• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.307-310
• /
• 2021

X-ray 영상 검사·검출 문제에 기존 딥러닝 모델을 사용하려는 시도들이 존재해왔고, 합성곱 신경망의 강력한 표현력 덕분에 대체로 준수한 성능이 보장되었다. 그러나 문제의 특성에 따라 기대한 만큼의 분류 및 검출 성능이 나오지 않는 경우가 존재한다. 이는 1) 검출 대상의 스케일이 다양하거나, 2) X-ray 영상은 흑백 영상으로 미세한 특징을 학습하기 어렵거나, 3) 지도학습을 하기에는 학습 데이터의 양이 부족하기 때문인 것이 주요 원인들이다. 본 논문에서는 다양한 스케일의 특징맵을 추출하여 종합적으로 학습하는 신경망을 통해, '생선살 X-ray 영상' 데이터셋에서 '생선 가시' 이물질 class가 모델 내에서 어떻게 학습되는지를 살펴본다. 그리고 X-ray 영상의 경우, 이물질 class를 크기별로 새롭게 labeling하여 성능 개선이 일어날 수 있음을 보인다. 또한 Multi-scale CAM을 통해 class에 따른 활성화 정도를 시각화하여 모델을 직관적으로 분석할 수 있음을 보일 것이다.

• Journal of Educational Research in Mathematics
• /
• v.13 no.3
• /
• pp.351-364
• /
• 2003

by A.C. Clairaut is the first geometry textbook based on the historico-genetic principle against the logico-deduction method of Euclid's This paper aims to recognize Clairaut's historico-genetic principle by inquiring into this book and to search for its applications to school mathematics. For this purpose, we induce the following five characteristics that result from his principle and give some suggestions for school geometry in relation to these characteristics respectively : 1. The appearance of geometry is due to the necessity. 2. He approaches to the geometry through solving real-world problems.- the application of mathematics 3. He adopts natural methods for beginners.-the harmony of intuition and logic 4. He makes beginners to grasp the principles. 5. The activity principle is embodied. In addition, we analyze the two useful propositions that may prove these characteristics properly.

• Journal of the Korea Computer Graphics Society
• /
• v.21 no.5
• /
• pp.1-10
• /
• 2015

This study proposes a method of developing authoring tool that can easily and intuitively generate diverse digital leaves that compose virtual landscape. The main system of the proposed authoring tool consists of deformation method for the contour of leaf blade based on image warping, procedural modeling of leaf vein and visualization method based on mathematical model that expresses the color and brightness of leaves. First, the proposed authoring tool receives leaf input image and searches for contour information on the leaf blades. It then designs leaf blade deformation method that can generate diverse shapes of leaf blades in an intuitive structure using feature-based image warping. Based on the computed leaf blade contour, the system implements the generalized procedural modeling method suitable for the authoring tool that generates natural vein patterns appropriate for the leaf blade shape. Finally, the system applies visualization function that can express color and brightness of leaves and their changes over time using a mathematical model based on convolution sums of divisor functions. This paper provides texture support function so that the digital leaves that were generated using the proposed authoring tool can be used in a variety of three-dimensional digital contents field.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.920-926
• /
• 2007

새로운 매체와 접촉 시 발생하는 거부감을 최소화 하고 별도의 학습 없이 사용 가능한 직관적 명령 전달 방식의 매개 인터페이스를 제안한다. 제안하는 매개 인터페이스는 3차원 공간에서 사용가능한 가상 마우스와 TV 리모트 컨트롤러의 기능적 결합을 목표로 하고 실버세대들에게 익숙한 매체인 펜을 형태로 삼아 개념적으로 설계되었다. 구체적인 구현은 가속도계의 신호를 분석하거나 펜촉에 레이저 포인터를 추가하여 레이저 포인터의 좌표 변화를 웹캠으로 추적, 인식하는 방법으로 구분하였고 본 논문에서는 가속도계의 경우를 소개한다. 가속도계 신호분석을 통해 마우스의 기능을 모사하고 동작을 감지하는데 발생하는 문제점과 이를 해결하기 위한 기존 연구를 분석하고 동작 중에 중력방향의 수직축이 바뀌면서 발생하는 가속도계 신호의 오류를 보상하기 위해 제안된 Zero Velocity Compensation 방법을 소개한다. ZVC의 결과에 필수적인 저주파의 시계열 신호 실시간 끝점 추출과 동시에 패턴인식을 위한 특징추출 기능을 수행하는 새로운 알고리즘을 제안하며 기존의 방법과 실험적으로 성능을 비교한다. 또한 입력된 가속도계 신호를 학습된 인식기를 통해 인식하는 기존의 연구에서 더 나아가, 마우스의 좌표변화를 짧은 시간동안 가속도 신호의 실시간 분석을 통해 모사하기 위해 변형시킨 알고리즘을 소개한다.

• Journal of KIISE:Software and Applications
• /
• v.35 no.4
• /
• pp.255-264
• /
• 2008

This paper proposes a novel method using K-means and Non-negative matrix factorization (NMF) for topic -based multi-document summarization. NMF decomposes weighted term by sentence matrix into two sparse non-negative matrices: semantic feature matrix and semantic variable matrix. Obtained semantic features are comprehensible intuitively. Weighted similarity between topic and semantic features can prevent meaningless sentences that are similar to a topic from being selected. K-means clustering removes noises from sentences so that biased semantics of documents are not reflected to summaries. Besides, coherence of document summaries can be enhanced by arranging selected sentences in the order of their ranks. The experimental results show that the proposed method achieves better performance than other methods.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.11
• /
• pp.73-79
• /
• 2009

In this paper, a method is proposed that enhances the performance of the facial expression recognition using template matching of Local Binary Pattern(LBP) histogram. In this method, the face image is segmented into blocks, and the LBP histogram is constructed to be used as the feature of the block. Block dissimilarity is calculated between a block of input image and the corresponding block of the model image. Image dissimilarity is defined as the weighted sum of the block dissimilarities. In conventional methods, the block weights are assigned by intuition. In this paper a new method is proposed that optimizes the weights from training samples. An experiment shows the recognition rate is enhanced by the proposed method.

• Journal of Digital Contents Society
• /
• v.18 no.6
• /
• pp.1033-1040
• /
• 2017

Artists use artistic features of paintings to provide various emotions in paintings. These features may be simply color and texture, but they can move on to form a composition or a symmetry. Through these features, people can feel various emotions when enjoying paintings. Even though they are using these features, there are paintings that are not readily accessible to non-extractable experts. This is because the analysis of features is not intuitive. In this paper, we want to produce content that matches paintings and music. This helps user to understand painting easily with paintings and matched music.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.3
• /
• pp.107-112
• /
• 2018

In this paper, optical flow based keypoint detection and tracking technique is proposed for the collaboration between flying drone with vision system and ground robots. There are many challenging problems in target detection research using moving vision system, so we combined the improved FAST algorithm and Lucas-Kanade method for adopting the better techniques in each feature detection and optical flow motion tracking, which results in 40% higher in processing speed than previous works. Also, proposed image binarization method which is appropriate for the given marker helped to improve the marker detection accuracy. We also studied how to optimize the embedded system which is operating complex computations for intelligent functions in a very limited resources while maintaining the drone's present weight and moving speed. In a future works, we are aiming to develop collaborating smarter robots by using the techniques of learning and recognizing targets even in a complex background.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.1
• /
• pp.11-19
• /
• 2022

In this paper we present a new method for interactive segmentation of a triangle mesh by using the concavity-sensitive harmonic field and anisotropic geodesic. The proposed method only requires a single vertex in a desired feature region, while most of existing methods need explicit information on segmentation boundary. From the user-clicked vertex, a candidate region which contains the desired feature region is defined and concavity-senstive harmonic field is constructed on the region by using appropriate boundary constraints. An initial isoline is chosen from the uniformly sampled isolines on the harmonic field and optimal points on the initial isoline are determined as interpolation points. Final segmentation boundary is then constructed by computing anisotropic geodesics passing through the interpolation points. In experimental results, we demonstrate the effectiveness of the proposed method by selecting several features in various 3D models.

• Journal of Industrial Convergence
• /
• v.21 no.1
• /
• pp.1-8
• /
• 2023

Study surveyed perception of dental hygienist occupation was surveyed by examining the qualifications, occupational evaluation Criteria, professional intuition of some college students for the dental hygienist occupation analyzed by the SPSS WIN18.0 program. Among the necessary qualities of dental hygienist, 'professional knowledge of dental hygiene', 'dental hygiene skills' were the highest. Average of Job evaluation Criteria was 4.06, which was higher than the average of 3.80 Job evaluation factors of dental hygienists. As for the Job evaluation criteria, 'stable job', 'job with good work atmosphere and interpersonal relationship' was the highest, 'job with contact with people', 'independent job' was the most. Job evaluation Criteria for dental hygienists, 'jobs with contact with people', 'jobs that can help others' were high, and 'high wages', 'high probability of promotion' were low. As a result of regression analysis of general characteristics and dental hygiene professionalism, it was analyzed that the professionalism of dental hygienists increased when the major was non-health. Overall, In order to improve the qualifications of dental hygienists and raise awareness of vocational evaluation, efforts should be made systematically to identify the strengths and weaknesses of vocational evaluation and dental hygienists and to seek improvements.