• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.3
• /
• pp.449-458
• /
• 2023

Artificial Intelligence is providing convenience in various fields using big data and deep learning technologies. However, deep learning technology is highly vulnerable to adversarial examples, which can cause misclassification of classification models. This study proposes a method to detect and purification various adversarial attacks using StarGAN. The proposed method trains a StarGAN model with added Categorical Entropy loss using adversarial examples generated by various attack methods to enable the Discriminator to detect adversarial examples and the Generator to purification them. Experimental results using the CIFAR-10 dataset showed an average detection performance of approximately 68.77%, an average purification performance of approximately 72.20%, and an average defense performance of approximately 93.11% derived from restoration and detection performance.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.6 s.312
• /
• pp.43-51
• /
• 2006

This paper proposes a metrics for example matching under the example-based machine translation for English-Korean machine translation. Our metrics served as similarity measure is based on edit-distance algorithm, and it is employed to retrieve the most similar example sentences to a given query. Basically it makes use of simple information such as lemma and part-of-speech information of typographically mismatched words. Edit-distance algorithm cannot fully reflect the context of matched word units. In other words, only if matched word units are ordered, it is considered that the contribution of full matching context to similarity is identical to that of partial matching context for the sequence of words in which mismatching word units are intervened. To overcome this drawback, we propose the context-weighting scheme that uses the contiguity information of matched word units to catch the full context. To change the edit-distance metrics representing dissimilarity to similarity metrics, to apply this context-weighted metrics to the example matching problem and also to rank by similarity, we normalize it. In addition, we generalize previous methods using some linguistic information to one representative system. In order to verify the correctness of the proposed context-weighted metrics, we carry out the experiment to compare it with generalized previous methods.

• The KIPS Transactions:PartB
• /
• v.17B no.4
• /
• pp.295-302
• /
• 2010

Example-based super resolution(EBSR) is a method to reconstruct high-resolution images by learning patch-wise correspondence between high-resolution and low-resolution images. It can reconstruct a high-resolution from just a single low-resolution image. However, when it is applied to a text image whose font type and size are different from those of training images, it often produces lots of noise. The primary reason is that, in the patch matching step of the reconstruction process, input patches can be inappropriately matched to the high-resolution patches in the patch dictionary. In this paper, we propose a new patch matching method to overcome this problem. Using an image observation model, it preserves the correlation between the input and the output images. Therefore, it effectively suppresses spurious noise caused by inappropriately matched patches. This does not only improve the quality of the output image but also allows the system to use a huge dictionary containing a variety of font types and sizes, which significantly improves the adaptability to variation in font type and size. In experiments, the proposed method outperformed conventional methods in reconstruction of multi-font and multi-size images. Moreover, it improved recognition performance from 88.58% to 93.54%, which confirms the practical effect of the proposed method on recognition performance.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.475-480
• /
• 2007

대화관리시스템은 사용자 발화로부터 사용자의 의도를 추론하여 시스템의 응답을 결정하고 이를 사용자에게 자연스러운 형태로 반환하는 역할을 한다. 본 논문에서는 마르코프 의사 결정과정에 기반한 대화관리자를 통하여 정확한 동작 수행과 사용자의 자연스러운 발화를 가능케 하는 대화관리시스템에 대해서 소개한다. 마르코프 의사 결정과정 대화관리자는 실세계 환경을 모델링 하는 유한 개수의 상태들과 이를 이용한 통계적 학습을 통해 시스템 응답을 결정 한다. 본 대화관리시스템은 대화관리자 이외에 언어이해부, 영역규칙 적용부, 목적시스템 제어부, 예제기반 응답생성부로 이루어져 있으며, 각 구성요소는 영역이식에 용이하도록 설계되어 있다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.371-375
• /
• 2008

예제 기반 학습(instance-based learning) 방법 중 하나인 k-최근접 이웃(k-nearest reighbor, k-NN) 학습은 간단하고 예측 정확도가 비교적 높아 분류 및 회귀 문제 해결을 위한 기반 방법론으로 널리 적용되고 있다. k-NN 학습을 위한 알고리즘은 기본적으로 유클리드 거리 혹은 2-놈(norm)에 기반하여 학습예제들 사이의 거리를 계산한다. 본 논문에서는 유클리드 거리를 일반화한 개념인 p-놈의 사용이 k-NN 학습의 성능에 어떠한 영향을 미치는지 연구하였다. 구체적으로 합성데이터와 다수의 기계학습 벤치마크 문제 및 실제 데이터에 다양한 p-놈을 적용하여 그 일반화 성능을 경험적으로 조사하였다. 실험 결과, 데이터에 잡음이 많이 존재하거나 문제가 어려운 경우에 p의 값을 작게 하는 것이 성능을 향상시킬 수 있었다.

• 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.

• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.186-189
• /
• 2019

Image inpainting is an image processing technique that restores an image by naturally filling the empty or damaged regions in an image. In this paper, we present a new image inpainting technique that can suppress the generation of texture garbage which is one of the artifacts of existing exemplar-based image inpainting. Unlike the existing technique, only the stationary source patch is sampled as the exemplar patch based on the assumption of spatial stationarity of the texture. This prevents the texture garbage, which is an inconsistent piece of texture from being copied to the target region. Experimental results show that the texture synthesis using the proposed method produces more natural inpainting results than the existing method.

• Journal of KIISE:Software and Applications
• /
• v.37 no.2
• /
• pp.129-136
• /
• 2010

In this paper, we present an Example-based Dialogue System for English conversation tutoring. It aims to provide intelligent one-to-one English conversation tutoring instead of old fashioned language education with static multimedia materials. This system can understand poor expressions of students and it enables green hands to engage in a dialogue in spite of their poor linguistic ability, which gives students interesting motivation to learn a foreign language. And this system also has educational functionalities to improve the linguistic ability. To achieve these goals, we have developed a statistical natural language understanding module for understanding poor expressions and an example-based dialogue manager with high domain scalability and several effective tutoring methods.

• 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.