of Physics A: Mathematical and General, vol.27, pp.237-242, 1994. J. Berke, “Using Spectral Fractal Dimension in Image Classification”, Innovations and advances in computer sciences and engineering, pp. 237-241, 2010. Z. Feng, “Variation and Minkowski dimension of fractal interpolation surface”, Journal of Mathematical Analysis and Applications, vol. 345, no.1, pp. 322-334, 2008. S. Peleg and J. Naor, “Multiple resolution texture analysis and classification”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.6, no.4, pp.518-523, 1984.

527

[15] C. Allain and M. Cloitre, “Characterizing the lacunarity of random and deterministic fractal sets”, Physical Review A, vol.44, no.6, pp. 35523558, 1991. [16] K. I. Kilic and R. H. Abiyev, “Exploiting the synergy between fractal dimension and lacunarity for improved texture recognition”, Signal Processing, vol. 91, no. 10, pp. 2332-2344, 2011. [17] Novianto, Suzuki, and Maeda, “Optimum estimation of local fractal dimension based on the blanket method,” Transactions of the Information Processing Society of Japan, vol. 43, no.3, pp. 825-828, 2002. [18] D. D. Hwang and I. Verbauwhede, “Design of portable biometric authenticators - energy, performance, and security tradeoffs,” IEEE Transactions on Consumer Electronics, vol. 50, no. 4, pp. 1222-1231, Nov.2004. [19] N. Miura, A. Nagasaka, and T. Miyatake, “Feature extraction of fingervein patterns based on repeated line tracking and its application to personal identification”, Machine Vision Application, vol. 15, no.4, pp.194–203, 2004. [20] W. Song, T. Kim, H. C. Kim, J. H. Choi, H. Kong and S. Lee, “A finger-vein verification system using mean curvature”, Pattern Recognition Letters, vol. 32, no.11, pp. 1541-1547, 2011.

BIOGRAPHIES Zhi Liu received the M.Sc. degree in Circuit and System from Shandong University, China (2004) and the Ph.D. degree in Pattern Recognition and Intelligence System from Shanghai Jiao Tong University, China (2008). He worked in the School of Information Science and Engineering, Shandong University since 2008. His current research interests include image processing (texture analysis, image classification, and image segmentation), computer vision, and pattern recognition.

Shangling Song received a BS degree in electrical engineering from Zhejiang Gongshang University, Hangzhou, China, in 2001. She received the PhD degree from Shandong University, China (2010). She was a dual-culture student at Chiba University of Japan from 2007 to 2008.

An Embedded Real-Time Finger-Vein Recognition System ieee.pdf ...

There was a problem previewing this document. Retrying... Download. Connect more apps... Try one of the apps below to open or edit this item. An Embedded ...

834KB Sizes 0 Downloads 248 Views

Recommend Documents

Review of Iris Recognition System Iris Recognition System Iris ... - IJRIT
Abstract. Iris recognition is an important biometric method for human identification with high accuracy. It is the most reliable and accurate biometric identification system available today. This paper gives an overview of the research on iris recogn

Review of Iris Recognition System Iris Recognition System Iris ...
It is the most reliable and accurate biometric identification system available today. This paper gives an overview of the research on iris recognition system. The most ... Keywords: Iris Recognition, Personal Identification. 1. .... [8] Yu Li, Zhou X

An Effective Segmentation Method for Iris Recognition System
Biometric identification is an emerging technology which gains more attention in recent years. ... characteristics, iris has distinct phase information which spans about 249 degrees of freedom [6,7]. This advantage let iris recognition be the most ..

An Optical Character Recognition System for Tamil ...
in HTML document format. 1. ... analysis [2], image gradient analysis [3], ... Figure 1. Steps involved in complete OCR for Tamil documents. 2. PREPROCESSING.

An Optical Character Recognition System for Tamil ...
For finding the text part we use the Radial Basis Function neural network (RBFNN) [16]. The network is trained to distinguish between text and non-text (non-.

Embedded-System-Design-Introduction-To-SoC-System ...
Architecture eBooks. Totally free Books, regardless of whether Embedded System Design: Introduction To SoC System. Architecture PDF eBooks or in other format, are accessible in a heap around the net. Embedded System Design: Introduction To SoC System

An Offline Cursive Handwritten Word Recognition System
as the training procedure for the NN-HMM hybrid system. Another recognition ..... Reading on French Checks”, Computer Vision and Image. Understanding, vol.

Embedded Programming with Android Bringing Up an Android System ...
Try one of the apps below to open or edit this item. Embedded Programming with Android Bringing Up an Android System from Scratch - Roger Ye.pdf.

ARM MICROCONTROLLER & EMBEDDED SYSTEM syllabus.pdf ...
Sign in. Page. 1. /. 2. Loading… Page 1 of 2. ARM MICROCONTROLLER & EMBEDDED SYSTEM. B.E., VI Semester, Telecommunication Engineering [CBCS scheme]. Subject Code 15EC62 IA Marks 20. Number of Lecture 04 Exam Marks 80. Hours/Week. Total Number of 50

Embedded System Design.pdf
b) Briefly explain Concept phase, Design phase and Programming phase of. software life cycle. 7. 11. Write a note on any three of the following : (5×3=15).

EMBEDDED SYSTEM DESIGN.pdf
EMBEDDED SYSTEM DESIGN.pdf. EMBEDDED SYSTEM DESIGN.pdf. Open. Extract. Open with. Sign In. Main menu. Displaying EMBEDDED SYSTEM ...

HMM-BASED MOTION RECOGNITION SYSTEM ...
hardware and software technologies that allow spatio- temporal ... the object trajectory include tracking results from video trackers ..... different systems for comparison. ... Conference on Computer Vision and Pattern Recognition, CVPR. 2004.

Computer Vision-based Wood Recognition System - CiteSeerX
The system has less mobility, although it can be used on laptops, but setting up ... density function normalizes the GLCM by dividing all its elements by the total ...

Face Authentication /Recognition System For Forensic Application ...
Graphic User Interface (GUI) is a program interface item that allows people to interact with the programs in more ways than just typing commands. It offers graphical icons, and a visual indicator, as opposed to text-based interfaces, typed command la

89. GESTURE RECOGNITION SYSTEM FOR WHEELCHAIR ...
GESTURE RECOGNITION SYSTEM FOR WHEELCHAIR CONTROL USING A DEPTH SENSOR.pdf. 89. GESTURE RECOGNITION SYSTEM FOR ...

Offline Arabic character recognition system
tion receiving considerable attention in recent years due to the increasing dependence on computer data process- ing. It is used to transform human readable ...

accent tutor: a speech recognition system - GitHub
This is to certify that this project prepared by SAMEER KOIRALA AND SUSHANT. GURUNG entitled “ACCENT TUTOR: A SPEECH RECOGNITION SYSTEM” in partial fulfillment of the requirements for the degree of B.Sc. in Computer Science and. Information Techn

Detection and Recognition of Text Embedded in Online ... - S-Space
music and mail make memories she spring is here every end beginning that star wars time myself without. Figure 4: Examples of text detection and recognition with true positives in green, detection successes but recognition failures in blue, and detec