• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.19 no.2
• /
• pp.251-259
• /
• 2010

It is presented in this study a new efficient intelligent machining strategy, which can be used to remove the uncut volume at the boundary region of curved surfaces caused by cutter interference. The geometric form definitions and recognition of topological features of the surface triangulation mesh are used to generate cutter paths along successive and interconnected steepest pathways, that minimize the cusp height left after flat end milling. In order to machine the uncut volume gradually, the z-map cutter centers are adjusted to avoid cutter interference for the 6 kinds of avoidance types. And then, the generative subsequent paths are sequenced to determine the second step cutter paths for the next uncut volume. For the 2 kinds of test models with convex and concave surface region, the implemented software algorithm is evaluated by investigating the residual swelling of uncut volume for each machining step.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1995.06a
• /
• pp.100-104
• /
• 1995

일반적으로 화자적응화는 이미 학습되어 있는 불특정 화자 모델을 표준모델로 하고 소량의 적응화용 발화로 추가적인 학습을 실시하여 특정화자 모델의 성능에 가깝게 하는 기술로서 연속음성 인식에 있어서 매우 중요하다. ML 추정법을 이용한 화자적응화는 카테고리마다 모델의 학습패턴들을 다수개 준비한 후 학습시에 일괄적으로 적용시켜 모델 파라메터를 추정 갱신하므로 추가되는 화자데이터에 대해 데이터를 모두 공급하여야 한다. 본 연구에서는 문발화 데이터의 음절단위를 자동추출한 후 추가되는 화자데이터가 주어질 때 마다 적응화할 수 있는 화자적응화 방법을 검토하였다. 이 방법은 문발화 데이터를 잘라내지 않고 음절 단위를 자동추출시켜 추가 데이터마다 최대 사후확률 추정법을 이용하여 적응화 시키는 것으로 수소의 데이터로서도 적응화를 가능하게 하는 것이다. 본 연구에서 사용되는 음성데이터는 신문사설에서 발췌한 연속음성 10문장을 사용하고, 이 음성 데이터중 6명분은 HMM 학습용으로 하고 나머지 3명분은 적응화용 및 평가용 데이터로 사용하였다. 6명의 화자를 DDCHMM으로 학습하고 나머지 3명분을 MAP법으로 적응화시켰다. 그 결과 적응전과 비교해 볼 때 약 32%의 인식율 향상을 얻을 수 있었다.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.17 no.9
• /
• pp.1006-1012
• /
• 2004

In this paper, neural networks is studied to apply as a PD source classification in XLPE power cable specimen. Two learning schemes are used to classification; BP(Back propagation algorithm), SOM(self organized map - kohonen network). As a PD source, using treeing discharge sources in the specimen, three defected models are made. And these data making use of a computer-aided discharge analyser, statistical and other discharge parameters is calculated to discrimination between different models of discharge sources. And a]so these distribution characteristics are applied to classify PD sources by two scheme of the neural networks. In conclusion, recognition efficiency of BP is superior to SOM.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1994.10a
• /
• pp.510-514
• /
• 1994

This paper deals with an application of neural network to camera calibration with wide angle lens and 2-D range finding. Wide angle lens has an advantage of having wide view angles for mobile environment recognition ans robot eye in hand system. But, it has severe radial distortion. Multilayer neural network is used for the calibration of the camera considering lens distortion, and is trained it by error back-propagation method. MLP can map between camera image plane and plane the made by structured light. In experiments, Calibration of camers was executed with calibration chart which was printed by using laser printer with 300 d.p.i. resolution. High distortion lens, COSMICAR 4.2mm, was used to see whether the neural network could effectively calibrate camera distortion. 2-D range of several objects well be measured with laser range finding system composed of camera, frame grabber and laser structured light. The performance of 3-D range finding system was evaluated through experiments and analysis of the results.

• The Journal of Korea Robotics Society
• /
• v.5 no.3
• /
• pp.251-261
• /
• 2010

In this paper, we introduce an internal pipeline exploration of an in-pipe robot, based on the landmark recognition system. The fittings of pipelines such as elbows and branches are used as the landmarks. The robot recognizes the landmarks with a vision system by using the shadows of the elements, which are generated by the specially designed illuminator on the robot. By using a simple image-processing, the robot can easily detect and distinguish these landmarks while recognizing the direction of the pipeline path. Simultaneously, all information for exploration is continuously recorded and used to reconstruct the map of the pipelines. The effectiveness of the proposed method is verified by real experiments using the in-pipe robot MRINSPECT V for moving inside of the miniature urban 8-inch gas pipeline structure.

• International journal of advanced smart convergence
• /
• v.5 no.4
• /
• pp.57-65
• /
• 2016

This paper aims to improve the quality of cultural experience by providing a three - dimensional guide service that enables users to experience themselves without additional guides and cultural commentators using the latest mobile IT technology to enhance understanding of cultural heritage. In this paper, we propose a method of constructing cultural contents based on location information such as user / cultural heritage using markerless tracking based augmented reality and GPS. We use marker detection technology and markerless tracking technology to recognize smart augmented reality object accurately and accurate recognition according to the state of cultural heritage, and also use Android's Google map to locate the user. The purpose of this paper is to produce content for introducing cultural heritage using GPS and augmented reality based on Android. It can be used in combination with various objects beyond the limitation of existing augmented reality contents.

• Annual Conference of KIPS
• /
• 2000.10b
• /
• pp.1665-1668
• /
• 2000

본 논문에서는 한국전력공사의 배전지리정보시스템를 보다 효과적으로 구축하기 위하여 배전설비 도면으로부터 설비정보를 자동취득하여 배전지리정보시스템의 데이타베이스에 입력하는 방법에 관하여 기술한다. 제안된 방법은 충남지사와 인천지사 관내 배전설비도면 약 30매를 대상으로 실험하고 그 결과를 제시한다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.6
• /
• pp.580-584
• /
• 2006

Material information for environment may be useful to accomplish mobile robot localization. A procedure to classify a set of indoor materials (glass, steel, wood, aluminum and concrete) with the reflected signal of ultrasonic sensor is proposed in this paper. The main idea is to use material-specific reflection characteristics for the recognition of material type. To achieve the classification task, we modeled reflected signal as a maximum amplitude with respect to distance. In this way, we can generate echo signal models for the given materials and these models are used to compare with the current sensor reading. The experimental results show that the proposed method may give material information during map building task of mobile robot.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.10
• /
• pp.100-112
• /
• 1992

In this paper, an integrated document input/output system is developed which constructs the graphic document from a text file, converts the document into encoded facsimile data, and also recognizes printed/handwritten alphanumerics and Korean characters in a facsimile or graphic document. For an output system, we develop the method which generates bit-map patterns from the document consisting of the KSC5601 and ASCII codes. The binary graphic image, if necessary, is encoded by the G3 coding scheme for facsimile transmission. For a user friendly input system for documents consisting of alphanumerics and Korean characters obtained from a facsimile or scanner, we propose a document recognition algirithm utilizing several special features(partial projection, cross point, and distance features) and the membership function of the fuzzy set theory. In summary, we develop an integrated document input/output system and its performance is demonstrated via computer simulation.

• Journal of Electrical Engineering and information Science
• /
• v.2 no.5
• /
• pp.79-88
• /
• 1997

This paper introduces a new energy function, as maximum a posteriori(MAP) estimate of binocular disparity, that can deal with both random dot stereo-gram(RDS) and natural scenes. The energy function uses phase-magnitude as features to detect only the shift for a pair of corrupted conjugate images. Also we adopted Fleet singularity that effectively detects unstable areas of image plant and thus eliminates in advance error-prone stereo mathcing. The multi-scale concept is applied to the multi laser architecture that can search the solutions systematically from coarse to fine details and thereby avoids drastically the local minima. Using mean field approximation, we obtained a compact representation that is suitable for fast computation. In this manner, the energy function satisfies major natural constraints and requirements for implementing parallel relaxation. As an experiment, the proposed algorithm is applied to RDS and natural stereo images. As a result we will see that it reveals good performance in terms of recognition errors, parallel implementation, and noise characteristics.