• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2003년도 가을 학술발표논문집 Vol.30 No.2 (1)
• /
• pp.4-6
• /
• 2003

A holistic representation, such as sparse ceding or independent component analysis (ICA), was successfully applied to explain early auditory processing and sound classification. In contrast, Part-based representation is an alternative way of understanding object recognition in brain. In this paper. we employ the non-negative matrix factorization (NMF)［1］which learns parts-based representation for sound classification. Feature extraction methods from spectrogram using NMF are explained. Experimental results show that NMF-based features improve the performance of sound classification over ICA-based features.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권10호
• /
• pp.1412-1417
• /
• 2004

전체관적인 표현방법인 희소 코딩 또는 독릴 성분 분해(ICA)는 이전의 청각의 처리와 소리 분류의 작업을 해명하는데 성공적으로 적용되었다. 반대로 부분 기반 표현법은 뇌에서 물체를 인식하는 방법을 이해하는 또 다른 방법이다. 이 논문에서, 우리는 소리 분류의 작업에 부분기반 표현법을 학습시키는 비음수화 행렬 분해(NMF)(1) 방법을 적용하였다. 잡음이 존재할 때와 존재하지 않을 때 두 가지 상황에서, NMF를 이용하여 주파수-시간영역의 소리로부터 특징을 추출하는 방법을 설명한다. 실험결과에서는 NMF에 기반을 둔 특징이 ICA에 기반을 두어 추출한 특징보다 소리 분류의 성능을 향상시킴을 보여준다.

• Journal of International Society for Simulation Surgery
• /
• 제3권2호
• /
• pp.46-48
• /
• 2016

Purpose In face reocognition area, estimating occlusion in face images is on the rise. In this paper, we propose a new face recognition algorithm based on dual sparse representation to solve this problem. Method Each face image is partitioned into several pieces and sparse representation is implemented in each part. Then, some parts that have large sparse concentration index are combined and sparse representation is performed one more time. Each test sample is classified by using the final sparse coefficient where correlation between the test sample and training sample is applied. Results The recognition rate of the proposed algorithm is higher than that of the basic sparse representation classification. Conclusion The proposed method can be applied in real life which needs to identify someone exactly whether the person disguises his face or not.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제33권5호
• /
• pp.481-488
• /
• 2006

부공간 투영기술(subspace projection)을 이용한 얼굴인식기술의 성능은 이들 기저영상들(basis images)의 특징과 밀접한 관련이 있다. 특히 표정변화와 같은 국부적 왜곡이나 오클루전이 있는 경우의 인식성능은 기저영상들의 특징에 의해 영향을 받게 된다. 부공간 투영기반의 얼굴인식 방법이 오클루전이나 표정변화와 같은 국부적인 왜곡발생에 강인하려면 부분국부적 표현(part-based local representation)의 기저벡터를 갖는 것이 중요하다. 본 연구에서는 국부적 왜곡과 오클루전에 강인한 효과적인 부분국부적 표현방법을 제안한다. 제안한 방법을 LS-ICA(locally salient ICA) 방법이라고 명명하였다. LS-ICA방법은 ICA 구조I의 기저영상을 구하는 과정에서 공간적인 국부성(locality)의 제약조건을 부과함으로써 부분국부적 기저영상(part-based local basis images)을 얻는 방법이다. 결과적으로 공간적으로 현저한 특징만을 포함하는 기저영상을 사용하게 되며, 이는 "Recognition by Parts"의 방법론과 유사하다. LS-ICA방법과 LNMF(Localized Non-negative Matrix Factorization)와 LFA(Local Feature Analysis)와 같은 기존의 부분 표현방법(part-based representation)들에 대해 다양한 얼굴영상 데이타베이스를 사용하여 실험한 결과, LS-ICA방법이 기존의 방법에 비하여 높은 인식성능을 보였으며, 특히 오클루전이나 국부적인 변형이 포함된 얼굴영상에서 뛰어난 인식성능을 보였다.

• 대한지구과학교육학회지
• /
• 제3권1호
• /
• pp.1-8
• /
• 2010

The purpose of this study was to analysis the 6th students' conceptions of the nature phenomenon focused on the systematic characteristics. For this study, 12 students of the 6th grades participated in special class for testing their conceptions about the water cycle in the earth system. And we analyzed the outcomes of students' conceptions based on SBF conceptual representation. The results indicate that most of the subjects perceived that the water cycle in earth system wasn't complex system maintaining its existence and functions as a whole through the interaction of its parts but simple system maintaining some actions between atmosphere and hydrosphere, geosphere, biosphere(biological world). And they didn't perceive the characteristics of the water cycle whose all parts must be presented the change of volume between vapor and water, glacier proposing the total hydro-volume are established in the earth system. Based on the results, it was suggested that the main goals of the schools' science education should be to provide students who understand the water cycle system as attaching importance to form with the skills needed to coherent understanding of the essential qualities for the nature phenomenon system.

• 한국정보보호학회:학술대회논문집
• /
• 한국정보보호학회 2006년도 하계학술대회
• /
• pp.251-257
• /
• 2006

The performance of face recognition methods using subspace projection is directly related to the characteristics of their basis images, especially in the cases of local distortion or partial occlusion. In order for a subspace projection method to be robust to local distortion and partial occlusion, the basis images generated by the method should exhibit a part-based local representation. We propose an effective part-based local representation method named locally salient ICA (LS-ICA) method for face recognition that is robust to local distortion and partial occlusion. The LS-ICA method only employs locally salient information from important facial parts in order to maximize the benefit of applying the idea of 'recognition by parts.' It creates part-based local basis images by imposing additional localization constraint in the process of computing ICA architecture I basis images. We have contrasted the LS-ICA method with other part-based representations such as LNMF (Localized Non-negative Matrix Factorization)and LFA (Local Feature Analysis). Experimental results show that the LS-ICA method performs better than PCA, ICA architecture I, ICA architecture II, LFA, and LNMF methods, especially in the cases of partial occlusions and local distortion

• 한국산학기술학회논문지
• /
• 제16권5호
• /
• pp.3000-3005
• /
• 2015

신뢰할 수 있는 공정 감시와 진단은 생산 공정의 안전과 최종제품의 품질을 보장이라는 관점에서 중요하다. 공정진단의 목적은 특정한 공정 이상의 원인을 밝혀내는 것이다. 본 연구에서는 분류기법에 기반한 공정진단 체계를 제시한다. 여기서는 공정데이터를 비선형 데이터 표현기법을 통해 변환함으로써 데이터의 크기를 줄이며 효율적인 데이터 표현이 가능하다. 추가적인 단계로서 공정 데이터의 전처리 과정을 통해 진단에 무관한 공정 패턴을 제거하고 진단 성능을 높이고자 한다. 진단 성능을 평가하기 위해 회분식 공정에 대한 사례연구를 수행한 결과 기존 선형 진단 방법론 및 전처리 과정이 없는 방법론에 비해 향상된 진단 결과를 얻을 수 있었다.

• 전자공학회논문지
• /
• 제54권3호
• /
• pp.55-62
• /
• 2017

비음수 행렬 분해 기법(non-negative matrix factorization)은 대표적인 부분 영역 기반 표현 기법의 하나로 영상의 부분적인 특징을 나타내는 기저 벡터의 선형 조합으로 영상을 표현하는 기법이다. 본 논문에서는 여러 가지 비음수 행렬 분해 기법을 이용하여 얼굴 영상을 표현하고, 추출된 특징을 기반으로 학습 벡터 양자화를 이용하여 얼굴 인식을 수행하였다. 추출된 각 기법의 기저 벡터를 비교하여 각 기법의 특징을 분석하였다. 또한 NMF 기법들의 인식율 검증을 통해 비음수 행렬 기법의 얼굴 인식에 대한 활용 가능성을 확인하였다.

• International journal of advanced smart convergence
• /
• 제8권1호
• /
• pp.141-146
• /
• 2019

These days, there are many applications using neural networks as parts of their system. On the other hand, adversarial examples have become an important issue concerining the security of neural networks. A classifier in neural networks can be fooled and make it miss-classified by adversarial examples. There are many research to encounter adversarial examples by using denoising methods. Some of them using GAN (Generative Adversarial Network) in order to remove adversarial noise from input images. By producing an image from generator network that is close enough to the original clean image, the adversarial examples effects can be reduced. However, there is a chance when adversarial noise can survive the approximation process because it is not like a normal noise. In this chance, we propose a research that utilizes high-level representation in the classifier by combining GAN network with a trained U-Net network. This approach focuses on minimizing the loss function on high representation terms, in order to minimize the difference between the high representation level of the clean data and the approximated output of the noisy data in the training dataset. Furthermore, the generated output is checked whether it shows minimum error compared to true label or not. U-Net network is trained with true label to make sure the generated output gives minimum error in the end. At last, the remaining adversarial noise that still exist after low-level approximation can be removed with the U-Net, because of the minimization on high representation terms.

• 한국CDE학회논문집
• /
• 제5권2호
• /
• pp.103-112
• /
• 2000

CAD databases are the core element to the management of product information. A key to the successful use of the databases is a rational method of query to and retrieval from the databases. Although it is parts geometry that users eager to retrieve from the CAD databases, no system yet supports geometry-based query. This paper aims at developing a new method of assessing geometric similarity which can serve as the basis of geometric query for CAD database. The proposed method uses ASVP (Alternating Sums of Volumes with Partitioning) decomposition that is a volumetric representation of a part obtained from its boundary representation. A measure of geometric similarity between two solid models is defined on their ASVP tree representations. The measure can take into account overall shapes of parte, shapes of features and their locations. Several properties that a similarity measure needs to satisfy are discussed. The geometric query developed in this paper can be used in a wide range of applications using CAD databases, which include similarity-based design retrieval, variant process planning, and components selection from part library. An experiment has been carried out to demonstrate the effectiveness of the method, and the results are presented.