• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.529-532
• /
• 2005

In this paper, we propose a motion picture processor for CSTN LCD. In order to eliminate flicker phenomenon, the proposed processor suggests a new driving scheme, SFP(Subgroup Frame Pattern). We use an input image compression methode from RGB(:8:8;8) to RGB(5:6:5) to improve quality of the image and apply the image to CSTN Module. The proposed hardware architecture has been implemented and verified using a FPGA on prototype board. The proposed Algorithm provide a lower computational complexity. Therefore the processor can be used in the display devices such as PDA, mobile phone and PMP(Portable Multimedia Player).

• International Journal of CAD/CAM
• /
• v.5 no.1
• /
• pp.11-18
• /
• 2005

The traditional method of manipulation of knots and degrees gives poor quality of surface, if compatibility of input curves is not good enough. In this work, a new algorithm of multiple refitting of curves has been developed using minimum energy based formulation to get compatible curves for skinning. The present technique first reduces the number of control points and gives smoother surface for given accuracy and the surface obtained is then skinned by compatible curves. This technique is very useful to reduce data size when a large number of data have to be handled. Energy based technique is suitable for approximating the missing data. The volumetric information can also be obtained from the surface data for analysis.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.1
• /
• pp.436-442
• /
• 2017

A novel method of Skin lesion segmentation based on the combination of Texture and Neural Network is proposed in this paper. This paper combines the textures of different pixels in the skin images in order to increase the performance of lesion segmentation. For segmenting skin lesions, a two-step process is done. First, automatic border detection is performed to separate the lesion from the background skin. This begins by identifying the features that represent the lesion border clearly by the process of Texture analysis. In the second step, the obtained features are given as input towards the Recurrent Echo state neural networks in order to obtain the segmented skin lesion region. The proposed algorithm is trained and tested for 862 skin lesion images in order to evaluate the accuracy of segmentation. Overall accuracy of the proposed method is compared with existing algorithms. An average accuracy of 98.8% for segmenting skin lesion images has been obtained.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1996.06a
• /
• pp.203-207
• /
• 1996

This paper describes a method for estimating motion vectors in a video sequence. In this method, we find motion vectors using the full search method from the training images and then, train the codebook of the neural networks vector quantizer using these motion vectors. A motion vector can be estimated using the codebook as a motion prediction region. The codewords in the codebook represent the motion vectors for the input image sequences. Since the codebook is used as the search region for estimating the motion vectors, search points and computation can be reduced compared with the full search block matching algorithm. Additionally, the information required to transmit the motion vectors can be reduced.

• Journal of Korean Institute of Industrial Engineers
• /
• v.20 no.4
• /
• pp.181-192
• /
• 1994

In an order-oriented production system such as mold manufacturing, the production starts with an order acceptance, and the production planning is set up according to the accepted order information. Such a work can be done through a dynamic process management system which can reflect shop floor situation dynamically. In this paper, so called the Quick order acceptance evaluation system that can investigate order confirmation quickly, is discussed. When an order is asked, this system must consider the time constraint to determine whether to accept or not, and must be reliable when the determined results are used in the shop floor. For this system, firstly, we simplified the machines by grouping based on their operation capabilities, secondly, we conducted load analysis to calculate available capacities during given periods using heuristic method instead of mathematical algorithm, thirdly, expert can input his experienced knowledge into the system interactively when simulation results don't meet the required due dates. As a case study, we applied this system to an injection mold manufacturing factory.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.915-918
• /
• 2000

In this paper, we propose an efficient feature vector extraction and decision fusion methods for the automatic classification of power system disturbances. Here, FFT and WPT(wavelet packet transform) are und to extract an appropriate feature for classifying power quality disturbances with variable properties. In particular, the WPT can be utilized to develop an adaptable feature extraction algorithm using best basis selection. Furthermore. the extracted feature vectors are applied as input to the decision fusion system which combines the decisions of several classifiers having complementary performances, leading to improvement of the classification performance. Finally, the applicability of the proposed approach is demonstrated using some simulations results obtained by analyzing power quality disturbances data generated by using Matlab.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.4
• /
• pp.81-90
• /
• 1996

In this paper, we implemented a computerized pulse diagnosis system for the developement of pulse diagnosis algorithms and the generalization of the pulse diagnosis. The system consists of the hardware and software. The hardware detects pulse waves and inputs the waves into the computer system, while the software not only manages and analyzes the input pulse wave data but also privides the database. In order to clinically test the developed pulse diagnosis system, we applied the carotid-radial pulse diagnosis algorithm to the system. As the results, it is found that the genralizatio of the pulse diagnosis is possible.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.5
• /
• pp.159-164
• /
• 1996

In this paper, a novel control strategy of curretn source PWM converter and inverter system for induction motor dirves is proposed. The PWM converter controls line current to be sinusoidal and makes input power factor unity. In the inverter part, a minor voltage control loop is incorporated in the current control looop in order to suppress unstale resonance between the filter capacitor and the motor leakage inductance and to keep the stator voltage under the rated value. In additon, the modulation index control of the inverter currents ripples and inverter loss. With the proposed algorithm, both high dynamic responses and satisfactory static performance can be obtained.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.4
• /
• pp.36-44
• /
• 1997

An efficient context-free multiple-object segmentation using attention operator based on modified generalized symmetry transform is proposed and implemented by modifying a radial basis function network. By using the difference of intensity gradient, instead of te intensity gradient itself, in generalized symmetry tranform so as to make the attention operator to preserve the edges of the objects shape, an efficient context-free multiple-object segementation is proposed in which no a priori shape informtion on the objects is requried. The attention operator is implemented by using a modified radial basis function network which can reflect symmetry, and by using te edge pyramid of the input image, both of the local and the global symmetry of the objects are reflected simultaneously to make the multiple-object with different sizes be segmented with a singel fixed-size $n\timesm$ can be done with O(n) complexity. The simulaton results show that the proposed algorithm can efficiently be used in context-free multiple-object segmentation even for the low contrast IR images as well as for the images from the camera.

• Journal of the Speleological Society of Korea
• /
• no.82
• /
• pp.5-7
• /
• 2007

In this paper, p-n junction formation using screen-printed metalization and co-firing is used to fabricate high-efficiency solar cells on single- crystalline silicon substrates. In order to form high-quality contacts, co-firing of a screen-printed Ag grid on the front and Al on the back surface field is implemented. These contacts require low contact resistance, high conductivity, and good adhesion to achieve high efficiency. Before co-firing, a statistically designed experiment is conducted. After the experiment, a neural network (NN) trained by the error back-propagation algorithm is employed to model the crucial relationships between several input factors and solar cell efficiency. The trained NN model is also used to optimize the beltline furnace process through genetic algorithms.