• Journal of KIISE:Software and Applications
• /
• v.36 no.11
• /
• pp.947-954
• /
• 2009

This paper proposes a novel method that reconstructs a surfel-based object by using visual hull from multiple images. The surfel is a point primitive that effectively approximates point-set surface. We create the surfel representation of an object from images by combining the LDC(Layered Depth Cube) surfel sampling with the concept of visual hull that represents the approximated shape from input images. Because the surfel representation requires relatively smaller memory resources than the polygonal one and its LDC resolution is freely changed, we can control the reconstruction quality of the target object and acquire the maximal quality on the given memory resource.

• Journal of Korea Multimedia Society
• /
• v.9 no.3
• /
• pp.287-295
• /
• 2006

This paper compares two different approaches based on wavelet and Gabor decomposition towards representing the texture of an arbitrary region. The Gabor-domain mean and standard deviation combination is considered to be best in representing the texture of rectangular regions. However, texture representation of arbitrary regions would enable generalized object-based image retrieval and other applications in the future. In this study, we have found that the wavelet features perform better than the Gabor features in representing the texture of arbitrary regions. Particularly, the wavelet-domain standard deviation and entropy combination results in the best retrieval accuracy. Based on our experiment with texture image sets, we present and compare tile retrieval accuracy of multiple wavelet and Gabor feature combinations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.5
• /
• pp.2539-2554
• /
• 2017

Regression-based image super resolution (SR) methods have shown great advantage in time consumption while maintaining similar or improved quality performance compared to other learning-based methods. In this paper, we propose a novel single image SR method based on hierarchical regression to further improve the quality performance. As an improvement to other regression-based methods, we introduce a hierarchical scheme into the process of learning multiple regressors. First, training samples are grouped into different clusters according to their geometry similarity, which generates the structure layer. Then in each cluster, a compact dictionary can be learned by Sparse Coding (SC) method and the training samples can be further grouped by dictionary atoms to form the detail layer. Last, a series of projection matrixes, which anchored to dictionary atoms, can be learned by linear regression. Experiment results show that hierarchical scheme can lead to regression that is more precise. Our method achieves superior high quality results compared with several state-of-the-art methods.

• Journal of Korea Multimedia Society
• /
• v.20 no.2
• /
• pp.126-133
• /
• 2017

The conventional hand-crafted features used to track objects have limitations in object representation. Convolutional neural networks, which show good performance results in various areas of computer vision, are emerging as new ways to break through the limitations of feature extraction. CNN extracts the features of the image through layers of multiple layers, and learns the kernel used for feature extraction by itself. In this paper, we use the feature map extracted from the convolution layer of the convolution neural network to create an outline model of the object and use it for tracking. We propose a method to adaptively update the outline model to cope with various environment change factors affecting the tracking performance. The proposed algorithm evaluated the validity test based on the 11 environmental change attributes of the CVPR2013 tracking benchmark and showed excellent results in six attributes.

• Journal of the Korea Computer Graphics Society
• /
• v.24 no.1
• /
• pp.9-16
• /
• 2018

In this paper, we introduce a visualization framework for cell image data obtained from optical diffraction tomography (ODT), including a method for representing cell morphology in 3D virtual environment and a color mapping protocol. Unlike commonly known volume data sets, such as CT images of human organ or industrial machinery, that have solid structural information, the cell image data have rather vague information with much morphological variations on the boundaries. Therefore, it is difficult to come up with consistent representation of cell structure for visualization results. To obtain desired visual representation of cellular structures, we propose an interactive visualization technique for the ODT data. In visualization of 3D shape of the cell, we adopt a volume rendering technique which is generally applied to volume data visualization and improve the quality of volume rendering result by using empty space jittering method. Furthermore, we provide a layer-based independent rendering method for multiple transfer functions to represent two or more cellular structures in unified render window. In the experiment, we examined effectiveness of proposed method by visualizing various type of the cell obtained from the microscope which can capture ODT image and fluorescence image together.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1994.10a
• /
• pp.670-675
• /
• 1994

Yhis paper describes a fault diagnosis simulation of the Real-Time Multiple Fault Dignosis System (RTMFDS) for forcasting faults in a system and deciding current machine state from signal information. Comparing with other diagnosis system for single fault,the system developed deals with multiple fault diagnosis,comprising two main parts. One is a remotesignal generating and transimission terminal and the other is a host system for fault diagnosis. Signal generator generate the random fault signal and the image information, and send this information to host. Host consists of various modules and agents such as Signal Processing Module(SPM) for sinal preprocessing, Performence Monotoring Module(PMM) for subsystem performance monitoring, Trigger Module(TM) for multi-triggering subsystem fault diagnosis, Subsystem Fault Diagnosis Agent(SFDA) for receiving trigger signal, formulating subsystem fault D\ulcornerB and initiating diagnosis, Fault Diagnosis Module(FDM) for simulating component fault with Hierarchical Artificial Neural Network (HANN), numerical models and Hofield network,Result Agent(RA) for receiving simulation result and sending to Treatment solver and Graphic Agent(GA). Each agent represents a separate process in UNIX operating system, information exchange and cooperation between agents was doen by IPC(Inter Process Communication : message queue, semaphore, signal, pipe). Numerical models are used to deseribe structure, function and behavior of total system, subsystems and their components. Hierarchical data structure for diagnosing the fault system is implemented by HANN. Signal generation and transmittion was performed on PC. As a host, SUN workstation with X-Windows(Motif)is used for graphic representation.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.6
• /
• pp.2917-2921
• /
• 2016

Background: To explore factors that influence quality of life (QOL) in patients receiving breast conserving therapy (BCT). Materials and Methods: In this sequential mixed methods study, 118 women from Songklanagarind Hospital were included. We used participants' characteristics, Body Image Scale (BIS), and Functional Assessment of Cancer Therapy with the Breast Cancer Subscale (FACT-B) for analysis. The BIS transformed into presence of body image disturbance (BID). Factors that influenced QOL were determined by stepwise multiple linear regression. Forty-one participants were selected for qualitative analysis. Our female researcher performed the semi-structured interviews with questions based on the symbolic interaction theory. Final codes were analysed using thematic analysis along with investigator triangulation methods. Results: Ninety percent had early stage breast cancer with post-completed BCT, for an average of 2.7 years. The median BIS score and FACT-B score were 2 (IQR=10) and 130 (IQR=39). In the regression analysis, an age of more than 50 years and BID were significant factors. As for the value of conserved breasts, two themes emerged: a conserved breast is an essential part of a participant's life and also the representation of her womanhood; the importance of a breast is related to age. Conclusions: Body image influenced QOL in post BCT participants. The conserved breasts also lead to positive and better impact on their body image as an essential part of their life.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.1
• /
• pp.31-40
• /
• 2024

Recently, static analysis-based signature and pattern detection technologies have limitations due to the advanced IT technologies. Moreover, It is a compatibility problem of multiple architectures and an inherent problem of signature and pattern detection. Malicious codes use obfuscation and packing techniques to hide their identity, and they also avoid existing static analysis-based signature and pattern detection techniques such as code rearrangement, register modification, and branching statement addition. In this paper, We propose an LLVM IR image-based automated static analysis of malicious code technology using machine learning to solve the problems mentioned above. Whether binary is obfuscated or packed, it's decompiled into LLVM IR, which is an intermediate representation dedicated to static analysis and optimization. "Therefore, the LLVM IR code is converted into an image before being fed to the CNN-based transfer learning algorithm ResNet50v2 supported by Keras". As a result, we present a model for image-based detection of malicious code.

• Journal of the Optical Society of Korea
• /
• v.12 no.2
• /
• pp.98-102
• /
• 2008

Optical Coherence Tomography (OCT) is an important noninvasive medical imaging technique that can reveal subsurface structures of biological tissue. OCT has demonstrated a good correlation with histology in sufficient resolution to identify morphological changes in articular cartilage to differentiate normal through progressive stages of degenerative joint disease. Current OCT systems provide individual cross-sectional images that are representative of the tissue directly under the scanning beam, but they may not fully demonstrate the degree of degeneration occurring within a region of a joint surface. For a full understanding of the nature and degree of cartilage degeneration within a joint, multiple OCT images must be obtained and an overall assessment of the joint surmised from multiple individual images. This study presents frequency domain three-dimensional (3-D) OCT imaging of degenerative joint cartilage extracted from bovine knees. The 3-D OCT imaging of articular cartilage enables the assembly of 126 individual, adjacent, rapid scanned OCT images into a full 3-D image representation of the tissue scanned, or these may be viewed in a progression of successive individual two-dimensional (2-D) OCT images arranged in 3-D orientation. A fiber-based frequency domain OCT system that provides cross-sectional images was used to acquire 126 successive adjacent images for a sample volume of $6{\times}3.2{\times}2.5\;mm^3$. The axial resolution was $8\;{\mu}m$ in air. The 3-D OCT was able to demonstrate surface topography and subsurface disruption of articular cartilage consistent with the gross image as well as with histological cross-sections of the specimen. The 3-D OCT volumetric imaging of articular cartilage provides an enhanced appreciation and better understanding of regional degenerative joint disease than may be realized by individual 2-D OCT sectional images.

• The KIPS Transactions:PartB
• /
• v.10B no.5
• /
• pp.543-552
• /
• 2003

An increasing in quantity of multimedia data brought a new problem that expected data should be retrieved fast and exactly. The adequate representation is a key element for the efficient retrieval. For this reason, MPEG-7 standard was established for description of multimedia data in 2001. However, the content of the standard is massive and the approach method is not clear for real application system yet, because of properties of MPEG-7 standard that has to include a lot of potential cases. In this paper, we suggested implementation scheme of retrieval system with using of only visual descriptors and presented the performance results of developed system. From the result of developed system, MPEG-7 VIRS (Video/Image Retrieval System), we analyzed the retrieval results between using individual descriptor and using multiple descriptors, and showed a layout for real application system.