• Journal of Korea Game Society
• /
• v.20 no.3
• /
• pp.75-84
• /
• 2020

This paper introduces an interactive indirect illumination algorithm which considers indirect visibility. First, a small number of rays are emitted on hemisphere of the current pixel to obtain the first intersection. If this point is directly illuminated by the light source, its illuminated color is collected. Second, in order to approximate the indirect visibility, a 3D ray marching algorithm, which is based on a hierarchy structure, is used to accelerate the ray-voxel intersection. Third, the indirect images are denoised by an edge-avoiding filtering with a local means replacement method.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.7
• /
• pp.1117-1122
• /
• 2017

Pedestrian detection is a very important and valuable part of artificial intelligence and computer vision. It can be used in various areas for example automatic drive, video analysis and others. Many works have been done for the pedestrian detection. The accuracy of pedestrian detection on multiple pedestrian image has reached high level. It is not easily get more progress now. This paper proposes a new structure based on the idea of HOG and convolutional filters to do the pedestrian detection in single pedestrian image. It can be a method to increase the accuracy depend on the high accuracy in single pedestrian detection. In this paper, we use Multiblock HOG and magnitude of the pixel as the feature and use convolutional filter to do the to extract the feature. And then use NEWFM to be the classifier for training and testing. We use single pedestrian image of the INRIA data set as the data set. The result shows that the Convolutional Multiblock HOG we proposed get better performance which is 0.015 miss rate at 10-4 false positive than the other detection methods for example HOGLBP which is 0.03 miss rate and ChnFtrs which is 0.075 miss rate.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.08a
• /
• pp.142-145
• /
• 2008

This paper proposes a computationally efficient algorithm for color image segmentation using self-organizing map(SOM) and grassfire algorithm. We reduce a computation time by decreasing the number of input neuron and input data which is used for learning at SOM. First converting input image to CIE $L^*u^*v^*$ color space and run the learning stage with the SOM-input neuron size is three and output neuron structure is 4by4 or 5by5. After learning, compute output value correspondent with input pixel and merge adjacent pixels which have same output value into segment using grassfire algorithm. The experimental results with various images show that proposed method lead to a good segmentation results than others.

• Advances in biomechanics and applications
• /
• v.1 no.1
• /
• pp.67-76
• /
• 2014

Bone properties are one of the key components when constructing models that can simulate the mechanical behavior of a mandible. Due to the complexity of the structure, the tooth, ligaments, different bones etc., some simplifications are often considered and bone properties are one of them. The objective of this study is to understand if a simplification of the problem is possible and assess its influence on mandible behavior. A cadaveric toothless mandible was used to build three computational models from CT scan information: a full cortical bone model; a cortical and cancellous bone model, and a model where the Young's modulus was obtained as function of the pixel value in a CT scan. Twelve muscle forces were applied on the mandible. Results showed that although all the models presented the same type of global behavior and proximity in some locations, the influence of cancellous bone can be seen in strain distribution. The different Young's modulus defined by the CT scan gray scale influenced the maximum and minimum strains. For modeling general behavior, a full cortical bone model can be effective. However, when cancellous bone is included, maximum values in thin regions increase the strain distribution. Results revealed that when properties are assigned to the gray scale some peaks could occur which did not represent the real situation.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.10 no.4
• /
• pp.151-160
• /
• 2014

In this paper, a comparison of superpixel characteristics based on SLIC(simple linear iterative clustering) for several color feature spaces is presented. Computer vision applications have come to rely increasingly on superpixels in recent years. Superpixel algorithms group pixels into perceptually meaningful atomic regions, which can be used to replace the rigid structure of the pixel grid. A superpixel is consist of pixels with similar features such as luminance, color, textures etc. Thus superpixels are more efficient than pixels in case of large scale image processing. Generally superpixel characteristics are described by uniformity, boundary precision and recall, compactness. However previous methods only generate superpixels a special color space but lack researches on superpixel characteristics. Therefore we present superpixel characteristics based on SLIC as known popular. In this paper, Lab, Luv, LCH, HSV, YIQ and RGB color feature spaces are used. Uniformity, compactness, boundary precision and recall are measured for comparing characteristics of superpixel. For computer simulation, Berkeley image database(BSD300) is used and Lab color space is superior to the others by the experimental results.

• Nuclear Engineering and Technology
• /
• v.54 no.2
• /
• pp.601-607
• /
• 2022

In recent years, monitoring of spent nuclear fuel inside dry cask storage has become an important area of national security. Muon tomography is a useful method for monitoring spent nuclear fuel because it uses high energy muons that penetrate deep into the target material and provides a 3-D structure of the inner materials. We designed a muon tomography system consisting of four 2-D position sensitive detector and characterized and optimized the system parameters. Each detector, measuring 200 × 200 cm², consists of a plastic scintillator, wavelength shifting (WLS) fibers and, SiPMs. The reconstructed image is obtained by extracting the intersection of the incoming and outgoing muon tracks using a Point-of-Closest-Approach (PoCA) algorithm. The Geant4 simulation was used to evaluate the performance of the muon tomography system and to optimize the design parameters including the pixel size of the muon detector, the field of view (FOV), and the distance between detectors. Based on the optimized design parameters, the spent fuel assemblies were modeled and the line profile was analyzed to conduct a feasibility study. Line profile analysis confirmed that muon tomography system can monitor nuclear spent fuel in dry storage container.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.6
• /
• pp.309-317
• /
• 2022

In this paper, we propose a machine learning-based copy-move forgery detection network with dual branches. Because the rotation or scaling operation is frequently involved in copy-move forger, the conventional convolutional neural network is not effectively applied in detecting copy-move tampering. Therefore, we divide the input into rotation-invariant and scaling-invariant features based on the wavelet coefficients. Each of the features is input to different branches having the same structure, and is fused in the combination module. Each branch comprises feature extraction, correlation, and mask decoder modules. In the proposed network, VGG16 is used for the feature extraction module. To check similarity of features generated by the feature extraction module, the conventional correlation module used. Finally, the mask decoder model is applied to develop a pixel-level localization map. We perform experiments on test dataset and compare the proposed method with state-of-the-art tampering localization methods. The results demonstrate that the proposed scheme outperforms the existing approaches.

• International Journal of Computer Science & Network Security
• /
• v.23 no.4
• /
• pp.85-94
• /
• 2023

Image halftoning is a technique for varying grayscale images into two-tone binary images. Unfortunately, the static representation of an image-half toning, wherever each pixel intensity is combined by its local neighbors only, causes missing subjective problem. Also, the existing noise causes an instability criterion. In this paper an image half-toning is represented as a dynamical system for recognizing the global representation. Also, noise is reduced based on a probabilistic model. Since image half-toning is considered as 2-D matrix with a full connected pass, this structure is recognized by the dynamical system of Cellular Neural Networks (CNNs) which is defined by its template. Bayesian Rough Sets is used in exploiting the ideal CNNs construction that synthesis its dynamic. Also, Bayesian rough sets contribute to enhance the quality of the halftone image by removing noise and discovering the effective parameters in the CNNs template. The novelty of this method lies in finding a probabilistic based technique to discover the term of CNNs template and define new learning rules for CNNs internal work. A numerical experiment is conducted on image half-toning corrupted by Gaussian noise.

• Nuclear Engineering and Technology
• /
• v.56 no.6
• /
• pp.1975-1988
• /
• 2024

It is important to maintain cladding integrity in spent nuclear fuel management. This study proposes a numerical analysis method to evaluate the fracture resistance of irradiated zirconium alloy cladding under pinch load known to cause Mode-III failure. The mechanical behavior and fracture of the cladding under pinch loading can be evaluated by a Ring Compression Test (RCT). To simulate the fracture of hydride precipitates, zirconium matrix, and Zr/hydride interfaces under the stress field generated by RCT, a micro-structure crack propagation simulation method based on Continuum Damage Mechanics (CDM) has been proposed. Our RCT simulation model was constructed from microscopic images of irradiated cladding. In this study, we developed an automated process to generate a pixel-based finite element model by separating the hydride precipitates, zirconium matrix, and interfaces using an image segmentation method. The appropriate element size was selected to ensure the efficiency and accuracy of a crack propagation simulation. The load-displacement curves and strain energies from RCT were compared and analyzed with the simulation results of different element sizes. The finalized RCT simulation model can be used to establish the failure criterion of fuel rods under pinch loading. The advantages and limitations of the proposed method are fully discussed here.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.4
• /
• pp.567-574
• /
• 2006

This paper focuses on lossy medical image compression methods for medical images that operate on three-dimensional(3-D) irreversible integer wavelet transform. We offer an application of unbalanced tree structure algorithm to medical images, using a 3-D unbalanced wavelet decomposition and a 3-D unbalanced spatial dependence tree. The wavelet decomposition is accomplished with integer wavelet filters implemented with the lifting method. We have tested our encoder on volumetric medical images using different integer filters and 16 coding unit size. The coding unit sizes of 16 slices save considerable dynamic memory(RAM) and coding delay from full sequence coding units used in previous works. If we allow the formation of trees of different lengths, then we can accomodate more transaxial scales than three. Then the encoder and decoder can then keep track of the length of the tree in which each pixel resides through the sequence of decompositions. Results show that, even with these small coding units, our algorithm with I(5,3)filter performs as well and better in lossy coding than previous coding systems using 3-D integer unbalanced wavelet transforms on volumetric medical images.