• Title/Summary/Keyword: Text Region Detection

Search Result 54, Processing Time 0.024 seconds

ROI Image Compression Method Using Eye Tracker for a Soldier (병사의 시선감지를 이용한 ROI 영상압축 방법)

  • Chang, HyeMin;Baek, JooHyun;Yang, DongWon;Choi, JoonSung
    • Journal of the Korea Institute of Military Science and Technology
    • /
    • v.23 no.3
    • /
    • pp.257-266
    • /
    • 2020
  • It is very important to share tactical information such as video, images, and text messages among soldiers for situational awareness. Under the wireless environment of the battlefield, the available bandwidth varies dynamically and is insufficient to transmit high quality images, so it is necessary to minimize the distortion of the area of interests such as targets. A natural operating method for soldiers is also required considering the difficulty in handling while moving. In this paper, we propose a natural ROI(region of interest) setting and image compression method for effective image sharing among soldiers. We verify the proposed method through prototype system design and implementation of eye gaze detection and ROI-based image compression.

Seal Detection in Scanned Documents (스캔된 문서에서의 도장 검출)

  • Yu, Kyeonah;Kim, Kyung-Hye
    • Journal of the Korea Society of Computer and Information
    • /
    • v.18 no.12
    • /
    • pp.65-73
    • /
    • 2013
  • As the advent of the digital age, documents are often scanned to be archived or to be transmitted over the network. The largest proportion of documents is texts and the next is seal images indicating the author of the documents. While a lot of research has been conducted to recognize texts in scanned documents and commercialized text recognizing products are developed as highlighted the importance of the scanned document, information about seal images is discarded. In this paper, we study how to extract the seal image area from the color or black and white document containing the seal image and how to save the seal image. We propose a preprocessing step to remove other components except for the candidate outlines of the seal imprint from scanned documents and a method to select the final region of interest from these candidates by using the feature of seal images. Also in case of a seal imprint overlapped with texts, the most similar image among those stored in the database is selected through the template matching process. We verify the implemented system for a various type of documents produced in schools and analyze the results.

Differences in Breast and Cervical Cancer Screening Rates in Jordan among Women from Different Socioeconomic Strata: Analysis of the 2012 Population-Based Household Survey

  • Al Rifai, Rami;Nakamura, Keiko
    • Asian Pacific Journal of Cancer Prevention
    • /
    • v.16 no.15
    • /
    • pp.6697-6704
    • /
    • 2015
  • Background: The burden of breast and cervical cancer is changing over time in developing countries. Regular screening is very important for early detection and treatment. In this study, we assessed inequalities in breast and cervical cancer screening rates in women according to household wealth status, and analyzed the potential predictors associated with a low cancer screening rate in Jordan. Materials and Methods: A nationwide populationbased cross-sectional survey collected information on different variables at the national level. All ever-married women (the phrase is used throughout the text to refer to women who had ever married) aged 15-49 years were included in the survey. Analysis of breast self-examination (BSE) and clinical breast examination (CBE) at least once in the previous year was carried out in 11,068 women, while lifetime Pap-smear testing was carried out in 8,333 women, aged 20-49 years. Results: Over 39% and 19% of ever-married Jordanian women reported having undergone a breast examination during the previous year and Pap smear examination at least once in their lifetime, respectively. The rate of BSE in the previous year was 31.5%, that of CBE in the previous year was 19.3%, and that of Pap smear examination at least once in life was 25.5%. The adjusted OR was higher for performing BSE (aOR 1.22, 95% CI 1.04-1.43), undergoing CBE (aOR 1.31, 95% CI 1.08-1.60) and undergoing Pap smear examination (aOR 2.38, 95% CI 1.92-2.93) among women in the highest wealth-index quintile as compared to those in the lowest quintile. The concentration index was 0.11 for BSE, 0.01 for CBE, and 0.27 for Pap smear examination. Women in their twenties, living in rural or the southern region of Jordan, with an elementary school education or less, who listened to the radio or read the newspaper not more than a few times a year, and nulliparous women were less likely to undergo breast and cervical cancer screening. Conclusions: The rates of breast and cervical cancer screening are low in Jordan. Reducing the sociodemographic and economic inequalities in breast and cervical cancer screenings requires concerted outreach activities for women living under socially deprived conditions.

A Macro Attacks Detection Model Based on Trace Back Information (트레이스 백 정보에 기반한 매크로 공격 탐지 모델)

  • Baek, Yong Jin;Hong, Suk Won;Park, Jae Heung;Kang, Gyeong Won;Kim, Sang Bok
    • Convergence Security Journal
    • /
    • v.18 no.5_1
    • /
    • pp.113-120
    • /
    • 2018
  • Today, the development of information and communication technology is rapidly increasing the number of users of network-based service, and enables real-time information sharing among users on the Internet. There are various methods in the information sharing process, and information sharing based on portal service is generally used. However, the process of information sharing serves as a cause of illegal activities in order to amplify the social interest of the relevant stakeholders. Public opinion attack using macro function can distort normal public opinion, so security measures are urgent. Therefore, security measures are urgently needed. Macro attacks are generally defined as attacks in which illegal users acquire multiple IP or ID to manipulate public opinion on the content of a particular web page. In this paper, we analyze network path information based on traceback for macro attack of a specific user, and then detect multiple access of the user. This is a macro attack when the access path information for a specific web page and the user information are matched more than once. In addition, when multiple ID is accessed for a specific web page in the same region, it is not possible to distort the overall public opinion on a specific web page by analyzing the threshold count value.

  • PDF