• Review of KIISC
• /
• v.29 no.3
• /
• pp.44-50
• /
• 2019

최근 딥러닝 기술은 다양한 분야에서 놀라운 성능을 보여주고 있어 많은 서비스에 적용되고 있다. 얼굴인식 또한 딥러닝 기술을 접목하여 높은 수준으로 얼굴인식이 가능해졌다. 하지만 딥러닝 기술은 원본 이미지를 최소한으로 변조시켜 딥러닝 모델의 오인식을 발생시키는 적대적 예제에 취약하다. 이에 따라, 본 논문에서는 딥러닝 기반 얼굴인식 시스템에 대해 적대적 예제를 이용하여 기만공격 실험을 수행하였으며 실제 얼굴에 분장할 수 있는 영역을 고려하여 설정된 변조 영역에 따른 기만공격 성능을 분석한다.

• 프린팅코리아
• /
• s.58
• /
• pp.151-153
• /
• 2007

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.7
• /
• pp.3454-3459
• /
• 2013

Sumi-e is one of the art work that uses not only ink line but also color painting. This technique is well known as a representative Asian painting style and widely used in movie, advertisement poster and various effect in camera device. In this paper, we propose an algorithm that can generate result image with Sumi-e effects of example image based on computer graphics and image processing techniques. For this, we pass two steps. The first is painting expression step. We used texture transfer technique to generate result with texture effect of reference image by analyzing numerically. The second step is ink-painting effect generation step. We express ink-painting effect in outline by considering intensity variation in edge of example image. Our algorithm can express various Sumi-e style based on selected reference image. So it can be utilized to various contents generating research.

• Journal of KIISE
• /
• v.44 no.9
• /
• pp.986-991
• /
• 2017

In this paper, we present a method for synthesizing imperative programs from input-output examples. Given (1) a set of input-output examples, (2) an incomplete program, and (3) variables and integer constants to be used, the synthesizer outputs a complete program that satisfies all of the given examples. The basic synthesis algorithm enumerates all possible candidate programs until the solution program is found (enumerative search). However, it is too slow for practical use due to the huge search space. To accelerate the search speed, our approach uses code optimization and avoids unnecessary search for the programs that are syntactically different but semantically equivalent. We have evaluated our synthesis algorithm on 20 introductory programming problems, and the results show that our method improves the speed of the basic algorithm by 10x on average.

• Journal of Korean Society of Steel Construction
• /
• v.24 no.1
• /
• pp.91-99
• /
• 2012

In recently, the vibration control of adjacent buildings have been studied and magneto-rheological(MR) fluid dampers have been applied to seismic response control. MR dampers can be controlled with small power supplies and the dynamic range of this damping force is quite large. This MR damper is one of semi-active dampers as a new class of smart dampers. In this study, vibration control effect according to the installation location of the MR damper connected adjacent buildings has been investigated. Adjacent building structures with different natural frequencies were used as example structures. Groundhook control model is applied to determinate control force of MR damper. In this numerical analysis, it has been shown that displacement responses can be effectively controlled as adjacent buildings are connected at roof floors by MR damper. And acceleration responses can be effectively reduced when two buildings are connected at the mid-stories of adjacent buildings by MR damper. Therefore, the installation floor of the MR damper should be selected with seismic response control target.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.744-748
• /
• 2008

In this paper, we propose a novel technique that generate a new song with given example songs. Our system use k-th order Markov chain of which each state represents notes in a measure. Because we have to consider very high-dimensional space if we use notes in a measure as a state of Markov chain directly, we exploit a hierarchical clustering technique for given example songs to use each cluster as a state. Each given examples can be represented as sequences of cluster ID, and we use them for training data of the Markov chain. The resulting Markov chain effectively gives new song similar to given examples.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.369-372
• /
• 2011

본 논문에서는 가상 시점 생성 시 발생하는 홀 영역의 메움 기법에 관하여 기하학적 제약조건을 이용한 예제 기반 영상 인페인팅 기술을 제안한다. 생성된 가상 시점이 실제 카메라들의 중간에 위치하는 경우, 이 때 발생하는 홀 영역은 시점 간 보상으로 메울 수 있다. 하지만, 가상 시점이 실제 카메라들의 Field-of-View를 벗어난 경우에는 홀 영역에 대한 정보가 없기 때문에 이를 메우는데 어려운 문제가 따른다. 이러한 문제를 해결하기 위해 제안한 방법은 예제 기반의 영상 인페인팅 기술을 이용하여 홀 영역을 메운다. 제안한 방법은 홀 영역의 기하학적 특성을 제약조건으로 우선순위(Priority)를 계산한다. 최적의 패치를 찾기 위해 컬러 정보뿐만 아니라 깊이 정보(Depth)를 활용한다. 또한, 전경 물체의 텍스쳐로 인하여 잘못된 패치가 선택되는 문제를 해결하기 위해 적응적으로 패치 크기를 변경한다. 실험 결과에서 제안한 방법은 일반적인 홀 메움 방식과 비교하여 객관적 평가와 주관적 평가 모두에서 시각적으로 우수한 결과를 보여주었다.

• Journal of Korea Game Society
• /
• v.9 no.1
• /
• pp.127-134
• /
• 2009

This paper presents a motion generation technique for arbitrary morphologies with the user defined correspondences between joints. Users can define the controlling part in the source character and the part to be controlled in the target character in our system. To remove the restriction in the morphology of the target character, we use the pair of example posture sets. In our system, in order to provide the correspondence regardless of the number of joints, the deformed part in the target character is simplified into the direction vector. The final postures are then generated with the weighted sum of the examples. Our experimental results demonstrate that our approach can generate motions for various target characters and can control the user defined joints in real-time.

• Journal of the Korea Computer Graphics Society
• /
• v.22 no.1
• /
• pp.1-8
• /
• 2016

We propose a novel framework for controlling various and complex models using primitive model. To control original model, first we correspond original model to simplified primitive model that contains original model. After doing deformable simulation with primitive model, we compute original model by inversion of result. Since existing method can only control one type formed models, our method - which can control all difference formed models by only one primitive model - has contribution. In conclusion, we show results that efficiently and intuitionally control the various deformable models by using one example primitive model.

• Journal of Practical Engineering Education
• /
• v.8 no.2
• /
• pp.95-101
• /
• 2016

In this paper, we introduce an implementation method of switch-based LED (Light Emitting Diode) Art logic circuits to help understanding the operation principle of digital logic circuits. Digital logic circuit practice using bread board is widely practiced in colleges or high schools in South Korea. However, actual digital logic circuit practice lacks examples of basic implementation, and as results of this problem, study with more complicated examples disturbs understanding the basic operation principle of digital logic circuits. Therefore, we proposed and tested an implementation method of switch-based LED Art logic circuits to help understanding the necessity of digital logic circuits which control signals of multiple output devices simultaneously.