Using Multiple Frame Integration for the Text Recognition of Video

Yi, Jian; Peng, Yuxin; Xiao, Jianguo

doi:10.1109/icdar.2009.58

Cited by 15 publications

(12 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Commercial OCRs are indeed usually developed for printed text, much less variable in style, color and size than texts in videos. Hua et al [11] and Yi et al [23] were interested in solving problems related to complex backgrounds by using multiple frame integration. The main idea consists in taking advantage of the temporal redundancy of a text in numerous frames.…”

Section: Related Workmentioning

confidence: 99%

A comprehensive neural-based approach for text recognition in videos using natural language processing

Elagouni

García

Sébillot

2011

Proceedings of the 1st ACM International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

This work aims at helping multimedia content understanding by deriving benefit from textual clues embedded in digital videos. For this, we developed a complete video Optical Character Recognition system (OCR), specifically adapted to detect and recognize embedded texts in videos. Based on a neural approach, this new method outperforms related work, especially in terms of robustness to style and size variabilities, to background complexity and to low resolution of the image. A language model that drives several steps of the video OCR is also introduced in order to remove ambiguities due to a local letter by letter recognition and to reduce segmentation errors. This approach has been evaluated on a database of French TV news videos and achieves an outstanding character recognition rate of 95%, corresponding to 78% of words correctly recognized, which enables its incorporation into an automatic video indexing and retrieval system.

show abstract

Section: Related Workmentioning

confidence: 99%

A comprehensive neural-based approach for text recognition in videos using natural language processing

Elagouni

García

Sébillot

2011

Proceedings of the 1st ACM International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

show abstract

“…The disadvantage of min/max is that it can be affected by an "outlier", i.e., a text instance that is much brighter/darker than the rest. Yi et al [3] used a combination of both. Otsu's binarization was employed to identify text and background pixels.…”

Section: Introductionmentioning

confidence: 98%

“…Thus, the focus is on identifying the first frame and the last frame of occurrence of text. A wide range of measures have been studied: intersection and difference of edge maps [3], and intersection of histograms of numbers of pixels contributing to high-frequency wavelet subbands [4]. The common drawback of these measures is that they do not distinguish between text pixels/edges and background pixels/edges.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recognition of Video Text through Temporal Integration

Phan

Shivakumara

Lü

et al. 2013

2013 12th International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

This paper presents a method for temporal integration, which can be used to improve the recognition accuracy of video texts. Given a word detected in a video frame, we use a combination of Stroke Width Transform and SIFT (Scale Invariant Feature Transform) to track it both backward and forward in time. The text instances within the word's framespan are then extracted and aligned at pixel level. In the second step, we integrate these instances into a text probability map. By thresholding this map, we obtain an initial binarization of the word. In the final step, the shapes of the characters are refined using the intensity values. This helps to preserve the distinctive character features (e.g., sharp edges and holes), which are useful for OCR engines to distinguish between the different character classes. Experiments on English and German videos show that the proposed method outperforms existing ones in terms of recognition accuracy.

show abstract

“…Recently, systems dedicated to embedded texts in video have generated a significant interest in the OCR community [10,2,12]. Most of the proposed approaches rely on an initial segmentation step that splits texts into individual characters (a complete survey of character segmentation methods is presented in [1]) and a second one that recognizes each segmented character.…”

Section: Introductionmentioning

confidence: 99%

Text Recognition in Videos Using a Recurrent Connectionist Approach

Elagouni

García

Mamalet

et al. 2012

Artificial Neural Networks and Machine Learning – ICANN 2012

View full text Add to dashboard Cite

Abstract. Most OCR (Optical Character Recognition) systems developed to recognize texts embedded in multimedia documents segment the text into characters before recognizing them. In this paper, we propose a novel approach able to avoid any explicit character segmentation. Using a multi-scale scanning scheme, texts extracted from videos are first represented by sequences of learnt features. Obtained representations are then used to feed a connectionist recurrent model specifically designed to take into account dependencies between successive learnt features and to recognize texts. The proposed video OCR evaluated on a database of TV news videos achieves very high recognition rates. Experiments also demonstrate that, for our recognition task, learnt feature representations perform better than hand-crafted features.

show abstract

Using Multiple Frame Integration for the Text Recognition of Video

Cited by 15 publications

References 7 publications

A comprehensive neural-based approach for text recognition in videos using natural language processing

A comprehensive neural-based approach for text recognition in videos using natural language processing

Recognition of Video Text through Temporal Integration

Text Recognition in Videos Using a Recurrent Connectionist Approach

Contact Info

Product

Resources

About