• Title/Summary/Keyword: readability enhancement

Search Result 6, Processing Time 0.019 seconds

Readability Enhancement Algorithm for Patterned Retarder based Stereoscopic 3D display (Patterned Retarder 방식 입체 디스플레이에서의 가독성 향상 기법)

  • Lee, Hui Jung;Song, Byung Cheol
    • Journal of the Institute of Electronics and Information Engineers
    • /
    • v.50 no.5
    • /
    • pp.175-182
    • /
    • 2013
  • This paper proposes a readability enhancement filter for Patterned Retarder (PR) display. In general, when some texts in stereoscopic images are shown on PR display, their readability tends to be lowered. In order to overcome this problem, we present a readability enhancement algorithm which consists of readability filtering stage and post-processing stage for specific characters. First, each input stereo image is divided into an odd line image and an even line image. Then, they are independently up-scaled vertically by using Lanczos filter. Next, two up-scaled line images are averaged considering vertical phase difference. In post-processing stage, two specific characters which are normally difficult to read on PR display are detected, and they are filtered for additional readability enhancement. Here, this additional filtering is based on a specific brightness adjustment, and is applied only for two characters. The experiment results show that the proposed method achieves significant improvement in terms of readability in comparison with the previous scheme.

Readability Enhancement of English Speech Recognition Output Using Automatic Capitalisation Classification (자동 대소문자 식별을 이용한 영어 음성인식 결과의 가독성 향상)

  • Kim, Ji-Hwan
    • MALSORI
    • /
    • no.61
    • /
    • pp.101-111
    • /
    • 2007
  • A modified speech recogniser have been proposed for automatic capitalisation generation to improve the readability of English speech recognition output. In this modified speech recogniser, every word in its vocabulary is duplicated: once in a de-caplitalised form and again in the capitalised forms. In addition its language model is re-trained on mixed case texts. In order to evaluate the performance of the proposed system, experiments of automatic capitalisation generation were performed for 3 hours of Broadcast News(BN) test data using the modified HTK BN transcription system. The proposed system produced an F-measure of 0.7317 for automatic capitalisation generation with an SER of 48.55, a precision of 0.7736 and a recall of 0.6942.

  • PDF

Image Contrast and Sunlight Readability Enhancement for Small-sized Mobile Display (소형 모바일 디스플레이의 영상 컨트라스트 및 야외시인성 개선 기법)

  • Chung, Jin-Young;Hossen, Monir;Choi, Woo-Young;Kim, Ki-Doo
    • Journal of IKEEE
    • /
    • v.13 no.4
    • /
    • pp.116-124
    • /
    • 2009
  • Recently the CPU performance of modem chipsets or multimedia processors of mobile phone is as high as notebook PC. That is why mobile phone has been emerged as a leading ICON on the convergence of consumer electronics. The various applications of mobile phone such as DMB, digital camera, video telephony and internet full browsing are servicing to consumers. To meet all the demands the image quality has been increasingly important. Mobile phone is a portable device which is widely using in both the indoor and outside environments, so it is needed to be overcome to deteriorate image quality depending on environmental light source. Furthermore touch window is popular on the mobile display panel and it makes contrast loss because of low transmittance of ITO film. This paper presents the image enhancement algorithm to be embedded on image enhancement SoC. In contrast enhancement, we propose Clipped histogram stretching method to make it adaptive with the input images, while S-shape curve and gain/offset method for the static application And CIELCh color space is used to sunlight readability enhancement by controlling the lightness and chroma components which is depended on the sensing value of light sensor. Finally the performance of proposed algorithm is evaluated by using histogram, RGB pixel distribution, entropy and dynamic range of resultant images. We expect that the proposed algorithm is suitable for image enhancement of embedded SoC system which is applicable for the small-sized mobile display.

  • PDF

Mobile Text Readability Improvement Study of Korean Font - Focusing on Google Noto Sans Typeface -

  • Jae-Hong Park
    • Journal of the Korea Society of Computer and Information
    • /
    • v.28 no.8
    • /
    • pp.77-86
    • /
    • 2023
  • The background of this study lies in the increasing economic value of Korean fonts and the necessity for font development focused on small character design suitable for the mobile environment. The objective of this study is to analyze and propose strategies to improve readability on mobile screens. The research was conducted by applying eight attributes that could enhance readability according to Tim Ahrens to the design process of a Korean mobile font, adjusting Google's Noto Sans Korean for print/publishing and for small sizes. The results of the study indicate that 1. type width should be increased, 2. open counter (interior space) should be increased, 3. closed counter should be decreased, 4. font weight should be increased, 5. stroke contrast should be decreased, 6. spacing between characters should be increased. Therefore, distinct font families should be provided, differentiating between print/publishing and mobile use, as well as varying font weights and sizes, applying readability and legibility enhancement techniques for Korean fonts.

Spoken-to-written text conversion for enhancement of Korean-English readability and machine translation

  • HyunJung Choi;Muyeol Choi;Seonhui Kim;Yohan Lim;Minkyu Lee;Seung Yun;Donghyun Kim;Sang Hun Kim
    • ETRI Journal
    • /
    • v.46 no.1
    • /
    • pp.127-136
    • /
    • 2024
  • The Korean language has written (formal) and spoken (phonetic) forms that differ in their application, which can lead to confusion, especially when dealing with numbers and embedded Western words and phrases. This fact makes it difficult to automate Korean speech recognition models due to the need for a complete transcription training dataset. Because such datasets are frequently constructed using broadcast audio and their accompanying transcriptions, they do not follow a discrete rule-based matching pattern. Furthermore, these mismatches are exacerbated over time due to changing tacit policies. To mitigate this problem, we introduce a data-driven Korean spoken-to-written transcription conversion technique that enhances the automatic conversion of numbers and Western phrases to improve automatic translation model performance.

An Evaluative Research on the Performances of E-book Producers and Suppliers (국내 전자책 제공업체의 성능 평가에 관한 연구)

  • Lee, Myeong-Hee
    • Journal of the Korean BIBLIA Society for library and Information Science
    • /
    • v.22 no.1
    • /
    • pp.135-154
    • /
    • 2011
  • This study examined the performances of eight current e-book producers and suppliers in three areas(technology development, contents and services) using 16 evaluation criteria. Each criterion was measured using 6 scales on eight e-book producers and suppliers. The study results showed that overall, Kyobobook was the best performer, followed by Bookcube in the 2nd, Ridibooks the 3rd and Interpark the 4th. Specifically, Bookcube was the best in the field of 'technology development', Kyobobook was the best in the field of 'contents' and Kyobobook and Ridibooks worked equally best in the field of 'services'. Based on the results, some recommendations have been suggested for developing better e-book producers, effective interface design, enhancement of readability, variety of contents, development of multimedia materials and aggressive advertisement.