• 융합신호처리학회논문지
• /
• 제19권1호
• /
• pp.1-6
• /
• 2018

본 논문에서는 다중 스케일 영상 공간에서 특징점 검출을 위해 수행되는 반복적인 과정을 제거하는 방법을 제안한다. 제안한 방법은 원 영상으로부터 특징점을 검출하고, 클러스터 필터를 이용하여 유효한 특징점을 선별하고, 특징점 클러스터를 생성한다. 그리고 특징점 클러스터의 방향 각도를 이용하여 참조 객체를 선별하고, 분산 거리 비율을 이용하여 원 영상의 스케일을 예측한다. 예측한 스케일에 따라 참조 영상의 스케일을 변환하고, 변환된 참조 영상에 대해 특징점 검출을 적용한다. 실험 결과 제안한 방법은 다중 스케일 영상을 사용하는 SIFT 방법 및 Scaled ORB 방법에 비해 특징점 검출 시간이 각각 75% 및 71% 향상됨을 알 수 있었다.

• 대한의용생체공학회:의공학회지
• /
• 제44권5호
• /
• pp.354-361
• /
• 2023

Most of spinal diseases are diagnosed based on the subjective judgment of a specialist, so numerous studies have been conducted to find objectivity by automating the diagnosis process using deep learning. In this paper, we propose a method that combines segmentation and feature extraction, which are frequently used techniques for diagnosing spinal diseases. Four models, U-Net, U-Net++, DeepLabv3+, and M-Net were trained and compared using 1000 X-ray images, and key-points were derived using Douglas-Peucker algorithms. For evaluation, Dice Similarity Coefficient(DSC), Intersection over Union(IoU), precision, recall, and area under precision-recall curve evaluation metrics were used and U-Net++ showed the best performance in all metrics with an average DSC of 0.9724. For the average Euclidean distance between estimated key-points and ground truth, U-Net was the best, followed by U-Net++. However the difference in average distance was about 0.1 pixels, which is not significant. The results suggest that it is possible to extract key-points based on segmentation and that it can be used to accurately diagnose various spinal diseases, including spondylolisthesis, with consistent criteria.

• 한국자동차공학회논문집
• /
• 제9권4호
• /
• pp.62-68
• /
• 2001

In an early engine development, it is highly required to determine the Key Test Points at the main driving, zone and lessen those points to reduce a test duration. This paper describes that it is possible not only to predict the cycle fuel consumption[g/km], emissions[g/km] from engine data(BSFC[g/kWh], emissions[g/kWh]) but also to confirm the emission regulation potential before a vehicle test.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권4호
• /
• pp.83-92
• /
• 2020

A recent study to determine the fall is focused on analyzing fall motions using a recurrent neural network (RNN), and uses a deep learning approach to get good results for detecting human poses in 2D from a mono color image. In this paper, we investigated the improved detection method to estimate the position of the head and shoulder key points and the acceleration of position change using the skeletal key points information extracted using PoseNet from the image obtained from the 2D RGB low-cost camera, and to increase the accuracy of the fall judgment. In particular, we propose a fall detection method based on the characteristics of post-fall posture in the fall motion analysis method and on the velocity of human body skeleton key points change as well as the ratio change of body bounding box's width and height. The public data set was used to extract human skeletal features and to train deep learning, GRU, and as a result of an experiment to find a feature extraction method that can achieve high classification accuracy, the proposed method showed a 99.8% success rate in detecting falls more effectively than the conventional primitive skeletal data use method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권7호
• /
• pp.2512-2529
• /
• 2015

Wireless mesh networks (WMNs) provide an efficient and flexible method to the field of wireless networking, but also bring many security issues. A mesh point may lose all of its available links during its movement. Thus, the mesh point needs to handover to a new mesh point in order to obtain access to the network again. For multi-domain WMNs, we proposed a new ID-based signcryption scheme and accordingly present a novel ID-based handover protocol for mesh points. The mutual authentication and key establishment of two mesh points which belong to different trust domains can be achieved by using a single one-round message exchange during the authentication phase. The authentication server is not involved in our handover authentication protocol so that mutual authentication can be completed directly by the mesh points. Meanwhile, the data transmitted between the two mesh points can be carried by the authentication messages. Moreover, there are no restrictions on the PKG system parameters in our proposed multi-domain ID-based signcryption scheme so our handover scheme can be easily applied to real WMNs circumstances. Security of the signcryption scheme is proved in the random oracle model. It shows that our protocol satisfies the basic security requirements and is resistant to existing attacks based on the security of the signcryption. The analysis of the performance demonstrates that the protocol is efficient and suitable for the multi-domain WMNs environment.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제55권4호
• /
• pp.165-172
• /
• 2006

In this paper we present a technique for detecting cross-reference points that allows improving watermark detect-ability. In general, Harris detector is commonly used for finding salient points. Harris detector is a kind of combined corner and edge detector which is based on neighboring image data distribution, therefore it has some limitation to find accurate salient points after watermark embedding or any kinds of digital attacks. The new method proposed in this paper used not data distribution but geometrical structure of a normalized image in order to avoid pointing error caused by the distortion of image data. After normalization, we constructed pre-specified number of virtual lines from top to bottom and left to right, and several of cross points were selected by a random key. These selected points specify almost same positions with the accuracy more than that of Harris detector after digital attacks. These points were arranged by a random key, and blocks centered in these points were formed. A reference watermark is formed by a block and embedded in the next block. Because same alteration is applied to the watermark generated and embedded blocks. the detect-ability of watermark is improved even after digital attacks.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2003년도 추계종합학술대회 논문집
• /
• pp.271-275
• /
• 2003

본 논문은 기하학적으로 왜곡된 입 모양을 보정하는 기법을 제안한다. 제안한 기법은 특징추출 단계와 보정 단계로 구성된다. 특징추출 단계에서는 원영상과 목적영상의 입술모델에 따라 각각의 특징과 특징점을 찾고 보정 단계에서는 부분 영상의 사상위치를 결정하고 어파인 변환을 적용하여 입의 왜곡을 보정한다. 여러 형태의 입모양을 실험한 결과, 많은 부분에 존재하는 왜곡이 보정된 것으로 나타났다.

• Journal of Acupuncture Research
• /
• 제33권4호
• /
• pp.1-6
• /
• 2016

Objectives : The purpose of this report is to inform readers of the important aspects of about acupuncture and the process of Hwangjenaegyeong Yongchu. Methods : We researched the word 'acupuncture' through Hwangjenaegyeong Youngchu. We formed three categories according to the meanings of the key aspects of acupuncture in each sentence. Results : In Hwangjenaegyeong Youngchu, the meanings of the key aspects of acupuncture (刺鍼之要) are follows : 1. The key aspect of acupuncture(刺鍼之要) is to control Gi & Sin(調氣治神). 2. Before administering acupuncture, a doctor must know Meridian, acu-points, contraindication of nature, Bo-sa acupuncture(補瀉), Deug Gi(得氣), the role of the acupuncture needle(官鍼), the number of the needle, Gi & condition of patients, and pulse diagnosis. 3. For acupuncture, there are several things to be aware of : contraindication of acupuncture, deleteriousness of acupuncture, acu-points, and Bo-sa acupuncture(補瀉).

• International Journal of Quality Innovation
• /
• 제3권2호
• /
• pp.84-92
• /
• 2002

In this Paper, We propose new performance measure model in Logistic Industry. New model has been learned by key points of PZB model and advanced structure of MBNQA which has cause measure points and effect measure points. The Structure of new performance measure model is Cubic Model which is reflected with time. We try to verify this model apply advance logistic company.

• 드라이브 ㆍ 컨트롤
• /
• 제21권2호
• /
• pp.65-71
• /
• 2024

In this study, we suggested a key-point detection method for robot harvesting of oriental melon. Our suggested method could be used to detect the detachment part and major composition of oriental melon. We defined four points (harvesting point, calyx, center, bottom) based on tomato with characteristics similar to those of oriental melon. The evaluation of estimated key-points was conducted by pixel error and PDK (percentage of detected key-point) index. Results showed that the average pixel error was 18.26 ± 16.62 for the x coordinate and 17.74 ± 18.07 for the y coordinate. Considering the resolution of raw images, these pixel errors were not expected to have a serious impact. The PDK score was found to be 89.5% PDK@0.5 on average. It was possible to estimate oriental melon specific key-point. As a result of this research, we believe that the proposed method can contribute to the application of harvesting robot system.