KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 10 of 18

Some of the metrics are blocked by your
consent settings
On-line signature verification based on forward and backward variances of signature
(2014-01-01)
Wibowo, Canggih Puspo
;
Thumwarin, Pitak
;
Matsuura, Takenobu
We propose new features called the forward and backward variances of signature for on-line signature verification. In the proposed method, stable features of signature can be characterized by the forward and backward variances of signature. It is shown that signature can be verified by evaluating the difference of K-L coefficients of the forward and backward variances between the reference and signature to be verified. Experiments are performed on public signature database MCYT-100, consists of 5000 signatures from 100 people. The Equal Error Rate is 4.49%. © 2014 IEEE.
Some of the metrics are blocked by your
consent settings
A technique of camera calibration using single view
(2011-12-01)
Sirisantisamrid, Kaset
;
Tirasesth, Kitti
;
Matsuura, Takenobu
This paper proposes a technique of camera calibration to calibrate a camera. It is easy for the proposed technique to extract the camera parameters with only one image using an iteration method. In this paper, radial and tangential lens distortion is modeled. The proposed technique divides original parameters into block of parameters. Each block of parameters is computed by minimizing a nonlinear error function after the intermediate parameters are linearly computed on each iteration. The formal distorted images and the distorted images with shifted principal point have been used to test the proposed technique and the conventional method. As the result, we have obtained good results. © 2011 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
A determination method of initial camera parameters for coplanar calibration
(2009-11-26)
Sirisantisamrid, Kaset
;
Tirasesth, Kitti
;
Matsuura, Takenobu
Most coplanar calibration algorithms determine the initial camera parameters from a single image under the assumption that the principal point is known in advance. However, the camera orientations, the shifted principal point and the noise corrupted on images have an influence on the estimated initial camera parameters under the above assumption. This paper proposes a useful method to determine the initial camera parameters for coplanar calibration. The proposed method can determine the initial camera parameters from the single image, wherein the principal point is considered as a parameter. In our experiments, both synthetic and real images are used. The experimental results show that the proposed method provides both stable initial camera parameters and noise robustness for changes of camera orientations, noise levels and shifts of principal point. © ICROS, KIEE and Springer 2009.
Some of the metrics are blocked by your
consent settings
Influence of principal point on camera calibration algorithms
(2009-01-01)
Sirisantisamrid, Kaset
;
Tirasesth, Kitti
;
Matsuura, Takenobu
The principal point has influence on the camera parameters determined by most calibration algorithms in which the camera parameters are inaccurate and unstable when the principal point is shifted from the center of image. This paper proposes a simple technique for camera calibration that is insensitive to change the principal point and shows an influence of principal point on camera calibration algorithms. The proposed method starts from defining a set of intermediate parameters in terms of camera parameters. Then, the intermediate parameters, the lens distortion coefficients, the principal point, and the distances between sensors are iteratively computed. Finally, the remaining camera parameters are estimted from the obtained intermediate parameters. In the experimental results, we tested the influence of principal point on camera parameters computed by the proposed method and compared the results with the conventional method.
Some of the metrics are blocked by your
consent settings
On-line writer dependent character recognition for Khmer based on FIR system characterizing handwriting motion
(2008-12-01)
Thumwarin, Pitak
;
Khem, Sochenda
;
Janchitraponvej, Kanok
;
Matsuura, Takenobu
We propose an on-line writer dependent Khmer recognition method based on time-frequency characteristics of handwriting motion. The handwriting motion can be described by two features, barycenter trajectory and its velocity of pen-tip movement. Then the barycenter trajectory and its velocity of the pen-tip movement are expanded into wavelet series to extract the time-frequency characteristics of the handwriting motion. After that, The fluctuation of the wavelet coefficients can be reduced by the FIR(Finite Impulse Response) Wiener filter. Moreover, the FIR system characterizing the time-frequency characteristics of the handwriting motion is introduced by using wavelet coefficients of the velocity and trajectory of the barycenter with fluctuation reduced as the input and output of the FIR system, respectively. The obtained impulse response of the FIR system is considered as the individual feature for a particular character. Finally, Khmer alphabets can be recognized by using the Euclidean distance between the impulse responses obtained from the reference alphabets and those of the alphabets to be recognized. Khmer character recognition experiments were performed on a database consisting of 6,750 of numerals and alphabets written by 17 people. As the results, the average of the recognition rate was 98.17%. © 2008 SICE.
Some of the metrics are blocked by your
consent settings
A simple technique for coplanar camera calibration
(2008-12-01)
Sirisantisamrid, Kaset
;
Tirasesth, Kitti
;
Matsuura, Takenobu
This paper proposes a simple technique for camera calibration under assumption that a calibration pattern is on world coordinate system. The proposed method consists of two steps. In the first step, the intermediate parameters, lens distortion coefficients, principal point and the distances between sensors are computed by an iterative linear method. Then, the camera parameters are determined from the obtained intermediate parameters. In the experimental results, the proposed method gives the accurate and stable camera parameters for change rotation angles when compared with the conventional method.
Some of the metrics are blocked by your
consent settings
An influential principal point on camera parameters
(2008-12-01)
Sirisantisamrid, Kaset
;
Thepmanee, Teerawat
;
Tirasesth, Kitti
;
Matsuura, Takenobu
This paper proposes a method of camera calibration and the influence of principal point on camera parameters. The camera parameters are represented in terms of a set of intermediate parameters. The intermediate parameters and lens distortion coefficients are iteratively computed. The image coordinates are rectified on each cycle of iteration. Once the iteration is terminated, the initial parameters are computed from the obtained intermediate parameters. Then, the camera parameters and distortion coefficients are iteratively computed from the obtained initial parameters and the image coordinates are rectified too. In the experimental results, the proposed method is tested by change principal point to observe the influential principal point on camera parameters and compared the results with the conventional method.
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.
Some of the metrics are blocked by your
consent settings
A personal identification method based on finger's outline
(2008-12-01)
Sirisantisamrid, Kaset
;
Tirasesth, Kitti
;
Iwanaga, Shuhei
;
Matsuura, Takenobu
We propose a personal identification method based on finger's outline. In this paper first, we extract the finger's outline from a hand image acquired by the image acquisition system. Secondly we normalize the finger's outline by expanding the horizontal and vertical components into the KL expansion. The resulting finger's outline has a rotation invariant feature. Thirdly we expand the horizontal and vertical components of the normalized finger's outline into the Fourier series, respectively. Furthermore we consider a FIR system having the absolute values of the Fourier coefficients (AFC) as the input and output, respectively. It is considered that the FIR system represents the finger's outline feature. Then we can identify a person by evaluating the difference between the impulse responses of the FIR systems corresponding to the reference and the person to be identified. Finally, personal identification experiments were performed for 2180 hand images obtained from 109 persons. As the results FRR (false rejection) and FAR (false acceptance) error rates were 1.05% and 0.09%, respectively. © 2008 IEEE.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results