• Journal of Internet Computing and Services
• /
• v.8 no.3
• /
• pp.19-32
• /
• 2007

This paper present a new face recognition method based on LVQ neural net to construct a real time face recognition system. The previous researches which used PCA, LDA combined neural net usually need much time in training neural net. The supervised LVQ neural net needs much less time in training and can maximize the separability between the classes. In this paper, the proposed method transforms the input face image by PCA and LDA sequentially into low-dimension feature vectors and recognizes the face through LVQ neural net. In order to make the system robust to external light variation, light compensation is performed on the detected face by max-min normalization method as preprocessing. PCA and LDA transformations are applied to the normalized face image to produce low-level feature vectors of the image. In order to determine the initial centers of LVQ and speed up the convergency of the LVQ neural net, the K-Means clustering algorithm is adopted. Subsequently, the class representative vectors can be produced by LVQ2 training using initial center vectors. The face recognition is achieved by using the euclidean distance measure between the center vector of classes and the feature vector of input image. From the experiments, we can prove that the proposed method is more effective in the recognition ratio for the cases of still images from ORL database and sequential images rather than using conventional PCA of a hybrid method with PCA and LDA.

• Journal of KIISE:Software and Applications
• /
• v.35 no.8
• /
• pp.463-478
• /
• 2008

Due to the high dimensional problem, typically machine learning algorithms have relied on feature selection techniques in order to perform effective classification in microarray gene expression datasets. However, the large number of features compared to the number of samples makes the task of feature selection computationally inprohibitive and prone to errors. One of traditional feature selection approach was feature filtering; measuring one gene per one step. Then feature filtering was an univariate approach that cannot validate multivariate correlations. In this paper, we proposed a function for measuring both class separability and correlations. With this approach, we solved the problem related to feature filtering approach.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.2
• /
• pp.143-150
• /
• 2010

Markerless augmented reality system must have the capability to recognize and match natural objects both in indoor and outdoor environment. In this paper, a novel approach is proposed for extracting features and recognizing natural objects using visual descriptors and codebooks. Since the augmented reality applications are sensitive to speed of operation and real time performance, our work mainly focused on recognition of multi-class natural objects and reduce the computing time for classification and feature extraction. SIFT(scale invariant feature transforms) and SURF(speeded up robust feature) are used to extract features from natural objects during training and testing, and their performance is compared. Then we form visual codebook from the high dimensional feature vectors using clustering algorithm and recognize the objects using naive Bayes classifier.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.11a
• /
• pp.25-28
• /
• 2006

사용자 의도 파악 (intention reading) 기술은 스마트 홈과 같은 복잡한 유비쿼터스(ubiquitous) 환경에서 사용자에게 보다 편리하고 개인화된(personalized) 서비스 제공이 가능하도록 해준다. 또한 학습 기능(learning capability)은 지식 발견(knowledge discovery)의 관점에서 의도 파악 기술의 핵심 요소 기술의 하나로 자리 매김 하고 있다. 본 논문에서는 스마트 홈 환경에서 제공 가능한 개인화된 서버스(personalized service) 중의 하나로, 개인화된 미디어 제어 방법에 대한 내용을 다룬다. 특히, 이러한 사람의 행동 패턴과 같은 데이터는 패턴 분류의 관점에서 구분해야 할 클래스(class)에 비해 입력 정보가 불충분할 경우가 많으므로 비일관적인(inconsistent) 데이터가 많으므로, 퍼지 논리(fuzzy logic)와 확률(probability)의 개념을 효과적으로 병행해야 의미 있는 지식을 추출해 낼 수 있다. 이를 위하여 반복 퍼지 지도 클러스터링 (IFCS; Iterative Fuzzy Clustering with Supervision) 알고리즘에 기반하여 주어진 데이터 패턴으로부터 확률적 퍼지 룰(probabilistic fuzzy rule)을 얻어 내는 방법에 대해 설명한다. 또한 이를 포함하는 학습 제어 시스템을 통해 개인화된 미디어 서비스를 추천해 줄 수 있는 방법에 대해서 설명하도록 한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.2
• /
• pp.151-156
• /
• 2002

There are two methods in evaluation student s achievement. The two evaluation methods are absolute evaluation and relative evaluation. They have much advantages respectively, but also have some limitations such as being too stereotyped or causing overcompetition among learners. This paper suggests a new evaluation method which evaluates student s achievements by considering the score distribution and the frequency The proposed method classifies the scores into several clusters considering the goodness. This approach calculates the goodness by applying the RE(relaxation error), and grades the achievement scores based on the goodness. The suggested method can avoid the problem of grading caused by the narrow gap of scores because it sets a standard for grading by the calculated goodness considering the score distribution and frequency of occurrence. The method can differentiate achievements of a school from those of others, and that it is useful for selecting advanced students and dull ones, and for evaluation of classes based on student s achievement.

• Journal of KIISE:Software and Applications
• /
• v.31 no.8
• /
• pp.980-990
• /
• 2004

The component-based development methodology aims at the high state of abstraction and the reusability with components larger than classes. It is indispensible to measure the component so as to improve the quality of the component-based system and the individual component. And, the quality of the component should be improved through putting the results into the process of the development. So, it is necessary to study the component metric which can be applied in the stage of the component analysis and design. Hence, in this paper, we propose component cohesion, coupling, independence metrics reflecting the information extracted in the step of component analysis and design. The proposed component metric bases on the similarity information about behavior patterns of operations to offer the component's service. Also, we propose the redesigning process for the improvement of component design. That process uses the techniques of clustering and is for the thing that makes the component as the independent functional unit having the low complexity and easy maintenance. And, we examine that the component design model can be improved by the component metrics and the component redesigning process.

• The KIPS Transactions:PartB
• /
• v.9B no.1
• /
• pp.113-118
• /
• 2002

This paper presents a cluster-based image retrieval method. It retrieves images from a related cluster after classifying images into clusters using RAGMD, a clustering technique. When images are retrieved, first they are retrieved not from the whole image database one by one but from the similar cluster, a similar small image group with a query image. So it gives us retrieval-time reduction, keeping almost the same precision with the exhaustive retrieval. In the experiment using an image database consisting of about 2,400 real images, it shows that the proposed method is about 18 times faster than 7he exhaustive method with almost same precision and it can retrieve more similar images which belong to the same class with a query image.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.6
• /
• pp.701-708
• /
• 2005

Structuring mechanism, important to serve messages in post-office box structure, is to construct the hierarchy of classes according to the contents of message objects. This Paper Proposes $\alpha$-cut based genealogy grouping method to cluster a lot of structured objects in application domain. The proposed method decides the relationship first by semantic similarity relation and fuzzy relation, and then performs the grouping by operations of search( ), insert() and hierarchy(). This hierarchy structure makes it easy to process group-related processing tasks such as answering queries, discriminating objects, finding similarities among objects, etc. The proposed post-office box structure may be efficiently used to serve and manage message objects by the creation of groups. The Proposed method is tested for 5500 message objects and compared with other methods such as non-grouping, BGM, RGM, OGM.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.1
• /
• pp.1-9
• /
• 2013

This paper propose a human action recognition method that uses bag-of-features (BoF) based on CS-LBP (center-symmetric local binary pattern) and a spatial pyramid in addition to the random forest classifier. To construct the BoF, an image divided into dense regular grids and extract from each patch. A code word which is a visual vocabulary, is formed by k-means clustering of a random subset of patches. For enhanced action discrimination, local BoF histogram from three subdivided levels of a spatial pyramid is estimated, and a weighted BoF histogram is generated by concatenating the local histograms. For action classification, a random forest, which is an ensemble of decision trees, is built to model the distribution of each action class. The random forest combined with the weighted BoF histogram is successfully applied to Standford Action 40 including various human action images, and its classification performance is better than that of other methods. Furthermore, the proposed method allows action recognition to be performed in near real-time.

• Journal of Korea Multimedia Society
• /
• v.9 no.3
• /
• pp.265-278
• /
• 2006

This paper presents a two-dimensional type inheritance hierarchy index(2D-THI) for XML databases. XML Schema is one of schema models for the XML documents supporting. The type inheritance. The conventional indexing techniques for XML databases can not support XML queries on type inheritance hierarchies. We construct a two-dimensional index structure using multidimensional file organizations for supporting type inheritance hierarchy in XML queries. This indexing technique deals with the problem of clustering index entries in the two-dimensional domain space that consists of a key element domain and a type identifier domain based on the user query pattern. This index enhances query performance by adjusting the degree of clustering between the two domains. For performance evaluation, we have compared our proposed 2D-THI with the conventional class hierarchy indexing techniques in object-oriented databases such as CH-index and CG-tree through the cost model. As the result of the performance evaluations, we have verified that our proposed two-dimensional type inheritance indexing technique can efficiently support the query Processing in XML databases according to the query types.