• 한국지능시스템학회논문지
• /
• 제22권3호
• /
• pp.319-327
• /
• 2012

본 논문에서는 착용식 추적장치나 표식 등의 보조 도구를 사용하지 않는 환경의 동영상 데이터로부터 수화 패턴을 인식하는 방법론에 관하여 고찰한다. 시스템 설계 및 구현에 관한 주제로서 특징점의 추출기법, 특징데이터의 표현기법 및 패턴 분류기법에 관한 방법론을 제시하고 그 유용성을 고찰한다. 일련의 동영상으로 표현되는 수화패턴에 대하여 특징점의 공간적 위치에 대한 변이 뿐만 아니라 시간차원의 변화를 고려한 특징데이터의 표현방법을 제시하며, 방대한 데이터에 의한 분류기의 크기 문제와 계산량의 문제를 개선하기 위하여 효과적으로 특징수를 줄일 수 있는 특징추출 방법을 소개한다. 패턴 분류과정에서 점진적 학습(incremental learning)이 가능한 신경망 모델을 제시하고 그 동작특성 및 학습효과를 분석한다. 또한 학습된 분류모델로부터 특징과 패턴 클래스 간의 상대적 연관성 척도를 정의하고, 이로부터 효과적인 특징을 선별하여 성능저하 없이 분류기의 규모를 최적화 할 수 있음을 보인다. 제안된 내용에 대하여 여섯 가지 수화패턴을 대상으로 적용한 실험을 통하여 유용성을 평가한다.

• Journal of Electrical Engineering and Technology
• /
• 제12권1호
• /
• pp.402-410
• /
• 2017

For many years, researchers in face description area have been representing and recognizing faces based on different methods that include subspace discriminant analysis, statistical learning and non-statistics based approach etc. But still automatic face recognition remains an interesting but challenging problem. This paper presents a novel and efficient face image representation method based on Optimized Local Ternary Pattern (OLTP) texture features. The face image is divided into several regions from which the OLTP texture feature distributions are extracted and concatenated into a feature vector that can act as face descriptor. The recognition is performed using nearest neighbor classification method with Chi-square distance as a similarity measure. Extensive experimental results on Yale B, ORL and AR face databases show that OLTP consistently performs much better than other well recognized texture models for face recognition.

• Journal of Information Processing Systems
• /
• 제4권2호
• /
• pp.77-86
• /
• 2008

This research proposes a new neural network for text categorization which uses alternative representations of documents to numerical vectors. Since the proposed neural network is intended originally only for text categorization, it is called NTC (Neural Text Categorizer) in this research. Numerical vectors representing documents for tasks of text mining have inherently two main problems: huge dimensionality and sparse distribution. Although many various feature selection methods are developed to address the first problem, the reduced dimension remains still large. If the dimension is reduced excessively by a feature selection method, robustness of text categorization is degraded. Even if SVM (Support Vector Machine) is tolerable to huge dimensionality, it is not so to the second problem. The goal of this research is to address the two problems at same time by proposing a new representation of documents and a new neural network using the representation for its input vector.

• 전기학회논문지
• /
• 제65권10호
• /
• pp.1731-1737
• /
• 2016

In this paper, a method is proposed to recognize human actions as nonverbal expression; the proposed method is composed of two steps which are action representation and action recognition. First, MHI(Motion History Image) is used in the action representation step. This method includes segmentation based on depth information and generates spatio-temporal templates to describe actions. Second, CNN(Convolution Neural Network) which includes feature extraction and classification is employed in the action recognition step. It extracts convolution feature vectors and then uses a classifier to recognize actions. The recognition performance of the proposed method is demonstrated by comparing other action recognition methods in experimental results.

• 한국정밀공학회지
• /
• 제16권10호
• /
• pp.194-202
• /
• 1999

A method for pattern recognition based on wavelet transform is proposed in this paper. The boundary of the object to be recognized includes shape information for object of machine parts. The contour is first represented using a one-dimensional signal and normalized about translation, rotation and scale, then is used to build the wavelet transform representation of the object. Wavelets allow us to decompose a function into multi-resolution hierarchy of localized frequency bands. The recognition of 2-dimensional object based on the wavelet is described to analyze the shape of analysis technique; the discrete wavelet transform(DWT). The feature vectors obtained using wavelet analysis is classified using a multi-layer neural network. The results show that, compared with the use of fourier descriptors, recognition using wavelet is more stable and efficient representation. And particularly the performance for objects corrupted with noise is better than that of other method.

• 한국컴퓨터그래픽스학회논문지
• /
• 제3권2호
• /
• pp.77-84
• /
• 1997

3차원 물체를 표현하는 솔리드 모델링 기법으로 Constructive Solid Geometry(CSG)와 경계표현 (Boundary Representation: BRep)이 널리 쓰이고 있다. 현대의 솔리드 모델링 시스템들은 대개 이 두 기법을 모두 지원하고 있으며, CSG와 BRep간 상호 변환은 매우 중요한 문제이다. 하지만, BRep에서 CSG로의 변환은 아직 완전히 해결되지 않은 과제이다. 이 논문은 BRep을 CSG의 특수한 형태인 Destructive Solid Geometry(DSG)로 변환하는 3차원 기하 추론 알고리즘을 소개한다. BRep에서 DSG를 만들어내는 알고리즘은 CAD와 CAM을 통합시키는 특정 형상 인식 분야에 직접 응용될 수 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2407-2424
• /
• 2022

Recently, Transformer has made great progress in video retrieval tasks due to its high representation capability. For the structure of a Transformer, the cascaded self-attention modules are capable of capturing long-distance feature dependencies. However, the local feature details are likely to have deteriorated. In addition, increasing the depth of the structure is likely to produce learning bias in the learned features. In this paper, an improved Transformer structure named TransDCS (Transformer with Dynamic Convolution and Shortcut) is proposed. A Multi-head Conv-Self-Attention module is introduced to model the local dependencies and improve the efficiency of local features extraction. Meanwhile, the augmented shortcuts module based on a dual identity matrix is applied to enhance the conduction of input features, and mitigate the learning bias. The proposed model is tested on MSRVTT, LSMDC and Activity-Net benchmarks, and it surpasses all previous solutions for the video-text retrieval task. For example, on the LSMDC benchmark, a gain of about 2.3% MdR and 6.1% MnR is obtained over recently proposed multimodal-based methods.

• 전자공학회논문지CI
• /
• 제41권6호
• /
• pp.39-46
• /
• 2004

클러스터 분석에 있어 중요한 문제 중의 하나는 주어진 데이터에 내재된 적절한 클러스터의 수를 찾아내는 것이다. 본 논문에서는 이러한 클러스터의 개수를 체계적으로 결정하기 위하여 IRC (Input Representation Coverage) 개념을 새로이 정의하고, 이를 이용하여 주어진 데이터에 적합한 클러스터의 개수를 자동 결정하는 방법을 제시한다. 또한, 이러한 방법의 유용성 및 응용성을 알아보기 위하여 가상 데이터를 가지고 분석 실험을 하였으며, 실험을 통해 데이터에 내재된 실제 클러스터의 개수를 찾아내는 데에 제안된 방법이 매우 유용하게 사용될 수 있음을 보여준다.

• 대한기계학회논문집
• /
• 제17권10호
• /
• pp.2446-2456
• /
• 1993

By virtue of progress of computer science, CAD/CAM technology has been developed greatly in each area. But the problems in the integration of CAD/CAM are not yet solved completely. The reason is that the exchange of data between CAD and CAM is difficult because the domains of design and manufacturing are different in nature. To solve this problem, a feature based modeller is developed in this study, which makes it possible to communicate between design and manufacturing through features. The modeller has feature, the concept of semi-bounded plane is introduced, and implemented as a B-rep sheet model using half-edge data structure. The features are then created on a part by local modification of the boundary on a part based on feature template information. This approach generalizes the modelling of features in a geometry model.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.965-976
• /
• 2020

We present in this work a segmentation method of E. coli bacterial images generated via phase contrast microscopy using a deep learning based hybrid feature generation. Unlike conventional machine learning methods that use the hand-crafted features, we adopt the denoising autoencoder in order to generate a precise and accurate representation of the pixels. We first construct a hybrid vector that combines original image, difference of Gaussians and image gradients. The created hybrid features are then given to a deep autoencoder that learns the pixels' internal dependencies and the cells' shape and boundary information. The latent representations learned by the autoencoder are used as the inputs of a softmax classification layer and the direct outputs from the classifier represent the coarse segmentation mask. Finally, the classifier's outputs are used as prior information for a graph partitioning based fine segmentation. We demonstrate that the proposed hybrid vector representation manages to preserve the global shape and boundary information of the cells, allowing to retrieve the majority of the cellular patterns without the need of any post-processing.