MULTIRESOLUTION TEXT DETECTION IN VIDEO FRAMES
作者： Basilios Gatos , Ioannis Pratikakis , Marios Anthimopoulos
DOI:
关键词: Computer science 、 Computer vision 、 Canny edge detector 、 Connected component 、 Artificial intelligence 、 Bounding overwatch 、 Dilation (morphology) 、 Text detection 、 Pattern recognition
摘要: This paper proposes an algorithm for detecting artificial text in video frames using edge information. First, map is created the Canny detector. Then, morphological dilation and opening are used order to connect vertical edges eliminate false alarms. Bounding boxes determined every non-zero valued connected component, consisting initial candidate areas. Finally, projection analysis applied, refining result splitting areas lines. The whole applied different resolutions ensure detection with size variability. Experimental results prove that method highly effective efficient detection.
demokritos.gr
researchgate.net 参考文章(16)
Majid Mirmehdi, Paul Clark, Finding Text Regions Using Localised Measures british machine vision conference. pp. 675- 684 ,(2000)
Tan Min, Yan Hao, Hou Zeng-guang, Zhang Yi, Automatic Text Detection In Video Frames Based on Bootstrap Artificial Neural Network And CED international conference in central europe on computer graphics and visualization. ,(2003)
Rainer W. Lienhart, Frank Stuber, Automatic text recognition in digital videos Image and Video Processing IV. ,vol. 2666, pp. 180- 188 ,(1996) , 10.1117/12.234741
David Crandall, Sameer Antani, Rangachar Kasturi, Extraction of special effects caption text events from digital video international conference on document analysis and recognition. ,vol. 5, pp. 138- 157 ,(2003) , 10.1007/S10032-002-0091-7
K. Sobottka, H. Bunke, H. Kronenberg, Identification of text on colored book and journal covers international conference on document analysis and recognition. pp. 57- 62 ,(1999) , 10.1109/ICDAR.1999.791724
Jie Xi, Xian-Sheng Hua, Xiang-Rong Chen, Liu Wenyin, Hong-Jiang Zhang, A video text detection and recognition system international conference on multimedia and expo. pp. 873- 876 ,(2001) , 10.1109/ICME.2001.1237861
Xian-Sheng Hua, Liu Wenyin, Hong-Jiang Zhang, An automatic performance evaluation protocol for video text detection algorithms international conference on document analysis and recognition. ,vol. 14, pp. 498- 507 ,(2004) , 10.1109/TCSVT.2004.825538
R. Lienhart, A. Wernicke, Localizing and segmenting text in images and videos IEEE Transactions on Circuits and Systems for Video Technology. ,vol. 12, pp. 256- 268 ,(2002) , 10.1109/76.999203
Datong Chen, H. Bourlard, J.-P. Thiran, Text identification in complex background using SVM computer vision and pattern recognition. ,vol. 2, pp. 621- 627 ,(2001) , 10.1109/CVPR.2001.991021
Yingzi Du, Chein-I Chang, Paul D Thouin, None, Automated system for text detection in individual video images Journal of Electronic Imaging. ,vol. 12, pp. 410- 422 ,(2003) , 10.1117/1.1584050