KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/kmitl/1

Browse

Search Results

Now showing 1 - 9 of 9

Some of the metrics are blocked by your
consent settings
Comparative study of character recognition on Thai license plate using DCT and FIR system
(2018-12-10)
Sirisantisamrid, Kaset
;
Wongvanich, Napasool
;
Gulpanich, Suphan
Thai characters have rather similar shapes, which they are not same as English characters that have distinct shapes. Thereby, performing of Thai character recognition is not simple. In this paper, the recognition of characters and numbers on Thai license plate using DCT and FIR system methods is proposed and compared base on recognition rate. There are two ways of studying in DCT method. First, compute the coefficients of 1D-DCT by separation in the horizontal and vertical complements of character and represent them as the features of character. Second, combine the coefficients of 1D-DCT at each component in form of power spectrum of DCT and use it as the character features. For FIR system method, the impulse responses of FIR system are used as the features of character. The 120 car images under variant illumination conditions are used to testing all three methods. Moreover, some images are incomplete conditions such peeling paint, stained with slush and so on. In the results, the success of recognition rate for separation of DCT coefficients, power spectrum of DCT and FIR system methods was 99.15%, 48.30% and 98.30%, respectively.
Some of the metrics are blocked by your
consent settings
Gait identification based on FIR system characterizing motion of leg
(2013-12-01)
Thumwarin, P.
;
Srisuk, K.
;
Matsuura, T.
This paper presents gait identification method based on Finite Impulse Response (FIR) system characterizing motion of leg. First, the four gait features, area of footstep, angle of footstep, height and width of the human silhouette image, are calculated from the human silhouette image. Then they are expanded into Fourier series to reduce the fluctuation of human body motion. The motion of leg can be characterized by two FIR gait identification systems. For the first FIR system, the Fourier coefficients of the width of human silhouette image and the area of footstep are used as input and output of the system, respectively. For the second FIR system, the Fourier coefficients of the height of the human silhouette image and the angle of footstep are used as input and output of the system, respectively. The obtained impulse responses of the two FIR systems are used as the individual feature for gait identification. The gait identification experiments were performed on CASIA GAIT Dataset B [6], which contains 8,184 gait data for 11 view angles from 124 persons. The average of error rates obtained from 90° view angle was 3.48%. © 2013 IEEE.
Some of the metrics are blocked by your
consent settings
On-line signature verification based on FIR system characterizing motion pressure
(2011-12-01)
Thumwarin, P.
;
Pernwong, J.
;
Matsuura, T.
We propose an on-line signature verification method based on finite impulse response(FIR) system characterizing motion pressure of pen-point trajectory in signing process. The discrete cosine transforms(DCTs) of the handwriting feature is used to reduce the fluctuation and extract the feature of handwriting. The signature verification system is realized by four FIR subsystems. Then motion pressure can be characterized by using the FIR subsystem having the DCTs of the area pressure and motion pressure as the input and the output of the FIR system, respectively. The obtained impulse responses of the four FIR subsystems are used as the individual feature for signature verification. Finally, the signature can be verified by evaluating the difference between the impulse responses of the FIR subsystems for a reference signature and the signature to be verified. The signature verification experiments were performed on the SUBCORPUS-100 MCYT [J. Ortega-Garcia et al. 2003] signature database consisting of 5,000 signatures from 100 signers. The propose method yielded equal error rate(EER) 4.38 % on skilled forgeries. © 2011 ACM.
Some of the metrics are blocked by your
consent settings
On-line signature verification based on FIR system characterizing velocity and direction change of barycenter trajectory
(2010-12-01)
Thumwarin, P.
;
Pernwong, J.
;
Wakayaphattaramanus, N.
;
Matsuura, T.
We propose an on-line signature verification method based on finite impulse response(FIR) system characterizing velocity and direction change of barycenter trajectory. First, the discrete cosine transforms (DCTs) of the characteristics are used to reduce fluctuation and extract the feature of handwriting in signing process. Then the signature verification system is realized by the three FIR subsystems. The obtained impulse responses of the three FIR subsystems are used as the individual feature for signature verification. Signature can be verified by evaluating the difference between the impulse responses of the FIR subsystems for a reference signature and the signature to be verified. The signature verification experiments were performed on the SUBCORPUS-100 MCYT signature database[6] consisting of 5,000 signatures from 100 signers. ©2010 IEEE.
Some of the metrics are blocked by your
consent settings
Firearm identification system with rotation invariance
(2010-01-01)
Thumwarin, P.
;
Prasit, C.
;
Yakoompai, K.
;
Matsuura, T.
This paper presents a firearm identification method with rotation invariance. The rotation invariant feature can be extracted by the magnitude of Fourier coefficients of polar image of the cartridge on circles with different radii. Then the fluctuation of the obtained magnitude of Fourier coefficients can be reduced by the FIR(Finite impulse response) Wiener filter. And they are used as the input and the output of the FIR system characterizing the rotation invariant feature of cartridge image. The impulse response of the FIR system is used as the unique feature for firearm identification. Finally, the firearm can be identified by the Fisher's linear discriminant function. The experimental results are given to show the effectiveness of the proposed method. ©ICROS.
Some of the metrics are blocked by your
consent settings
On-line writer identification system characterizing velocity and areal velocity in handwriting process
(2009-12-01)
Matsuura, Takenobu
;
Thumwarin, Pitak
In this paper,we propose an on-line writer identification system characterizing velocity and areal velocity of pen-tip movement in handwriting process. The writer identification system consists of two finite impulse response (FIR) systems characterizing the velocity and areal velocity in handwriting process. Individual handwriting feature is represented by the impulse response of the FIR system. Writer can be identified by evaluating the difference between the impulse responses of the FIR systems for the reference and a person to be identified. In our experiments 2,000 Thai numerals were used to identify 10 different writers.
Some of the metrics are blocked by your
consent settings
On-line writer identification method based on FIR system characterizing pen-tip movement
(2008-12-01)
Matsuura, Takenobu
;
Thumwarin, Pitak
In this paper on-line writer identification problem is reduced to FIR system identification problem. Then person can be identified by evaluating the difference between the impulse responses of the FIR system for the reference and the person to be identified. The FIR system is realized by considering the DCTs of the horizontal and vertical components of the pen-tip movement with reduced fluctuation as the input and output,respectively. Finally, writer identification experiments are given to show the effectiveness of the proposed method. Copyright © 2008 by Department of Electronics, AGH University of Science and Technology.
1
Some of the metrics are blocked by your
consent settings
Firearm identification based on FIR system characterizing rotation invariant feature of cartridge case image
(2008-12-01)
Thumwarin, P.
;
Prasit, C.
;
Boonbumroong, P.
;
Matsuura, T.
We propose firearm identification method based on FIR system characterizing rotation invariant feature of cartridge case image. The rotation invariant feature is represented by the absolute value of Fourier coefficients of polar image on circles with different radii of the cartridge case's primer. Then the FIR(Finite impulse response) system characterizing the rotation invariant feature of cartridge case's primer image is introduced. The absolute value of Fourier coefficients obtained from the polar image on the circles with different radii are used as the input and output of the FIR system, respectively. The obtained impulse response of the FIR system is considered as the unique feature of the individual gun. Finally, a firearm can be identified by using the Fisher's linear discriminant function of the obtained impulse response of the FIR system. The firearm identification experiments are conducted to show the effectiveness of the proposed method. © 2008 IEEE.
Some of the metrics are blocked by your
consent settings
On-line writer identification based on handwriting velocity and curvature of script
(2008-12-01)
Matsuura, T.
;
Thumwarin, P.
;
Kato, N.
We propose an on-line writer identification method based on the handwriting velocity and curvature of script. First, we calculate the autocorrelation functions for the normalized handwriting velocity and the normalized curvature of script, respectively. Secondly, we realize a finite impulse response (FIR) system having the Fourier coefficients of the obtained autocorrelation functions as the input and output, respectively. The realized FIR system can characterize the relation between the handwriting velocity and curvature of script. Writer can be identified by evaluating the difference between the impulse responses of the FIR systems for the writer and the reference. Finally, writer identification experiments are given to show the effectiveness of the proposed method. © 2008 IEEE.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results