• MALSORI
• /
• no.51
• /
• pp.151-165
• /
• 2004

For educational and research purposes, a Korean speech recognition platform is designed. It is based on an object-oriented architecture and can be easily modified so that researchers can readily evaluate the performance of a recognition algorithm of interest. This platform will save development time for many who are interested in speech recognition. The platform includes the following modules: Noise reduction, end-point detection, met-frequency cepstral coefficient (MFCC) and perceptually linear prediction (PLP)-based feature extraction, hidden Markov model (HMM)-based acoustic modeling, n-gram language modeling, n-best search, and Korean language processing. The decoder of the platform can handle both lexical search trees for large vocabulary speech recognition and finite-state networks for small-to-medium vocabulary speech recognition. It performs word-dependent n-best search algorithm with a bigram language model in the first forward search stage and then extracts a word lattice and restores each lattice path with a trigram language model in the second stage.

• The Journal of the Acoustical Society of Korea
• /
• v.9 no.3
• /
• pp.42-47
• /
• 1990

A neural auditory system is studied for the aim of making better speech recognition systems. The cochlear mechanics is described. A IIR digital filter modeling of basilar membrane is discussed for the speech recognition. A multi-layer model of consonant recognition using phoneme detection filters and discriminant functions for feature estimation is constructed. This model shows more then 90% recognition rate in consonants.

• Journal of KIISE:Databases
• /
• v.30 no.3
• /
• pp.237-251
• /
• 2003

In this paper, we propose a video retrieval system to search logical structure and semantic contents of video data efficiently. The proposed system employs a layered modelling method that orBanifes video data in raw data layer, content layer and key frame layer. The layered modelling of the proposed system represents logical structures and semantic contents of video data in content layer. Also, the proposed system supports various types of searches such as text search, visual feature based similarity search, spatio-temporal relationship based similarity search and semantic contents search.

• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.294-296
• /
• 2006

Recently the development of GIS and spatial information technology is used to construct very detail forest information. In addition, in order to classify forest characteristic, the geographical characteristic information of forest could be very useful for the forest classification, In this study sampling points were arranged to clarify the difference between the orm area and the land forest area. Also, forest feature pattern could be discriminated by using satellite images and SML. This study result should be constructed to efficiency forest management in especially forest area in Jeju Island

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.1 no.1
• /
• pp.81-86
• /
• 2001

In this paper, we investigated the modeling of Bank Asset Management System(BAME) based on intelligent agent. To achieve this goal, we introduced several kinds of agents that show intelligent features. BAMS is a user friendly system and adopts fuzzy converting system and fuzzy matching system that returns reasonable similarity matching results. Generation function of the proximity degree is suggested. Fuzzification of investment type categories and feature values are defined, and generation of proximity degree is also derived. An example of bank asset management system is introduced and simulated. Investment type matching utilizing fuzzy measure is tested and it showed quite reasonable similarity matching results.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.34.5-34
• /
• 2002

In this paper we propose a new method for modeling indoor environment with stereo camera and suggest a localization method for mobile robot navigation on the basis of it. From the viewpoint of easiness in map building and exclusion of artificiality, the main idea of this paper is that environment is represented as global topological map and each node has omni-directional metric and color information by using stereo camera and pan/tilt mechanism. We use the depth and color information itself in image pixel as feature for environmental abstraction. In addition, we use only the depth and color information at horizontal centerline in image, where optical axis is passing. The usefulness of this m...

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.1626-1629
• /
• 2003

The study is expressed on the web browser using virtual reality of developer manufacturing process and method or manufactured goods conviction for designer and developer with visualized model. This study purpose of basic feature with VRML file and Java and VRML with AWT to get WC code was presented. The study process is equal to the real thing modeling on using Pro/Engineer and exports on the VRML1.0. The condition converts VRML1.0 to VRML2.0 on the CROSS ROADS. And then Cosmo World is coding and manufacturing simulation is expressed on the Cosmo Player.

• International Journal of Precision Engineering and Manufacturing
• /
• v.9 no.3
• /
• pp.75-78
• /
• 2008

Tire molds are manufactured by aluminum casting, direct five-axis machining, and electric discharging machining. Master models made of chemical wood are necessary if aluminum casting is used. They are designed with a three-dimensional computer-aided design system and milled by a five-axis machine. In this paper, a method for generating and machining a tire surface model is proposed and demonstrated. The groove surfaces, which are the main feature of the tire model, are created using a parametric design concept. An automatically programmed tool-like descriptive language is presented to implement the parametric design. Various groove geometries can be created by changing variables. For convenience, groove surfaces and raw cutter location (CL) data are generated in two-dimensional drawing space. The CL data are mapped to the tread surface to obtain five-axis CL data to machine the master model. The proposed method was tested by actual milling using the five-axis control machine. The results demonstrate that the method is useful for manufacturing a tire mold.

• International Journal of Contents
• /
• v.2 no.1
• /
• pp.22-28
• /
• 2006

In this paper, we propose new semantic contents modeling using individual features, associative relations and visual features for efficiently supporting browsing and retrieval of video semantic contents. And we implement and design a browsing and retrieval system based on the semantic contents modeling. The browsing system supports annotation based information, keyframe based visual information, associative relations, and text based semantic information using a tree based browsing technique. The retrieval system supports text based retrieval, visual feature and associative relations according to the retrieval types of semantic contents.

• Proceedings of the Korea Contents Association Conference
• /
• 2008.05a
• /
• pp.525-528
• /
• 2008

Recently multimedia contents is more important because multimedia media environment improved. In this paper, we study that special effect apply technique using after effect system for Maya 3D modeling. The system is useful for development 3D contents. We discuss usefulness, distinctive feature and applying part.