• Title/Summary/Keyword: Image Search System

Search Result 395, Processing Time 0.026 seconds

Hidden Markov Model-based Extraction of Internet Information (은닉 마코브 모델을 이용한 인터넷 정보 추출)

  • Park, Dong-Chul
    • Journal of the Institute of Electronics Engineers of Korea CI
    • /
    • v.46 no.3
    • /
    • pp.8-14
    • /
    • 2009
  • A Hidden Markov Model(HMM)-based information extraction method is proposed in this paper. The proposed extraction method is applied to extraction of products' prices. The input of the proposed IESHMM is the URLs of a search engine's interface, which contains the names of the product types. The output of the system is the list of extracted slots of each product: name, price, image, and URL. With the observation data set Maximum Likelihood algorithm and Baum-Welch algorithm are used for the training of HMM and The Viterbi algorithm is then applied to find the state sequence of the maximal probability that matches the observation block sequence. When applied to practical problems, the proposed HMM-based system shows improved results over a conventional method, PEWEB, in terms of recall ration and accuracy.

A Study on Developing XML Marine GIS metadata (XML 형식의 해양GIS 메타데이터 작성에 관한 연구)

  • Oh, Se-Woong;Park, Jong-Min;Suh, Sang-Hyun
    • Journal of Navigation and Port Research
    • /
    • v.28 no.3
    • /
    • pp.247-252
    • /
    • 2004
  • It's important to develop Metadata standard to manage a large of marine geospatial data such as observation, ocean survey, satellite image more effectively. If we use metadata in Marine GIS we can make sense marine geospatial data, make the most of marine dataset. International standard organization's work and NGIS's standard are a good example to illustrate metadata standard's importance. But we don't have metadata standard for marine dataset, so it's difficult to search and use geospatial data In this paper, we presented common marine metadata element, and composited metadata implementation schema. Finally we constructed marine GIS metadata editing tool..

Passports Recognition Using ART2-Based RBF Network (ART2 기반 RBF 네트워크를 이용한 여권 인식)

  • Kim Kwang-Baek;Oh Am-Suk
    • Journal of Korea Multimedia Society
    • /
    • v.8 no.5
    • /
    • pp.700-706
    • /
    • 2005
  • The immigration control system authorizes the immigration of travelers by means of passport inspections such as the judgment of forged passports, the search for a wanted criminal or a person disqualified for immigration, etc. The judgment of forged passports plays an important role in the immigration control system. Therefore, as the pre-phase for the judgment of forged passports, this paper proposed a novel method for the recognition of passport using ART2-based RBF network. The proposed method extracts the area of code and individual codes by applying the Sobel masking, the smearing and the contour tracking algorithm in turn to the passport image. This paper proposed the RBF network that applies the ART2 algorithm to the middle layer, and applied the enhanced RBF network to the recognition of individual codes. The results of the experiments for performance evaluation on the real passport images showed that the proposed method has the better performance compared with other approaches.

  • PDF

Work Environment Monitoring of Workers Using Wearable Sensor and Helmet (착용형 센서와 헬멧을 이용한 작업자의 작업환경 모니터링)

  • Gu, Ye-Jin;Kim, Jong-Jin;Chung, Wan-Young
    • Journal of the Institute of Convergence Signal Processing
    • /
    • v.20 no.2
    • /
    • pp.91-98
    • /
    • 2019
  • Accidents of worker that occur in isolated places are difficult to rescue, unlike general construction accidents. There is a problem of communication limitation when an accident occurs in an isolated place. Also, it is difficult to search the accident place due to the absence of CCTV. In order to solve these problems, this paper proposes a device that combines IoT technology with a safety helmet, which must be worn in the workplace. The proposed device additionally designs and implements a real-time PPG(Photoplethysmography) sensor, body temperature sensor, accelerometer sensor and a camera sensor on the helmet. The proposed helmet system allows the user and the control center to monitor the state of the worker. In addition, when an abnormal biological signal or fall occurs to the worker, the image is transmitted to the control center. By using the proposed system, it is possible to check the status of the worker in real time, so that it has an advantage that it can cope with the accident quickly.

Recognition of Natural Hand Gesture by Using HMM (HMM을 이용한 자연스러운 손동작 인식)

  • Kim, A-Ram;Rhee, Sang-Yong
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.22 no.5
    • /
    • pp.639-645
    • /
    • 2012
  • In this paper, we propose a method that gives motion command to a mobile robot to recognize human being's hand gesture. Former way of the robot-controlling system with the movement of hand used several kinds of pre-arranged gesture, therefore the ordering motion was unnatural. Also it forced people to study the pre-arranged gesture, making it more inconvenient. To solve this problem, there are many researches going on trying to figure out another way to make the machine to recognize the movement of the hand. In this paper, we used third-dimensional camera to obtain the color and depth data, which can be used to search the human hand and recognize its movement based on it. We used HMM method to make the proposed system to perceive the movement, then the observed data transfers to the robot making it to move at the direction where we want it to be.

A Study on 'Care Work' Directionality of Child Care Helper in Healthy Family Support Centers (건강가정지원센터 아이 돌봄 활동가의 '돌봄 노동' 방향성 연구)

  • Lee, Eun-Joo;Jun, Mi-Kyung
    • Journal of Families and Better Life
    • /
    • v.32 no.2
    • /
    • pp.27-40
    • /
    • 2014
  • The purpose of this study is to examine the motive of participating in the care work, the overall cognition survey for the care work and the infant care practice areas required in the care work for the child care helpers who activate in the care work, and search for methods of specializing infant care and care experiences on the results. Results of study showed that firstly, middle- or the late middle-age women participated in the care worker recognized care work as productive labor to create economic value and that secondly, the child care helpers' recognition degree of self-development and job satisfaction through performance of care work was wholly high level and that there was will of participation in training for self-development but actual participation rate was low due to restrictions by general conditions. Thirdly, the infant care practice areas and their particular contents that the child care helpers recognized in the care work necessary were highly shown in the whole. The requested level of education for safety management, play guidance, humanity guidance for infant and child was high. Point to discuss is that occupation stability and occupation image must be raised through the public job-hunting system for the child care helpers. In addition, a tailor-made education support suitable for the child care helpers' career stage is needed. Education support by the performance of infant care practice area and the educational requirements must be provided to major rearers to ensure that they can function as behavioral and emotional supporters. Finally, a support system for continuous self-management.

A Study on the Interactive Architecture in Nature Environment

  • Baek, Seung-Man
    • Journal of the Regional Association of Architectural Institute of Korea
    • /
    • v.20 no.6
    • /
    • pp.41-46
    • /
    • 2018
  • The context of innovation in which we evolve today, subtracts us in a spacial reality and virtuality (digital) that aimed less and less to interact with natural processes which could converge to new possible relationships in the world. We constantly live in presence of fluctuations and imperceptible natural energies (wind, solar radiation, etc.) defined by flows, their own physicality, which remains without being virtual, elusive. This study first outlines how these energies already exploited within the framework of production, could be thought as interactive of our habitat's space dimension, as a prolongation of a physical and material environment built by men and for men, giving rise to new social, cultural dynamics, and making natural complexity of our space vivid, comprehensible with new visual and physical clues. In recent days, where lifestyles are changing, architecture no longer needs to limit its scope of creation to only built structures. Based on a deeper understanding of human and through new potential advanced technologies (kinetic system, etc), it is time to fundamentally diagnose what environments or devices contribute to our lives. Architecture becomes ${\ll}interface{\gg}$, step up its fundamental role, and newly defines the sturdy image and tectonics of existing environment, establishing a stance to search for a new typology. In the end, building will show two simultaneous and distinctive connections related to its physical existence: reality in its function and irreductibility, in its ability to forge new dynamic connections with its environment, hybridizing the spatial dimension to a new form of physicality, adaptive and incessantly flexible in the dimension time, becoming a vessel for ever changing contemporary lifestyles.

Study on Remote Face Recognition System Using by Multi Thread on Distributed Processing Server (분산처리서버에서의 멀티 쓰레드 방식을 적용한 원격얼굴인식 시스템)

  • Kim, Eui-Sun;Ko, Il-Ju
    • The Journal of Korean Institute of Next Generation Computing
    • /
    • v.13 no.5
    • /
    • pp.19-28
    • /
    • 2017
  • Various methods for reducing the load on the server have been implemented in performing face recognition remotely by the spread of IP security cameras. In this paper, IP surveillance cameras at remote sites are input through a DSP board equipped with face detection function, and then face detection is performed. Then, the facial region image is transmitted to the server, and the face recognition processing is performed through face recognition distributed processing. As a result, the overall server system load and significantly reduce processing and real-time face recognition has the advantage that you can perform while linked up to 256 cameras. The technology that can accomplish this is to perform 64-channel face recognition per server using distributed processing server technology and to process face search results through 250 camera channels when operating four distributed processing servers there was.

Convergence and Integration Review of Fire fighter Image through Disaster Movies (재난 영화를 통해 본 소방관 이미지에 대한 융·복합적 고찰)

  • Lee, In-Seob;Kim, Jee-Hee;Kim, Yun-Jeong
    • Journal of the Korea Convergence Society
    • /
    • v.8 no.2
    • /
    • pp.91-97
    • /
    • 2017
  • The purpose of the study was to investigate the fire fighter image through disaster movies in Korea and other countries. From September 1 to 7, 2016, the movie search methods were carried out using movie title and key words via Wikipedia and various internet web sites from 1903 to 2016. The results included that the fire fighters had been considered as the precious person of volunteer activity regarding fire suppression, investigators, and self-sacrifice. Through the convergence and integration review of the disaster movie, this research suggested that the national based establishment of the welfare and safety system for the posttraumatic stress disorder(PTSD) and critical incident stress management(CISM) education program. This study will provide the basic data for the development of welfare and safety management for the fire fighters and let the people know the sacrifice of the fire fighters including the motto, "First in and the last out".

A Combined Hough Transform based Edge Detection and Region Growing Method for Region Extraction (영역 추출을 위한 Hough 변환 기반 에지 검출과 영역 확장을 통합한 방법)

  • N.T.B., Nguyen;Kim, Yong-Kwon;Chung, Chin-Wan;Lee, Seok-Lyong;Kim, Deok-Hwan
    • Journal of KIISE:Databases
    • /
    • v.36 no.4
    • /
    • pp.263-279
    • /
    • 2009
  • Shape features in a content-based image retrieval (CBIR) system are divided into two classes: contour-based and region-based. Contour-based shape features are simple but they are not as efficient as region-based shape features. Most systems using the region-based shape feature have to extract the region firs t. The prior works on region-based systems still have shortcomings. They are complex to implement, particularly with respect to region extraction, and do not sufficiently use the spatial relationship between regions in the distance model In this paper, a region extraction method that is the combination of an edge-based method and a region growing method is proposed to accurately extract regions inside an object. Edges inside an object are accurately detected based on the Canny edge detector and the Hough transform. And the modified Integrated Region Matching (IRM) scheme which includes the adjacency relationship of regions is also proposed. It is used to compute the distance between images for the similarity search using shape features. The experimental results show the effectiveness of our region extraction method as well as the modified IRM. In comparison with other works, it is shown that the new region extraction method outperforms others.