• Journal of the Semiconductor & Display Technology
• /
• v.23 no.2
• /
• pp.23-27
• /
• 2024

Underwater images are typically degraded due to color distortion, light absorption, scattering, and noise from artificial light sources. Restoration of these images is an essential task in many underwater applications. In this paper, we propose a two-phase deep learning-based method, Underwater Deep Curve Estimation (UWDCE), designed to effectively enhance the quality of underwater images. The first phase involves a white balancing and color correction technique to compensate for color imbalances. The second phase introduces a novel deep learning model, UWDCE, to learn the mapping between the color-corrected image and its best-fitting curve parameter maps. The model operates iteratively, applying light-enhancement curves to achieve better contrast and maintain pixel values within a normalized range. The results demonstrate the effectiveness of our method, producing higher-quality images compared to state-of-the-art methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.9C
• /
• pp.720-724
• /
• 2008

Channel estimation in OFDM systems is usually carried out in frequency domain based on the least-squares (LS) method and the minimum mean-square error (MMSE) method with known pilot symbols. The LS estimator has a merit of low complexity but may suffer from the noise because it does not consider any noise effect in obtaining its solution. To enhance the noise immunity of the LS estimator, we consider estimation noise in time domain. Residual noise existing at the estimated channel coefficients in time domain could be reduced by reasonable selection of a threshold value. To achieve this, we propose a channel-estimation method based on a time-domain threshold which is a standard deviation of noise obtained by wavelet decomposition. Computer simulation shows that the estimation performance of the proposed method approaches to that of the known-channel case in terms of bit-error rates after the Viterbi decoder in overall SNRs.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.4
• /
• pp.617-624
• /
• 2021

The accurate estimation of the number of signals included in the received signal is required for the AOA(: Angle-of-Arrival) estimation, the interference suppression, the signal reception, etc. AIC(: Akaike Information Criterion) and MDL(: Minimum Description Length) algorithms, which are known as the typical algorithms to estimate the signal number, estimate the number of signals according to the minimum of each criterion. As the number of antenna elements increased, the estimation performance is enhanced, but the computational complexity is increased because values of criteria for entire antenna elements should be calculated for finding their minimum. In order to improve this problem, in this paper, we propose AIC and MDL algorithms based on the beamspace, which efficiently estimate the number of signals while reducing the computational complexity by reducing the dimension of an array antenna through the beamspace processing. In addition, we provide computer simulation results based on various scenarios for evaluating and analysing the estimation performance of the proposed algorithms.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1081-1088
• /
• 2021

The modern wireless communication system employes the beamforming technique based on a massive array antenna with a number of elements, for supporting the smooth communication services. A reliable beamforming technology requires the Angle-of-Arrival(: AOA) information for the signal incident to the receiving antenna, which is generally estimated by the high-resolution AOA estimation algorithm such as Multiple Signal Classification(: MUSIC). Although the MUSIC algorithm has the excellent estimation performance, it is difficult to estimate AOA in real time for the massive array antenna due to the extremely high computational complexity. In order to enhance this problem, in this paper, we propose the cascade AOA estimation algorithm based on a Flexible Massive Concentric Circular Array(: FMCCA) antenna with the On/Off function for antenna elements. The proposed cascade algorithm consists of the CAPON algorithm using some elements among entire antenna elements and the Beamspace MUSIC algorithm using entire elements. We provide computer simulation results for various scenarios to demonstrate the AOA estimation performance of the proposed approach.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.1
• /
• pp.78-84
• /
• 2015

Depth estimation is often required for robot vision, 3D modeling, and motion control. Previous method is based on the focus measures which are calculated for a series of image by a single camera at different distance between and object. This method, however, has disadvantage of taking a long time for calculating the focus measure since the mask operation is performed for every pixel in the image. In this paper, we estimates the depth by using the focus measure of the boundary pixels located between the objects in order to minimize the depth estimate time. To detect the boundary of an object consisting of a straight line and a circle, we use the Hough transform and estimate the depth by using the focus measure. We performed various experiments for PCB images and obtained more effective depth estimation results than previous ones.

• Journal of Electrical Engineering and Technology
• /
• v.6 no.4
• /
• pp.439-446
• /
• 2011

Frequency is an important operating parameter for the protection, control, and stability of a power system. Thus, it must be maintained very close to its nominal frequency. Due to the sudden change in generation and loads or faults in a power system, however, frequency deviates from its nominal value. An accurate monitoring of the power frequency is essential for optimum operation and prevention of wide area blackout. Most conventional frequency estimation schemes are based on the DFT filter. In these schemes, the gain error could cause defects when the frequency deviates from the nominal value. We present an advanced frequency estimation technique using gain compensation to enhance the DFT filter-based technique. The proposed technique can reduce the gain error caused when the frequency deviates from the nominal value. Simulation studies are performed using both the data from EMTP-RV software and the user-defined arbitrary signals to demonstrate the effectiveness of the proposed algorithm. Results show that the proposed algorithm achieves good performance under both steady state tests and dynamic conditions.

• Journal of Welding and Joining
• /
• v.28 no.1
• /
• pp.92-99
• /
• 2010

For the last couple of decades many studies have been carried out to find out solutions to improve the effectiveness and productivity of the plate forming process. The practical way for the automation of the plate forming process has not been, however, developed yet. Since the characteristics of heating machines may be different form each other, it is necessary to investigate the thermal deformation characteristics of the heating machine to be used in the automation system. And their characteristics may be updated as new information about thermal deformation by heating is accumulated. In this paper, data base system has been constructed based on the results of experiments and numerical analyses, which will be used in deriving the deformation estimation formula. The computer code which can automatically derive the deformation estimation formula has been also developed. This paper also illustrates how the formula is updated as experimental data are added. From the present findings, it can be said that the automatic deriving procedure may be important in the automated plate forming system since the heating line information to be generated must be directly influenced by the deformation estimation formula.

• Journal of electromagnetic engineering and science
• /
• v.1 no.1
• /
• pp.105-111
• /
• 2001

This paper presents a new and robust technique for a coarse frequency offset estimation in OFDM systems. As an evaluation of the proposed algorithm, we apply it to Eureka 147 DAB system. The proposed coarse frequency offset estimation algorithm is based on the differential detection technique between adjacent subcarriers to eliminate the phase shift effects of symbol timing offset and fractional frequency offset. A coarse frequency offset is determined from the correlation output between a received interarrier differential phase reference symbol and several locally generated but frequency-shifted intercarrier differential phase reference symbols. The performance of our estimation algorithm is evaluated by means of computer simulation and is compared with those of previous proposed algorithms for DAB transmission modes I, II, III, and IV. Simulation results show that the proposed algorithm generates extremely accurate estimates with low complexity irrespective of the symbol timing offset.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.9A
• /
• pp.882-890
• /
• 2008

To overcome the limit of the time-domain based channel estimation caused by the ADC speed, this paper present a new BPM-UWB receiver where the channel estimations and the compensations are digitally performed in the frequency domain. We theoretically show that the channel estimation can be accomplished by exploiting the periodicity of a training sequence consisting of finite number of pulses. We also present the digital receiver structure to implement the proposed system and derive its BER performances. Through computer simulations, we show the proposed receiver can dramatically improve the BER performances due to the incorporation of the estimated channel frequency response.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.9
• /
• pp.1224-1231
• /
• 2018

Automatic age estimation has been used in many social network applications, practical commercial applications, and human-computer interaction visual-surveillance biometrics. However, it has rarely been explored. In this paper, we propose an automatic age estimation system, which includes face detection and convolutional deep learning based on an inception module. The latter is a 22-layer-deep network that serves as the particular category of the inception design. To evaluate the proposed approach, we use 4,000 images of eight different age groups from the Adience age dataset. k-fold cross-validation (k = 5) is applied. A comparison of the performance of the proposed work and recent related methods is presented. The results show that the proposed method significantly outperforms existing methods in terms of the exact accuracy and off-by-one accuracy. The off-by-one accuracy is when the result is off by one adjacent age label to the above or below. For the exact accuracy, the age label of "60+" is classified with the highest accuracy of 76%.