Telop-on-demand: video structuring and retrieval based on text recognition

Kuwano, Hidetaka; Taniguchi, Yukinobu; Arai, Hiromasa; Mori, M.; Shoji, K.; Kojima, Hironori

doi:10.1109/icme.2000.871472

Cited by 22 publications

(18 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are a number of ways to find text in video frames, including those that classify textual and nontextual regions by their textural features [12,17,20], by connected components [1,21,10,28], and by the spatial distribution of object edges [14,27,31]. Kuwano et al [14] propose a method to identify text in individual video frames that overcomes some shortcomings found in the method proposed by [27].…”

Section: Introductionmentioning

confidence: 98%

Caption analysis and recognition for building video indexing systems

et al. 2005

View full text Add to dashboard Cite

In this paper, we propose several methods for analyzing and recognizing Chinese video captions, which constitute a very useful information source for video content. Image binarization, performed by combining a global threshold method and a window-based method, is used to obtain clearer images of characters, and a caption-tracking scheme is used to locate caption regions and detect caption changes. The separation of characters from possibly complex backgrounds is achieved by using size and color constraints and by cross examination of multiframe images. To segment individual characters, we use a dynamic split-and-merge strategy. Finally, we propose a character recognition process using a prototype classification method, supplemented by a disambiguation process using support vector machines, to improve recognition outcomes. This is followed by a postprocess that integrates multiple recognition results. The overall accuracy rate for the entire process applied to test video films is 94.11%.

show abstract

Section: Introductionmentioning

confidence: 98%

Caption analysis and recognition for building video indexing systems

et al. 2005

View full text Add to dashboard Cite

show abstract

“…To construct such systems, both low-level features such as object shape, region intensity, color, texture, motion descriptors, audio measurements, and high-level techniques such as human face detection, speaker identification, and character recognition have been studied for indexing and retrieving image and video information in recent years [3], [4], [10], [11], [13], [19], [21], [24], [27]- [29], [32], [36]. Among these techniques, video caption based methods have attracted particular attention due to the rich content information contained in caption text [1], [2], [6], [9], [11]- [13], [15], [16], [19], [20], [27], [33], [36]. Caption text routinely provides such valuable indexing information as scene locations, speaker names, program introductions, sports scores, special announcements, dates and time.…”

Section: Introductionmentioning

confidence: 99%

“…Since characters are composed of line segments, text regions contain rich edge information [1], [2], [8], [16], [27], [33]. Utilizing the high-frequency information in text edges, the methods are effective in segmenting text from surrounding background after the text bounding box is already detected.…”

Section: Introductionmentioning

confidence: 99%

“…Even though some address text detection in video frames [1], [5], [11]- [13], [16], [20], [34], they usually treat each video frame as an independent image. When temporal information are utilized, they are used only for text enhancement through multiframe averaging [18] or time-based minimum pixel search [15], [20], [27], [28].…”

Section: Introductionmentioning

confidence: 99%

“…Finally, the majority of the existing researches on caption extraction have been focusing on English captions, with a few exceptions addressing captions in Korean and Japanese [12], [16]. We have found few existing researches dealing with captions in Chinese.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A spatial-temporal approach for video caption detection and recognition

Tang

Gao

Liu

et al. 2002

IEEE Trans. Neural Netw.

106

View full text Add to dashboard Cite

Abstract-We present a video caption detection and recognition system based on a fuzzy-clustering neural network (FCNN) classifier. Using a novel caption-transition detection scheme we locate both spatial and temporal positions of video captions with high precision and efficiency. Then employing several new character segmentation and binarization techniques, we improve the Chinese video-caption recognition accuracy from 13% to 86% on a set of news video captions. As the first attempt on Chinese video-caption recognition, our experiment results are very encouraging.Index Terms-Chinese caption detection, fuzzy clustering neural networks (FCNNs), video indexing, video OCR, video shot segmentation.

show abstract

Segmentation of broadcasted baseball videos into every inning and plate appearance

Abe

Misawa

Nendai

et al. 2006

IEEJ Trans Elec Electron Eng

View full text Add to dashboard Cite

Most current ideas for producing highlights of broadcasted sports videos are focused on scenes of scoring and receiving loud cheers. However, depending on recent performances of Japanese baseball players in the US, Japanese TV programs often show their performances as highlights in the broadcasts without depending on the highlight. This paper presents a method for segmenting broadcasted baseball videos into every inning and every plate appearance by analyzing the change of the sports ticker by a correlation coefficient. The proposed technique could be efficiently used as a preprocessing method in extracting highlight scenes about a batter from broadcasted sports videos and making an index of the videos. The experimental results have shown that the proposed method has exactly segmented broadcasted baseball videos into each inning and each plate appearance.

show abstract

Telop-on-demand: video structuring and retrieval based on text recognition

Cited by 22 publications

References 8 publications

Caption analysis and recognition for building video indexing systems

Caption analysis and recognition for building video indexing systems

A spatial-temporal approach for video caption detection and recognition

Segmentation of broadcasted baseball videos into every inning and plate appearance

Contact Info

Product

Resources

About