• 제목/요약/키워드: text enhancement

검색결과 71건 처리시간 0.029초

장면 텍스트 영역 추출을 위한 적응적 에지 강화 기반의 기울기 검출 및 보정 (The Slope Extraction and Compensation Based on Adaptive Edge Enhancement to Extract Scene Text Region)

  • 백재경;장재혁;서영건
    • 디지털콘텐츠학회 논문지
    • /
    • 제18권4호
    • /
    • pp.777-785
    • /
    • 2017
  • 실세계에서 텍스트가 포함 된 장면은 텍스트를 추출하고 인식하여 많은 정보를 얻을 수 있으므로, 장면의 텍스트 영역을 추출하고 인식하는 기술들은 꾸준히 발전하고 있다. 장면에서 텍스트 영역을 추출하는 기술은 크게 텍스쳐를 기반으로 하는 방법과 연결요소방법, 그리고 이 둘을 적절히 혼합하는 방법들로 구분 할 수 있다. 텍스처를 기반으로 하는 방법은 영상의 색상, 명도 등의 정보를 이용하여 텍스트가 다른 요소와는 다른 값을 갖는다는 것을 기반으로 한다. 연결 요소 방법은 장면의 각 화소마다 인접해 있는 유사 화소를 연결 요소로 만들어 기하학적인 특성을 이용하여 판별한다. 본 논문에서는 텍스트 영역 추출의 정확도를 높이기 위해 영상의 기울기를 검출하고 보정한 후 에지를 적응적으로 변경하는 방법을 제안한다. 제안 방법은 영상의 기울기를 보정한 후 텍스트가 포함 된 정확한 영역만 추출하기 때문에 MSER보다 15%, EEMSER보다 10% 더 정확하게 영역을 얻었다.

Enhancement of L-Threonine Production by Controlling Sequential Carbon-Nitrogen Ratios during Fermentation

  • Lee, Hyeok-Won;Lee, Hee-Suk;Kim, Chun-Suk;Lee, Jin-Gyeom;Kim, Won-Kyo;Lee, Eun-Gyo;Lee, Hong-Weon
    • Journal of Microbiology and Biotechnology
    • /
    • 제28권2호
    • /
    • pp.293-297
    • /
    • 2018
  • Controlling the residual glucose concentration is important for improving productivity in $\text\tiny{L}$-threonine fermentation. In this study, we developed a procedure to automatically control the feeding quantity of glucose solution as a function of ammonia-water consumption rate. The feeding ratio ($R_{C/N}$) of glucose and ammonia water was predetermined via a stoichiometric approach, on the basis of glucose-ammonia water consumption rates. In a 5-L fermenter, 102 g/l $\text\tiny{L}$-threonine was obtained using our glucose-ammonia water combined feeding strategy, which was then successfully applied in a 500-L fermenter (89 g/l). Therefore, we conclude that an automatic combination feeding strategy is suitable for improving $\text\tiny{L}$-threonine production.

The Role of Visual Enhancement and Awareness in L2 Learning

  • Lim, Ja-Yeon
    • 영어어문교육
    • /
    • 제9권spc호
    • /
    • pp.99-112
    • /
    • 2003
  • This study investigated how different types of formal instruction affect the second language looming of English grammatical structure among Korean high-school students. The linguistic focus of the study was English present perfect, which often creates learning problems for Korean learners of English. Subjects were divided into a control group and an experimental group (Enhanced group). The input the subjects in the experimental group received was manipulated by visually enhancing (with highlighting of the target structures in a reading text). Learners' awareness of the rules throughout the treatment period, as well as accuracy of target structures was measured. Results indicated that subjects in the Enhanced group showed higher performance than the control group. Further, awareness of rules that learners developed over the treatment period did not provide any advantage in learning.

  • PDF

Investigation of Terminology Coverage in Radiology Reporting Templates and Free-text Reports

  • Hong, Yi;Zhang, Jin
    • International Journal of Knowledge Content Development & Technology
    • /
    • 제5권1호
    • /
    • pp.5-14
    • /
    • 2015
  • The Radiological Society of North America (RSNA) is improving reporting practices by developing an online library of clear and consistent report templates. To compare term occurrences in free-text radiology reports and RSNA reporting templates, the Wilcoxon signed-rank test method was applied to investigate how much of the content of conventional narrative reports is covered by the terms included in the RSNA reporting templates. The results show that the RSNA reporting templates cover most terms that appear in actual radiology reports. The Wilcoxon test may be helpful in evaluatingexisting templates and guiding the enhancement of reporting templates.

Rapid and Brief Communication GPU implementation of neural networks

  • Oh, Kyoung-Su;Jung, Kee-Chul
    • 한국HCI학회:학술대회논문집
    • /
    • 한국HCI학회 2007년도 학술대회 3부
    • /
    • pp.322-325
    • /
    • 2007
  • Graphics processing unit (GPU) is used for a faster artificial neural network. It is used to implement the matrix multiplication of a neural network to enhance the time performance of a text detection system. Preliminary results produced a 20-fold performance enhancement using an ATI RADEON 9700 PRO board. The parallelism of a GPU is fully utilized by accumulating a lot of input feature vectors and weight vectors, then converting the many inner-product operations into one matrix operation. Further research areas include benchmarking the performance with various hardware and GPU-aware learning algorithms. (c) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

Digital enhancement of pronunciation assessment: Automated speech recognition and human raters

  • Miran Kim
    • 말소리와 음성과학
    • /
    • 제15권2호
    • /
    • pp.13-20
    • /
    • 2023
  • This study explores the potential of automated speech recognition (ASR) in assessing English learners' pronunciation. We employed ASR technology, acknowledged for its impartiality and consistent results, to analyze speech audio files, including synthesized speech, both native-like English and Korean-accented English, and speech recordings from a native English speaker. Through this analysis, we establish baseline values for the word error rate (WER). These were then compared with those obtained for human raters in perception experiments that assessed the speech productions of 30 first-year college students before and after taking a pronunciation course. Our sub-group analyses revealed positive training effects for Whisper, an ASR tool, and human raters, and identified distinct human rater strategies in different assessment aspects, such as proficiency, intelligibility, accuracy, and comprehensibility, that were not observed in ASR. Despite such challenges as recognizing accented speech traits, our findings suggest that digital tools such as ASR can streamline the pronunciation assessment process. With ongoing advancements in ASR technology, its potential as not only an assessment aid but also a self-directed learning tool for pronunciation feedback merits further exploration.

Linguistic and Stylistic Markers of Influence in the Essayistic Text: A Linguophilosophic Aspect

  • Kolkutina, Viktoriia;Orekhova, Larysa;Gremaliuk, Tetiana;Borysenko, Natalia;Fedorova, Inna;Cheban, Oksana
    • International Journal of Computer Science & Network Security
    • /
    • 제22권5호
    • /
    • pp.163-167
    • /
    • 2022
  • The article explores linguo-stylistic influence markers in essayistic texts. The novelty of this investigation is provided by its perspective. Essayism is looked at as a style of thinking and writing and studied as a holistic philosophical and cultural phenomenon, as a revalent form of comprehension of reality that features non-lasting author's judgements and enhancement of the author's voice in the text. Based on the texts by V. Rosanov, G.K. Chesterton, and D. Dontsov, the remarkable English, Russian, and Ukrainian essay-writers of the first party of the 20th century, the article tracks the typical ontological-and-existentialist correlation at the content, stylistic, and semantic levels. It is observed in terms of the ideas presented in the texts of these publicists and the lexicostylistic markers of the influence on the reader that enable these ideas to implement. The explored poetic syntax, key lexemes, dialogueness, intonational melodics, specific language, free associations, aphoristic nature, verbalization of emotions and feeling in the psycholinguistic form of their expression, stress, heroic elevation, metaphors and evaluative linguistic units in the ontological-and-existentialist aspects contribute to extremely delicate and demanding nature of the essayistic style. They create a "lacework" of unpredictable properties, intellectual illumination, unexpected similarity, metaphorical freshness, sudden discoveries, unmotivated unities.

Okapi BM25 단어 가중치법 적용을 통한 문서 범주화의 성능 향상 (A Research on Enhancement of Text Categorization Performance by using Okapi BM25 Word Weight Method)

  • 이용훈;이상범
    • 한국산학기술학회논문지
    • /
    • 제11권12호
    • /
    • pp.5089-5096
    • /
    • 2010
  • 문서 범주화는 정보검색 시스템의 중요한 기능중의 하나로 문서들을 어떤 기준에 의해 그룹화를 하는 것을 말한다. 범주화의 일반적인 방법은 대상 문서에서 중요한 단어들을 추출하고 가중치를 부여한 후에 분류 알고리즘에 따라 문서를 분류한다. 따라서 성능과 정확성은 분류 알고리즘에 의해 결정됨으로 알고리즘의 효율성이 중요하다. 본 논문에서는 단어 가중치 계산 방법을 개선하여 문서분류 성능을 향상시키는 것을 소개하였다. Okapi BM25 단어 가중치법은 일반적인 정보검색분야에서 사용되어 검색 결과에 좋은 결과를 보여주고 있다. 이를 적용하여 문서 범주화에서도 좋은 성능을 보이는지를 실험하였다. 비교한 단어 가중치법에는 가장 일반적인 TF-IDF법와 문서분류에 최적화된 가중치법 TF-ICF법, 그리고 문서요약에서 많이 사용되는 TF-ISF법을 이용하여 4가지 가중치법에 따라 결과를 측정하였다. 실험에 사용한 문서로는 Reuter-21578 문서를 사용하였으며 분류기 알고리즘으로는 Support Vector Machine(SVM)와 K-Nearest Neighbor(KNN)알고리즘을 사용하여 실험하였다. 사용된 가중치법 중 Okapi BM25 법이 가장 좋은 성능을 보였다.

인터넷 쇼핑몰 웹접근성 평가 및 대체 텍스트율 향상 방안 구현 (Web Accessibility Evaluation of Internet Shopping Malls and Development of Alternative Text Rate Improvement Tool)

  • 임경규;이구연;김화종
    • 디지털콘텐츠학회 논문지
    • /
    • 제19권3호
    • /
    • pp.537-546
    • /
    • 2018
  • 본 논문에서는 국내 인터넷 쇼핑몰 웹사이트의 웹접근성 향상을 위한 연구를 수행한다. 먼저 국내 웹접근성의 기준을 분석하고, 이어 국내 주요 인터넷 쇼핑몰 웹사이트의 웹접근성 평가를 실행하여, 인터넷 쇼핑몰 웹 사이트가 가지고 있는 웹접근성 현안 문제를 도출하고 분석한다. 이러한 국내 인터넷 쇼핑몰 웹사이트의 웹접근성에 대한 평가를 근거로 하여 웹 접근성을 향상시키기 위한 대체텍스트 비율을 높이기 위한 방법으로 엑셀 VBA를 이용한 대체텍스트 향상 방법을 제안하고 구현한다. 제안된 방법을 사용할 경우 웹 프로그래밍 전문지식이 없더라도 웹페이지에 포함된 이미지의 대체 텍스트를 확인하고 수정할 수 있게 되어 웹접근성 준수율 향상에 도움이 될 수 있다.