• Journal of the Korea Society of Computer and Information
• /
• 제29권8호
• /
• pp.23-32
• /
• 2024

NVS (Novel View Synthesis) is a field in computer vision that reconstructs new views of a scene from a set of input views. Real-time rendering and high performance are essential for NVS technology to be effectively utilized in various applications. Recently, 3D-GS (3D Gaussian Splatting) has gained popularity due to its faster training and inference times compared to those of NeRF (Neural Radiance Fields)-based methodologies. However, since 3D-GS reconstructs a 3D (Three-Dimensional) scene by splitting and cloning (Density Control) Gaussian points, the number of Gaussian points continuously increases, causing the model to become heavier as training progresses. To address this issue, we propose two methodologies: 1) Gaussian blending, an improved density control methodology that removes unnecessary Gaussian points, and 2) a performance enhancement methodology using a depth estimation model to minimize the loss in representation caused by the blending of Gaussian points. Experiments on the Tanks and Temples Dataset show that the proposed methodologies reduce the number of Gaussian points by up to 4% while maintaining performance.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• 제5권1호
• /
• pp.95-101
• /
• 2011

In this paper, we propose the gaussian mixture model based pattern classification algorithm of forearm electromyogram. We define the motion of 1-degree of freedom as holding and unfolding hand considering a daily life for patient with prosthetic hand. For the extraction of precise features from the EMG signals, we use the difference absolute mean value(DAMV) and the mean absolute value(MAV) to consider amplitude characteristic of EMG signals. We also propose the D_DAMV and D_MAV in order to classify the amplitude characteristic of EMG signals more precisely. In this paper, we implemented a test targeting four adult male and identified the accuracy of EMG pattern classification of two motions which are holding and unfolding hand.

• Speech Sciences
• /
• 제5권1호
• /
• pp.7-21
• /
• 1999

This paper proposes an improved training procedure in speech recognition based on the continuous density of the Hidden Markov Model (CDHMM). Of the three parameters (initial state distribution probability, state transition probability, output probability density function (p.d.f.) of state) governing the CDHMM model, we focus on the third parameter and propose an efficient algorithm that determines the p.d.f. of each state. It is known that the resulting CDHMM model converges to a local maximum point of parameter estimation via the iterative Expectation Maximization procedure. Specifically, we propose two independent algorithms that can be embedded in the segmental K -means training procedure by replacing relevant key steps; the adaptation of the number of mixture Gaussian p.d.f. and the initialization using the CDHMM parameters previously estimated. The proposed adaptation algorithm searches for the optimal number of mixture Gaussian humps to ensure that the p.d.f. is consistently re-estimated, enabling the model to converge toward the global maximum point. By applying an appropriate threshold value, which measures the amount of collective changes of weighted variances, the optimized number of mixture Gaussian branch is determined. The initialization algorithm essentially exploits the CDHMM parameters previously estimated and uses them as the basis for the current initial segmentation subroutine. It captures the trend of previous training history whereas the uniform segmentation decimates it. The recognition performance of the proposed adaptation procedures along with the suggested initialization is verified to be always better than that of existing training procedure using fixed number of mixture Gaussian p.d.f.

• Journal of the Institute of Electronics and Information Engineers
• /
• 제52권4호
• /
• pp.135-144
• /
• 2015

Fingerprint pores have proven to be useful features for fingerprint recognition and several pore-based fingerprint recognition systems have been reported recently. In order to recognize fingerprints using pore information, it is very important to extract pores reliably and accurately. Existing pore extraction methods utilize 2D model fitting to detect pore centers. This paper proposes a pore extraction method using 1D Gaussian model which is much simpler than 2D model. During model fitting process, 1D model requires less computational cost than 2D model. The proposed method first calculates local ridge orientation; then, ridge mask is generated. Since pore center is brighter than its neighboring pixels, pore candidates are extracted using a $3{\times}3$ filter and a $5{\times}5$ filter successively. Pore centers are extracted by fitting 1D Gaussian model on the pore candidates. Extensive experiments show that the proposed pore extraction method can extract pores more effectively and accurately than other existing methods, and pore matching results show the proposed pore extraction method could be used in fingerprint recognition.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제11권1호
• /
• pp.40-50
• /
• 2011

A two-dimensional (2D) analytical model for the potential distribution and threshold voltage of short-channel ion-implanted GaAs MESFETs operating in the sub-threshold regime has been presented. A double-integrable Gaussian-like function has been assumed as the doping distribution profile in the vertical direction of the channel. The Schottky gate has been assumed to be semi-transparent through which optical radiation is coupled into the device. The 2D potential distribution in the channel of the short-channel device has been obtained by solving the 2D Poisson's equation by using suitable boundary conditions. The effects of excess carrier generation due to the incident optical radiation in channel region have been included in the Poisson's equation to study the optical effects on the device. The potential function has been utilized to model the threshold voltage of the device under dark and illuminated conditions. The proposed model has been verified by comparing the theoretically predicted results with simulated data obtained by using the commercially available $ATLAS^{TM}$ 2D device simulator.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제13권1호
• /
• pp.59-66
• /
• 2013

In this paper, we propose a probabilistic framework for model-based clustering of direction of arrival (DOA) data to obtain stable sound source localization (SSL) estimates. Model-based clustering has been shown capable of handling highly overlapped and noisy datasets, such as those involved in DOA detection. Although the Gaussian mixture model is commonly used for model-based clustering, we propose use of the von Mises mixture model as more befitting circular DOA data than a Gaussian distribution. The EM framework for the von Mises mixture model in a unit hyper sphere is degenerated for the 2D case and used as such in the proposed method. We also use a histogram of the dataset to initialize the number of clusters and the initial values of parameters, thereby saving calculation time and improving the efficiency. Experiments using simulated and real-world datasets demonstrate the performance of the proposed method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제13권1호
• /
• pp.121-126
• /
• 2009

Plane-based computational integral imaging (CIIR) provides the reconstruction of depth-dependent 3D plane images. However, it has problem degrading the resolution of reconstructed images due to the artifact noise according to the depth. In this paper, to overcome this problem, a signal model for plane-based CIIR is explain. Also the compensation process is introduced to remove the noise caused from CIIR. Computational experiments show that we analyze the characteristics of noise in the reconstructed image of 2D Gaussian image and the high-resolution images can be obtained by using the compensation process.

• Communications for Statistical Applications and Methods
• /
• 제12권3호
• /
• pp.545-556
• /
• 2005

Hjort(1990) obtained the nonparametric Bayes estimator $\^{F}_{c,a}$ of $F_0$ with respect to beta processes in the random censorship model. Let $X_1,{\cdots},X_n$ be i.i.d. $F_0$ and let $C_1,{\cdot},\;C_n$ be i.i.d. G. Assume that $F_0$ and G are continuous. This paper shows that {$\^{F}_{c,a}$(u){\|}0 < u < T} converges weakly to a Gaussian process whenever T < $\infty$ and $\~{F}_0({\tau})\;<\;1$.

• ETRI Journal
• /
• 제34권2호
• /
• pp.190-198
• /
• 2012

An adaptive correlation noise model (CNM) construction algorithm is proposed in this paper to increase the efficiency of parity bits for correcting errors of the side information in transform domain Wyner-Ziv (WZ) video coding. The proposed algorithm introduces two techniques to improve the accuracy of the CNM. First, it calculates the mean of direct current (DC) coefficients of the original WZ frame at the encoder and uses it to assist the decoder to calculate the CNM parameters. Second, by considering the statistical property of the transform domain correlation noise and the motion characteristic of the frame, the algorithm adaptively models the DC coefficients of the correlation noise with the Gaussian distribution for the low motion frames and the Laplacian distribution for the high motion frames, respectively. With these techniques, the proposed algorithm is able to make a more accurate approximation to the real distribution of the correlation noise at the expense of a very slight increment to the coding complexity. The simulation results show that the proposed algorithm can improve the average peak signal-to-noise ratio of the decoded WZ frames by 0.5 dB to 1.5 dB.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• 제30A권12호
• /
• pp.43-50
• /
• 1993

Three-dimensional simulator for the ion implantation process is developed. The simulator based on an analytical model which would be a choice with high computational efficiency and accuracy. This is an important issue for the simulation of a numerous number of processing steps required in the fabrication of ULSI or GSI. The model can explain scattering and bulk channeling mechanism (1D). It can also explain depth dependent lateral diffusion effect(2D) and mask effect(3D). The model is consist of one-dimensional JPD(Joined Pearson Distribution) function and two-dimensional modified Gaussian functions. Final implanted profiles under typical mask structures such as hole, line and island structure are obtained with varying ion species.