KMITL

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

Browse

Search Results

Now showing 1 - 10 of 19

Some of the metrics are blocked by your
consent settings
IC chip marking inspection using fir system
(2020-01-01)
Khannakum, Wirat
;
Sirisantisamrid, Kaset
In this paper, we proposed a novel method for inspection the marking label of IC chip using FIR system. Firstly, the IC chip is loaded to the inspection machine and IC chip image are captured. Secondly, Maximum Stable Extremal Region (MSER) algorithm is applied to find the characters, numbers, and company logo regions of IC chip and crop the detected marking label region. Thirdly, convert the grayscale image to a binary image and segmented the characters, numbers and company logo using connected component labeling algorithm. We observed some IC chip is tilted when moving to marking inspection station and effect to the position of the characters, numbers and company logo are shifted. Thereby, we need to orientate them by using Normalization. Finally, the recognition system based on DCT and FIR system. The example of the correct extracting rate of IC marking inspection was 94%.
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
Application of the OpenCV-python for personal identifier statement
(2018-08-13)
Sriratana, Witsarut
;
Mukma, Suppakorn
;
Tammarugwattana, Narin
;
Sirisantisamrid, Kaset
Work attendance is one of the processes that either large or small companies need to be involved with. To reduce the time-consuming and improve the reliability of such process, this work proposes an alternative solution by applying the combinations of image processing and Viola Jones algorithm on the facial-employee database. The facial detection and recognition system shows the high accuracy over 90%. The proposed process not only improves the efficiency of the work attendance in term of data-collecting and data-analyzing but also possibly prevents the cheating of appearance compared to the old-fashion processes e.g. signing-paper or Radio Frequency Identification (RFID).
Some of the metrics are blocked by your
consent settings
LQR/PID controller design of PLC-based inverted pendulum
(2018-01-01)
Sirisantisamrid, Kaset
;
Wongvanich, Napasool
;
Gulpanich, Suphan
;
Tammarugwattana, Narin
This paper presents an LQR based PID controller to control the inverted pendulum system. The control design employs a control zoning approach whereby the entire pendulum system is divided into two regions: a normal pendulum region and the inverted pendulum region where the system is approximately linear close to the upright position. The LQR architecture is used to obtain optimal gains for the PID controller. An algebraic approach is also presented for selection of Q and R matrices. Experimental implementations with a PLC based system show that the computed gains yield the most stable controlled responses compared to the gains chosen through trial and errors.
Some of the metrics are blocked by your
consent settings
Representation of Thai character features with impulse response of FIR system
(2017-12-13)
Sirisantisamrid, Kaset
This paper proposes a concept of how to representation of Thai character features with impulse response of FIR system. The character or numeral image captured by a digital camera is converted to binary image. The character and numeral features extraction method is performed that consists of edge contour detection, thinning, and searching for coordinates of character and number. Then its coordinates is normalized and the DCT coefficients in horizontal and vertical components of coordinates are calculated. Finally, the impulse response of FIR system of that character and number is determined by setting the DCT coefficients in horizontal and vertical components as input and output of FIR system, respectively. The aim of this research is to apply the proposed concept to identify and recognize the characters and numbers on Thai license plate. On experiments, 100 car images are tested to identify the characters and numbers of plate number on Thai license plate. The experimental results shown the accuracy of the proposed method is about 87%.
Some of the metrics are blocked by your
consent settings
Identification of Thai characters and numbers on plate number
(2017-07-01)
Sirisantisamrid, Kaset
This paper proposes a method of Thai characters and numeral identification on plate number. The proposed method consists of license plate detection and identification of characters and numbers. In the license plate detection, the vertical edges, the vertical projection, and some operations of morphology are used to searching for license plate location. Once plate location is known, the identification of characters and numbers starts from inversion of binary image, character and number segmentation, normalization, computation of the horizontal and vertical DCT coefficients. Finally, the impulse response of FIR system of character and number are determined using the horizontal and vertical DCT coefficients as input and output of FIR system. The unknown characters or numbers on the plate number can be identified by comparison of their impulse response with the impulse responses of known characters and numbers in database, if the sum square error of them is smallest. On experiments, it found that the correct detection of license plate is about 95.52% and the accuracy of characters and numeral identification is about 81.25%.
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
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
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.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results