• Title/Summary/Keyword: OCR(Optical Character Recognition) technology

Search Result 46, Processing Time 0.018 seconds

A Real-time Bus Arrival Notification System for Visually Impaired Using Deep Learning (딥 러닝을 이용한 시각장애인을 위한 실시간 버스 도착 알림 시스템)

  • Seyoung Jang;In-Jae Yoo;Seok-Yoon Kim;Youngmo Kim
    • Journal of the Semiconductor & Display Technology
    • /
    • v.22 no.2
    • /
    • pp.24-29
    • /
    • 2023
  • In this paper, we propose a real-time bus arrival notification system using deep learning to guarantee movement rights for the visually impaired. In modern society, by using location information of public transportation, users can quickly obtain information about public transportation and use public transportation easily. However, since the existing public transportation information system is a visual system, the visually impaired cannot use it. In Korea, various laws have been amended since the 'Act on the Promotion of Transportation for the Vulnerable' was enacted in June 2012 as the Act on the Movement Rights of the Blind, but the visually impaired are experiencing inconvenience in using public transportation. In particular, from the standpoint of the visually impaired, it is impossible to determine whether the bus is coming soon, is coming now, or has already arrived with the current system. In this paper, we use deep learning technology to learn bus numbers and identify upcoming bus numbers. Finally, we propose a method to notify the visually impaired by voice that the bus is coming by using TTS technology.

  • PDF

Study for the Pseudonymization Technique of Medical Image Data (의료 이미지 데이터의 비식별화 방안에 관한 연구)

  • Baek, Jongil;Song, Kyoungtaek;Choi, Wonkyun;Yu, Khiguen;Lee, Pilwoo;In, Hanjin;Kim, Cheoljung;Yeo, Kwangsoo;Kim, Soonseok
    • Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
    • /
    • v.6 no.6
    • /
    • pp.103-110
    • /
    • 2016
  • The recent frequent cases of damage due to leakage of medical data and the privacy of medical patients is increasing day by day. The government says the Privacy Rule regulations established for these victims, such as prevention. Medical data guidelines can be seen 'national medical privacy guidelines' is only released. When replacing the image data between the institutions it has been included in the image file (JPG, JPEG, TIFF) there is exchange of data in common formats such as being made when the file is leaked to an external file there is a risk that the exposure key identification information of the patient. This medial image file has no protection such as encryption, This this paper, introduces a masking technique using a mosaic technique encrypting the image file contains the application to optical character recognition techniques. We propose pseudonymization technique of personal information in the image data.

Automatic Extraction of Route Information from Road Sign Imagery

  • Youn, Junhee;Chong, Kyusoo
    • Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
    • /
    • v.33 no.6
    • /
    • pp.595-603
    • /
    • 2015
  • With the advances of the big-data process technology, acquiring the real-time information from the massive image data taken by a mobile device inside a vehicle will be possible in the near future. Among the information that can be found around the vehicle, the route information is needed for safe driving. In this study, the automatic extraction of route information from the road sign imagery was dealt with. The scope of the route information in this study included the route number, route type, and their relationship with the driving direction. For the recognition of the route number, the modified Tesseract OCR (Optical Character Recognition) engine was used after extracting the rectangular-road-sign area with the Freeman chain code tracing algorithm. The route types (expressway, highway, rural highway, and municipal road) are recognized using the proposed algorithms, which are acquired from colour space analysis. Those road signs provide information about the route number as well as the roads that may be encountered along the way. In this study, such information was called “OTW (on the way)” or “TTW (to the way)” which between the two should be indicated is determined using direction information. Finally, the route number is matched with the direction information. Experiments are carried out with the road sign imagery taken inside a car. As a result, route numbers, route number type, OTW or TTW are successfully recognized, however some errors occurred in the process of matching TTW number with the direction.

A Simulator for the Validation of Non-invasive Blood Pressure (NIBP) Monitoring Devices (자동혈압계 성능평가를 위한 인체혈압 시뮬레이터 개발)

  • Doh, Il;Lim, Hyun Kyoon;Ahn, Bongyoung;Chee, Youngjoon;Lee, Jongshill;OH, Jae Hoon
    • Journal of Biomedical Engineering Research
    • /
    • v.38 no.3
    • /
    • pp.111-115
    • /
    • 2017
  • Blood pressure is one of the important vital signs for monitoring the medical condition of a patient. Automated NIBP(non-invasive blood pressure) monitoring devices calculate systolic and diastolic blood pressures from the oscillation in cuff pressure caused by a pulsation of an artery. To validate the NIBP devices, we developed a simulator to supply the oscillometric waveforms obtained from human subjects. The simulator provided pressure pulses to device-under-test and device readings were compared to the auscultatory references. Fully automated simulation system including OCR(optical character recognition) were developed and used for NIBP monitoring devices. The validation results using the simulator agreed well with previous clinical validation. More validation studies using the standardized oscillometric waveforms would be required for the replacement of clinical trials to validate a new automated NIBP monitoring device.

Improving International Access to the IARC Monographs Database with Linkage to other Sources of Information

  • Rice, Jerry M.;Waters, Michael D.;Wright, R.Glenn
    • Toxicological Research
    • /
    • v.17
    • /
    • pp.227-236
    • /
    • 2001
  • The IARC Monographs Programme on the Evaluation of Carcinogenic Risks to Humans has reviewed, summarized and evaluated 869 environmental agents and exposures as oj June 2000. This large collection includes all relevant published epidemiological data on cancer in exposed humans and results of bioassays for carcinogenicity in experimental animals. Since 1986. cancer data have been systematically supplemented by summaries of other toxicological data that are relevant to assessments of carcinogenic hazard. These include summaries qf genetic and related effects of chemicals. which have been prepared as Genetic Activity Profiles (GAP) by the U.S. EPA in collaboration with IARC. As the Mono-graphs have proved increasingly valuable and influential worldwide. they have evolved into an encyclopedia on environmental carcinogenic risks to humans. However. the Monographs have historically been prepared only as printed books with limited distribution. and the Monographs Programme has needed to adjust to expectations oj wider availability. Since 1998 the evaluations and summaries have been globally accessible by Internet from IARC (http://www.iarc.fr) and the GAP profiles by Internet from EPA (http://www.epa.gov/gapdb/). with the two web sites linked. Improved EPN/ARC GAP database and software. GAP2000. now link GAP profiles directly to the appropriate IARC web pages for summaries of evaluations of a given compound and its overall IARC classification. During the year 2000. by means of optical character recognition (OCR) technology the entire series of IARC Monographs is being converted to an electronic version. The first edition is now available commercially in CD-ROM format and will soon become available on-line at .

  • PDF

Individual Ortho-rectification of Coast Guard Aerial Images for Oil Spill Monitoring (유출유 모니터링을 위한 해경 항공 영상의 개별정사보정)

  • Oh, Youngon;Bui, An Ngoc;Choi, Kyoungah;Lee, Impyeong
    • Korean Journal of Remote Sensing
    • /
    • v.38 no.6_1
    • /
    • pp.1479-1488
    • /
    • 2022
  • Accidents in which oil spills occur intermittently in the ocean due to ship collisions and sinkings. In order to prepare prompt countermeasures when such an accident occurs, it is necessary to accurately identify the current status of spilled oil. To this end, the Coast Guard patrols the target area with a fixed-wing airplane or helicopter and checks it with the naked eye or video, but it was difficult to determine the area contaminated by the spilled oil and its exact location on the map. Accordingly, this study develops a technology for direct ortho-rectification by automatically geo-referencing aerial images collected by the Coast Guard without individual ground reference points to identify the current status of spilled oil. First, meta information required for georeferencing is extracted from a visualized screen of sensor information such as video by optical character recognition (OCR). Based on the extracted information, the external orientation parameters of the image are determined. Images are individually orthorectified using the determined the external orientation parameters. The accuracy of individual orthoimages generated through this method was evaluated to be about tens of meters up to 100 m. The accuracy level was reasonably acceptable considering the inherent errors of the position and attitude sensors, the inaccuracies in the internal orientation parameters such as camera focal length, without using no ground control points. It is judged to be an appropriate level for identifying the current status of spilled oil contaminated areas in the sea. In the future, if real-time transmission of images captured during flight becomes possible, individual orthoimages can be generated in real time through the proposed individual orthorectification technology. Based on this, it can be effectively used to quickly identify the current status of spilled oil contamination and establish countermeasures.