• KSCI Review
• /
• v.14 no.1
• /
• pp.265-271
• /
• 2006

In this paper, we propose a new automatic fingerprint identification system that identifies individuals in large databases. The algorithm consists of three steps: preprocessing, classification, and matching, in the classification, we present a new classification technique based on the statistical approach for directional image distribution. In matching, we also describe improved minutiae candidate pair extraction algorithm that is faster and more accurate than existing algorithm. In matching stage, we extract fingerprint minutiaes from its thinned image for accuracy, and introduce matching process using minutiae linking information. Introduction of linking information into the minutiae matching process is a simple but accurate way, which solves the problem of reference minutiae pair selection in comparison stage of two fingerprints quickly. This algorithm is invariant to translation and rotation of fingerprint. The proposed system was tested on 1000 fingerprint images from the semiconductor chip style scanner. Experimental results reveal false acceptance rate is decreased and genuine acceptance rate is increased than existing method.

• Journal of Computing Science and Engineering
• /
• v.3 no.3
• /
• pp.165-180
• /
• 2009

The HKIB, or Hankookilbo, test collections are two archives of Korean newswire stories manually categorized with semi-hierarchical or hierarchical category taxonomies. The base newswire stories were made available by the Hankook Ilbo (The Korea Daily) for research purposes. At first, Chungnam National University and KISTI collaborated to manually tag 40,075 news stories with categories by semi-hierarchical and balanced three-level classification scheme, where each news story has only one level-3 category (single-labeling). We refer to this original data set as HKIB-40075 test collection. And then Yonsei University and KISTI collaborated to select 20,000 newswire stories from the HKIB-40075 test collection, to rearrange the classification scheme to be fully hierarchical but unbalanced, and to assign one or more categories to each news story (multi-labeling). We refer to this modified data set as HKIB-20000 test collection. We benchmark a k-NN categorization algorithm both on HKIB-20000 and on HKIB-40075, illustrating properties of the collections, providing baseline results for future studies, and suggesting new directions for further research on Korean text categorization problem.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.2A
• /
• pp.79-85
• /
• 2006

Generally, it is essential that high-speed routers, switches, and network security appliances should have an efficient packet classification scheme in order to achieve the high-speed packet forwarding capability. For the multi-gigabit packet-processing network equipment the high-speed content search hardware such as TCAM and search engine is recently used to support the content-based packet inspection. During the packet classification process, hundreds and thousands of rules are applied to provide the network security policies regarding traffic screening, traffic monitoring, and traffic shaping. In addition, these rules could be dynamically changed during operations of systems if anomaly traffic patterns would vary. Particularly, in the high-speed network, an efficient algorithm that updates and reorganizes the packet classification rules is critical so as not to degrade the performance of the network device. In this paper, we have proposed an efficient update algorithm using a partial-ordering that can relocate the dynamically changing rules at the TCAM. Experimental results should that our algorithm does not need to relocate existing rules feature until 70$\%$ of TCAM utilization.

• Journal of Ocean Engineering and Technology
• /
• v.8 no.2
• /
• pp.64-79
• /
• 1994

In this study, terrain classification, which was done by using the quantitative classification parameters and suitable interpolation method was applied to improve the accuracy of digital elevation models, and to increase its practical use of aerial photogrammetry. A terrain area was classified into three groups using the quantitative classification parameters to the ratio of horizontal, inclined area, magnitude of harmonic vectors, deviation of vector, the number of breakline and proposed the suitable interpolation. Also, the accuracy of digital elevation models was improved in case of large grid intervals by applying combined interpolation suitable for each terrain group. As a result of this study, I have an algorithm to perform the classification of the topography in the area of interest objectively and decided optimal data interpolation scheme for given topography.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1413-1415
• /
• 2004

This paper proposes a SVM(Support Vector Machine) training algorithm to control a service robot with voice command. The service robot with a stereo vision system and dual manipulators of four degrees of freedom implements a User-Dependent Voice Control System. The training of SVM algorithm that is one of the statistical learning theories leads to a QP(quadratic programming) problem. In this paper, we present an efficient SVM speech recognition scheme especially based on less learning data comparing with conventional approaches. SVM discriminator decides rejection or acceptance of user's extracted voice features by the MFCC(Mel Frequency Cepstrum Coefficient). Among several SVM kernels, the exponential RBF function gives the best classification and the accurate user recognition. The numerical simulation and the experiment verified the usefulness of the proposed algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.19-19
• /
• 2000

This paper introduces a new scheme for neural network classifier which can describe the shape of patterns in clustered group by using a self-organizing teeming algorithm. The prototype based neural network classifier can not describe the shape of group and it has low classification performance when the data groups are complex. To improve above-mentioned problem, new neural scheme is introduced. This proposed neural network algorithm can be regarded as the extension of self-organizing feature map which can describe The experimental results shows that the proposed algorithm can describe the shape of pattern successfully.

• Journal of information and communication convergence engineering
• /
• v.15 no.1
• /
• pp.53-61
• /
• 2017

The preferred feature selection methods for text classification are filter-based. In a common filter-based feature selection scheme, unique scores are assigned to features; then, these features are sorted according to their scores. The last step is to add the top-N features to the feature set. In this paper, we propose an improved global feature selection scheme wherein its last step is modified to obtain a more representative feature set. The proposed method aims to improve the classification performance of global feature selection methods by creating a feature set representing all classes almost equally. For this purpose, a local feature selection method is used in the proposed method to label features according to their discriminative power on classes; these labels are used while producing the feature sets. Experimental results obtained using the well-known 20 Newsgroups and Reuters-21578 datasets with the k-nearest neighbor algorithm and a support vector machine indicate that the proposed method improves the classification performance in terms of a widely known metric ($F_1$).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.1
• /
• pp.288-301
• /
• 2017

In this paper, we propose an optimized algorithm for texture classification by computing a completed modeling of the local binary pattern (CLBP) instead of the traditional LBP of a scalable block size in an image. First, we show that the CLBP descriptor is a better representative than LBP by extracting more information from an image. Second, the CLBP features of scalable block size of an image has an adaptive capability in representing both gross and detailed features of an image and thus it is suitable for image texture classification. This paper successfully implements a machine learning scheme by applying the CLBP features of a scalable size to the Support Vector Machine (SVM) classifier. The proposed scheme has been evaluated on Outex and CUReT databases, and the evaluation result shows that the proposed approach achieves an improved recognition rate compared to the previous research results.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.399-401
• /
• 2003

This paper presents a geostatistical contextual classifier for the classification of remote sensing data. To obtain accurate spatial/contextual information, a simple indicator kriging algorithm with local means that allows one to estimate the probability of occurrence of certain classes on the basis of surrounding pixel information is applied. To illustrate the proposed scheme, supervised classification of multi-sensor remote sensing data is carried out. Analysis of the results indicates that the proposed method improved the classification accuracy, compared to the method based on the spectral information only.

• The Journal of Society for e-Business Studies
• /
• v.12 no.3
• /
• pp.193-210
• /
• 2007

In order for a classification system to be useful in every day business environments, it has to reflect peculiar characteristics of enterprises and organizations. By automating the generation process of classification, the overall operation of classification system becomes effective and efficient. However, in order for it to be really useful, human input and interventions are needed from the very beginning phase of the classification generation. This paper proposes an user-guided classification generation algorithm, in which the user inputs a specific level of the classification that she/he wants. Also we propose and implement manipulation operators to tailor the initial classification into the shape that user wants.