• Journal of the Korea Computer Industry Society
• /
• v.2 no.11
• /
• pp.1465-1476
• /
• 2001

For the applications like video indexing, text understanding, and automatic captions localization system, real-time localization of captions is an essential task. This paper presents a algorithm for localization of captions in MPEG compression images based on I frame. In this algorithm, caption text regions are segmented from background images using their distinguishing texture characteristics and chrominance information. Unlike previously published algorithms which fully decompress the video sequence before extracting the text regions, this algorithm locates candidate caption text region directly in the DCT compressed domain.

• The Korean Journal of Health Service Management
• /
• v.4 no.2
• /
• pp.33-46
• /
• 2010

In this study, we investigated web contents accessibility of 60 hospital web sites in Korea. The eight evaluation criteria were used for estimating the web contents accessibility of the web sites. These criteria were as follows: providing an alternative text, providing caption for moving picture, providing a skip navigation, usage of pop-up windows, usage of a summary or a caption tag for data table, providing a page title, providing a label for online form, and usage of java scripts. K-WAH 3.0 was used for estimating five evaluation criteria. According to Internet web contents accessibility guideline 1.0, we estimated the rest three evaluation criteria manually and described good or bad examples for the evaluation results technically. The results show that the web accessibility of hospital web sites is generally insufficient and the constant interests in improvement for accessibility are urgently needed.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2010.07a
• /
• pp.335-336
• /
• 2010

장애인도 비장애인과 정보접근 기회를 동일하게 가질 권리가 있다. 하지만 청각장애인은 의사소통 수단이나 정보획득의 수단으로부터 소외됨으로써 다양한 사회적 참여에서 배제되기 일쑤였다. 따라서 이 논문에서는 청각장애인을 위한 음성인식을 이용한 자동 자막 시스템을 제안한다. 이 논문에서 제안하는 시스템은 음성 특징 파라미터 추출과 DTW에 의한 음성인식을 통해 음성을 추출하여 화면에 자막으로 나타나게 하는 시스템이다.

• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1318-1330
• /
• 2018

Video captioning refers to the process of extracting features from a video and generating video captions using the extracted features. This paper introduces a deep neural network model and its learning method for effective video captioning. In this study, visual features as well as semantic features, which effectively express the video, are also used. The visual features of the video are extracted using convolutional neural networks, such as C3D and ResNet, while the semantic features are extracted using a semantic feature extraction network proposed in this paper. Further, an attention-based caption generation network is proposed for effective generation of video captions using the extracted features. The performance and effectiveness of the proposed model is verified through various experiments using two large-scale video benchmarks such as the Microsoft Video Description (MSVD) and the Microsoft Research Video-To-Text (MSR-VTT).

• Electronics and Telecommunications Trends
• /
• v.34 no.3
• /
• pp.1-12
• /
• 2019

In the digital era, broadcasting plays a very large role as a means of communication, as it no longer merely provides information or entertainment media. Particularly in the case of the visually and hearing-impaired, broadcasting is the primary means of acquiring information, so its role as a public service needs to be expanded. The development of digital technology enables the quantitative expansion of traditional methods of disability broadcasting, i.e., closed caption, sign language, and descriptive video service, with an acceptable level of quality. In this study, we review the current trends of, and concerns related to, broadcasting services for disabled people, as well as technological trends, and proposals for increasing visibility and accessibility to broadcasting for hearing-impaired people.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.461-464
• /
• 2020

지상파 방송에서는 청각장애인을 위해 폐쇄자막(closed caption) 서비스가 제공되고 있다. 현재의 폐쇄자막 방송은 속기사가 실시간으로 방송을 보면서 입력하기 때문에 지연이 있다. 또한 이렇게 입력된 폐쇄자막은 TV 프로그램 영상과 별도로 저장되기 때문에 영상과 그 시작점이 맞지 않는 경우가 대부분이다. 폐쇄자막을 온라인 서비스 등에 제공하고자 할 때 이러한 문제로 인해 영상과의 동기가 맞지 않아 사용이 어렵다. 본 논문에서는 TV 프로그램의 음성을 인식하여 동기화된 텍스트를 추출하고, 이를 기 저장된 폐쇄자막과 정렬하여 동기화하는 방법을 제안한다. 실제 TV 프로그램과 자막에 적용하였을 때 대부분의 음절과 라인에서 동기화가 정확히 이루어짐을 확인하였다.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.9
• /
• pp.2294-2301
• /
• 1998

The aim of this paper is to extract features from each news scenes for example, symbol icon which can be distinct each broadcasting corp, icon and caption which are has feature and important information for the scene in respectively, In this paper, we propose extraction methods of caption that has important prohlem of news videos and it can be classified in three steps, First of al!, we converted that input images from video frame to YIQ color vector in first stage. And then, we divide input image into regions in clear hy using equalized color histogram of input image, In last, we extracts caption using edge histogram based on vertical and horizontal line, We also propose the method which can extract news icon in selected key frames by the difference of inter-histogram and can divide each scene by the extracted icon. In this paper, we used comparison method of edge histogram instead of complex methcxls based on color histogram or wavelet or moving objects, so we shorten computation through using simpler algorithm. and we shown good result of feature's extraction.

• Journal of Digital Contents Society
• /
• v.18 no.7
• /
• pp.1323-1331
• /
• 2017

Despite the fact that the copyright has grown into a large-scale business, there are many constant problems especially in image copyright. In this study, we propose an automatic object extraction and classification system for the scanned educational book image by combining document image processing and intelligent information technology like deep learning. First, the proposed technology removes noise component and then performs a visual attention assessment-based region separation. Then we carry out grouping operation based on extracted block areas and categorize each block as a picture or a character area. Finally, the caption area is extracted by searching around the classified picture area. As a result of the performance evaluation, it can be seen an average accuracy of 83% in the extraction of the image and caption area. For only image region detection, up-to 97% of accuracy is verified.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.1
• /
• pp.10-19
• /
• 2003

Caption information in news videos can be useful for video indexing and retrieval since it usually suggests or implies the contents of the video very well. In this paper, a new algorithm for extracting and recognizing characters from news video is proposed, without a priori knowledge such as font type, color, size of character. In the process of text region extraction, in order to improve the recognition rate for videos with complex background at low resolution, continuous frames with identical text regions are automatically detected to compose an average frame. The image of the averaged frame is projected to horizontal and vertical direction, and we apply region filling to remove backgrounds to produce the character. Then, K-means color clustering is applied to remove remaining backgrounds to produce the final text image. In the process of character recognition, simple features such as white run and zero-one transition from the center, are extracted from unknown characters. These feature are compared with the pre-composed character feature set to recognize the characters. Experimental results tested on various news videos show that the proposed method is superior in terms of caption extraction ability and character recognition rate.

• Korean journal of communication and information
• /
• v.18
• /
• pp.231-268
• /
• 2002

This is a study about the audience's aspect of decoding the photography and words comprising photojournalism. For this study, the way of audience's decoding five pictures depicting a foreign worker's death and the captions for each were analyzed. Ethnographic method was used to find distinctive features of the audiences in decoding the pictures. Picture images without any title and caption shown to audiences bring quite different decodings from those of picture images titled and captioned. This led to the following three conclusions. First, picture image added by caption transforms the way the audience decode. Second, the cultural background of an audience works as a major variable, which means how the audience decode the picture image depends on what sort of cultural background the audience has. Third, it is also learned that picture image not captioned would not be able to represent the reality faithfully. The author made an experimental trial in this thesis how the communication process works successfully in a reality that photojournalists tried to represent and the way the audience decode it for the successful communication in photojournalism.