• Journal of Korea Multimedia Society
• /
• v.20 no.5
• /
• pp.748-757
• /
• 2017

In order to recognize the facial expressions, good features that can express the facial expressions are essential. It is also essential to find the characteristic areas where facial expressions appear discriminatively. In this study, we propose a directional LBP feature for facial expression recognition and a method of finding directional LBP operation and feature region for facial expression classification. The proposed directional LBP features to characterize facial fine micro-patterns are defined by LBP operation factors (direction and size of operation mask) and feature regions through AdaBoost learning. The facial expression classifier is implemented as a SVM classifier based on learned discriminant region and directional LBP operation factors. In order to verify the validity of the proposed method, facial expression recognition performance was measured in terms of accuracy, sensitivity, and specificity. Experimental results show that the proposed directional LBP and its learning method are useful for facial expression recognition.

• Smart Structures and Systems
• /
• v.7 no.5
• /
• pp.329-348
• /
• 2011

Large-scale earthquakes pose serious threats to infrastructure causing substantial damage and large residual deformations. Superelastic (SE) Shape-Memory-Alloys (SMAs) are unique alloys with the ability to undergo large deformations, but can recover its original shape upon stress removal. The purpose of this research is to exploit this characteristic of SMAs such that concrete Beam-Column Joints (BCJs) reinforced with SMA bars at the plastic hinge region experience reduced residual deformation at the end of earthquakes. Another objective is to evaluate the seismic performance of SMA Reinforced Concrete BCJs repaired with flowable Structural-Repair-Concrete (SRC). A $\frac{3}{4}$-scale BCJ reinforced with SMA rebars in the plastic-hinge zone was tested under reversed cyclic loading, and subsequently repaired and retested. The joint was selected from an RC building located in the seismic region of western Canada. It was designed and detailed according to the NBCC 2005 and CSA A23.3-04 recommendations. The behaviour under reversed cyclic loading of the original and repaired joints, their load-storey drift, and energy dissipation ability were compared. The results demonstrate that SMA-RC BCJs are able to recover nearly all of their post-yield deformation, requiring a minimum amount of repair, even after a large earthquake, proving to be smart structural elements. It was also shown that the use of SRC to repair damaged BCJs can restore its full capacity.

• Smart Media Journal
• /
• v.10 no.2
• /
• pp.22-29
• /
• 2021

In the past decade, deep learning has been applied to various medical image analysis tasks. Skeletal bone age estimation is clinically important as it can help prevent age-related illness and pave the way for new anti-aging therapies. Recent research has applied deep learning techniques to the task of bone age assessment and achieved positive results. In this paper, we propose a bone age prediction method using a deep convolutional neural network. Specifically, we first train a classification model that automatically localizes the most discriminative region of an image and crops it from the original image. The regions of interest are then used as input for a regression model to estimate the age of the patient. The experiments are conducted on a whole-body scintigraphy dataset that was collected by Chonnam National University Hwasun Hospital. The experimental results illustrate the potential of our proposed method, which has a mean absolute error of 3.35 years. Our proposed framework can be used as a robust supporting tool for clinicians to prevent age-related diseases.

• Computers and Concrete
• /
• v.30 no.1
• /
• pp.75-83
• /
• 2022

This study introduced a post-tensioned precast concrete system that was developed and designed to improve the performance of joints by post-tensioning. Full-scaled specimens were tested to investigate flexural performances at the negative moment region, where the test variables were the presence of slabs, tendon types, and post-tensioned lengths. A specimen with slabs exhibited significantly higher stiffness and strength values than a specimen without slabs. Thus, it would be reasonable to consider the effects of a slab on the flexural strength for an economical design. A specimen with unbonded mono-tendons had slightly lower initial stiffness and flexural strength values than a specimen with bonded multi-tendons but showed greater flexural strength than the value specified in the design codes. The post-tensioned length was found to have no significant impact on the flexural behavior of the proposed post-tensioned precast concrete system. In addition, a finite element analysis was conducted on the proposed post-tensioned precast concrete system, and the tests and analysis results were compared in detail.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2515-2517
• /
• 2002

The process of character recognition goes through 5 steps; image acquisition, character region extraction, preprocessing, character region segmentation, character recognition. Therefore the final recognition rate of character recognition is directly affected by the performance of each step. This paper is a leading research for object recognition using image processing algorithm which is one of the field of study in computer vision. And this paper will suggest an algorithm to extract the portion of number chain, which is part of the research embodying a system to perceive the data of manufacture and the name of the producer on the wrapping of groceries. In addition, this can extract the number chain comparatively accurate without using many complex algorithm by diving and extracting the moving number region at the same time.

• International journal of advanced smart convergence
• /
• v.11 no.4
• /
• pp.81-87
• /
• 2022

In this paper, we propose a watershed algorithm that applies a high-frequency enhancement filter to emphasize the boundary and a local adaptive threshold to search for minimum points. The previous method causes the problem of over-segmentation, and over- segmentation appears around the boundary of the object, creating an inaccurate boundary of the region. The proposed method applies a high-frequency enhancement filter that emphasizes the high-frequency region while preserving the low-frequency region, and performs a minimum point search to consider local characteristics. When merging regions, a fixed threshold is applied. As a result of the experiment, the proposed method reduced the number of segmented regions by about 58% while preserving the boundaries of the regions compared to when high frequency emphasis filters were not used.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.4
• /
• pp.39-46
• /
• 2009

Many lip region detection methods have been developed in PC environment. But the existing methods are difficult to run on real-time in resource limited mobile devices. To solve the problem, this paper proposes a real-time lip region detection method for lipreading in Mobile device. It detects face region by using adaptive face color information. After that, it detects lip region by using geometrical relation between eyes and lips. The proposed method is implemented in a smart phone with Intel PXA 270 embedded processor and 386MB memory. Experimental results show that the proposed method runs at the speed 9.5 frame/see and the correct detection rate was 98.8% for 574 images.

• The KIPS Transactions:PartB
• /
• v.15B no.3
• /
• pp.189-196
• /
• 2008

In this paper, a CMOS digital image sensor, which consists of A/D conversion, motion estimation circuits, and an attention module for ROI (Region of Interest) detection is presented. The functions of A/D conversion and motion estimation are implemented by $0.6{\mu}m$ CMOS processing circuit as hardware, and the attention module is implemented outside the circuit as software currently. Attention modules are taken to improve limited applications of the smart image sensor. The current smart image sensor responses to the changes of intensity, and uses the integration time to estimate motion. Therefore it is limited in its applications. To make up for inherent property of the sensor from circuit design and extend its applications we decide to introduce perception solutions to the image sensor. Attention modules for still and moving images are employed to achieve such purposes. The suggested approach makes the smart image sensor available with additional functions for such cases that motion estimation or intensity changes are not observed. Experimental result shows the usefulness and extension of the image sensor.

• BMB Reports
• /
• v.46 no.5
• /
• pp.282-287
• /
• 2013

Cecropin A and papiliocin are novel 37-residue cecropin-like antimicrobial peptides isolated from insect. We have confirmed that papiliocin possess high bacterial cell selectivity and has an ${\alpha}$-helical structure from $Lys^3$ to $Lys^{21}$ and from $Ala^{25}$ to $Val^{35}$, linked by a hinge region. In this study, we demonstrated that both peptides showed high antimicrobial activities against multi-drug resistant Gram negative bacteria as well as fungi. Interactions between these cecropin-like peptides and phospholipid membrane were studied using CD, dye leakage experiments, and NMR experiments, showing that both peptides have strong permeabilizing activities against bacterial cell membranes and fungal membranes as well as $Trp^2$ and $Phe^5$ at the N-terminal helix play an important role in attracting cecropin-like peptides to the negatively charged bacterial cell membrane. Cecropin-like peptides can be potent peptide antibiotics against multi-drug resistant Gram negative bacteria and fungi.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.4
• /
• pp.31-36
• /
• 2018

The tourism industry has a great influence on national economy activation. The development of IT technology has enabled the collection and analysis of personal profile information, location information and activity information based on the characteristics, behavior, purchase propensity and interest of tourists. In order to realize this, the implementation of convergence smart tourism information service platform is completed by developing business model, IoT & Big Data integration management system, big data algorithm development and analysis platform in three stages. The underlying technology of the platform and algorithm needs a process of adopting open source, expanding the service element on the basis of it, and then complementing the problem through the test-bed demonstration test that connects the area. Using this platform, it is possible to develop a smart tourism environment that can provide customized services for each tourist by analyzing various information in an integrated manner. Also, it will be possible to improve the life of tourist destination residents and contribute to regional revitalization and job creation through the creation of smart tourism ecosystem focused on the region.