57 Hits in 6.5 sec

Correction of Signboard Distortion by Vertical Stroke Estimation

2013 KSII Transactions on Internet and Information Systems  
Finally, distortion of the text image is corrected by bilinear transformation based on the estimated outline.  ...  The recognition rate of the distortion corrected signboard images is 29.63% and 21.9% higher at the character and the text unit than those of the original images.  ...  Fig. 12 shows examples of four signboard images with the estimated outline and distortion-corrected images obtained by the proposed method.  ... 
doi:10.3837/tiis.2013.09.0014 fatcat:zaoqh3nigrampm7ufm6aoexmjy

An Interactive Image Rectification Method Using Quadrangle Hypothesis [chapter]

Satoshi Yonemoto
2013 Lecture Notes in Computer Science  
Our method has two interactive techniques that allow a user to choose the target region of interest. First, with a user-stroke based cropping. Second, with a box based cropping.  ...  The idea is based on use of horizontal and vertical lines with the target object. We assume that such lines can be richly detected.  ...  This estimation problem is solved as a search problem with the best 4-tuple combination of line segments, evaluating whether re-projected line segments will be horizontal (vertical) or not.  ... 
doi:10.1007/978-3-642-41184-7_6 fatcat:kuoof6g2azebdijaxxgt7yahna

Text Detection and Recognition: A Review

Prakhar Pathak, Pulkit Gupta, Nishant Kishore, Nikhil Kumar Yadav, Dr. Himanshu Chaudhary
2022 International Journal for Research in Applied Science and Engineering Technology  
Abstract: In this review paper we have done extensive reading of various research paper on Text Detection and Recognition from images by different authors of around the world.  ...  Each research paper deploys different algorithms and strategies for text detection and text recognition of image.  ...  number of properly estimated targets by recall correctly estimates IEI.  ... 
doi:10.22214/ijraset.2022.42932 fatcat:g5vgk5s3evhcthscw6vkyayqk4

Automated Recognition of Text in Images: A Survey

Kanika Wadhawan, E. Gajendran
2015 International Journal of Computer Applications  
Text is one of the most influential inventions of Humanity.  ...  This survey paper presents a review of various state-of-the-art techniques proposed for different processes (i.e. detection, localization, extraction, etc.) of text information processing in Images.  ...  [21] used vertical and horizontal projection visibility to detect Korean text in out-of-door signboards. Shiva kumara et al.  ... 
doi:10.5120/ijca2015906661 fatcat:kokcce4wvzg3tlerjvpqjn6mvy

Robust Vanishing Point Detection for MobileCam-Based Documents

Xu-Cheng Yin, Hong-Wei Hao, Jun Sun, Satoshi Naoi
2011 2011 International Conference on Document Analysis and Recognition  
Document images captured by a mobile phone camera often have perspective distortions. In this paper, fast and robust vanishing point detection methods for such perspective documents are presented.  ...  The rectified image acceptance rate for MobileCam-based documents, signboards and posters is more than 98% with an average speed of about 100ms.  ...  ACKNOWLEDGMENTS The work of the authors Xu-Cheng Yin and Hong-Wei  ... 
doi:10.1109/icdar.2011.36 dblp:conf/icdar/YinHSN11 fatcat:c65ajcmgafhyljlywkdcbkehxi

Joint Energy-based Detection and Classificationon of Multilingual Text Lines [article]

Igor Milevskiy, Yuri Boykov
2014 arXiv   pre-print
This paper proposes a new hierarchical MDL-based model for a joint detection and classification of multilingual text lines in im- ages taken by hand-held cameras.  ...  This energy model can be efficiently minimized by fusion moves.  ...  Moreover, Stroke width transform (SWT) [1, 4] also aims to find blobs that have consistent width of stroke.  ... 
arXiv:1407.6082v1 fatcat:h6xjnouorjdezj7mul6tadabii

Recognizing Planar Symbols with Severe Perspective Deformation

Linlin Li, Chew Lim Tan
2010 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Particularly, a symbol is represented by a sequence of cross ratio spectra, in which perspective deformation is modeled as an uneven stretching deformation.  ...  Dynamic Time Warping algorithm is employed to compare the similarity of spectra and to find the pixel level correspondence between two symbols.  ...  Pixel level correspondence of two similar, but not identical, symbols.  ... 
doi:10.1109/tpami.2009.196 pmid:20224129 fatcat:gfqtbhbu5zd4znrqrlqf4exg5m

Data Embedding into Characters

Koichi KISE, Shinichiro OMACHI, Seiichi UCHIDA, Masakazu IWAMURA, Marcus LIWICKI
2015 IEICE transactions on information and systems  
For example, characters are redesigned to have better machine-readability even under various geometric distortions by embedding a geometric invariant into each character image to represent class label  ...  An experimental result showed that we can embed 32-bit information into a handwritten line of 5 cm length by using the pen device.  ...  If this estimation is correct, it is possible to remove the distortion. However, existence of the many methods ironically suggests that this estimation problem is still not solved completely.  ... 
doi:10.1587/transinf.2014mui0002 fatcat:5otu5dji3zf5xpxzpjzelgsx5i

A Chinese Character Teaching System Using Structure Theory and Morphing Technology

Linjia Sun, Min Liu, Jiajia Hu, Xiaohui Liang, Rongrong Ji
2014 PLoS ONE  
generates the evolution animation by using the process of Chinese character morphing.  ...  Given two or several different scripts of the same Chinese character, the online phase firstly divides the Chinese characters into components by using the process of Chinese character parsing, and then  ...  The position and the shape of strokes are statistically modeled and their distributions are estimated from training samples.  ... 
doi:10.1371/journal.pone.0100987 pmid:24978171 pmcid:PMC4076269 fatcat:aq42btjftnc7xnm5ea4l3s2y7u

SUNet: Symmetric Undistortion Network for Rolling Shutter Correction [article]

Bin Fan and Yuchao Dai and Mingyi He
2021 arXiv   pre-print
First, two time-symmetric dense undistortion flows are estimated by using well-established principles: pyramidal construction, warping, and cost volume processing.  ...  The vast majority of modern consumer-grade cameras employ a rolling shutter mechanism, leading to image distortions if the camera moves during image acquisition.  ...  can compensate for RS distortions and put the corrected GS image patches at the right scale.  ... 
arXiv:2108.04775v1 fatcat:ltmgkgxmbvfkvljcmc4mjy5hjm

Scene-Text-Detection Method Robust Against Orientation and Discontiguous Components of Characters

Rei Endo, Yoshihiko Kawai, Hideki Sumiyoshi, Masanori Sano
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
We also evaluated our proposed scene-text-detection method by using the wellknown MSRA-TD500 dataset that includes rotated characters with discontiguous components.  ...  In this paper, we tackle two problems of scene-text detection. The first is the discontiguous component problem in specific languages that contain characters consisting of discontiguous components.  ...  • Stroke Width Difference of Pair d swd θm (r i , r j ) = |swdm(r i ) − swdm(r j )| max(w θm (r i ), h θm (r i )) , (16) where swdm(r) = s swd (r)/n ssp (r). • Vertical Overlap of Pair d ovl θm (r i  ... 
doi:10.1109/cvprw.2017.130 dblp:conf/cvpr/EndoKSS17 fatcat:w4mkvaor5jghdgx6lq6gp63q44

MyOcrTool: Visualization System for Generating Associative Images of Chinese Characters in Smart Devices

Laxmisha Rai, Hong Li, Abd E.I.-Baset Hassanien
2021 Complexity  
overview of a Chinese text.  ...  Considering the extensive use and application of mobile devices, automatic identification of Chinese characters and display of associative images are made possible in smart devices to facilitate quick  ...  Acknowledgments is work is supported by the College of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao 266590, China.  ... 
doi:10.1155/2021/5583287 fatcat:adgxot2isrdy3ojkokiexwl2bu

Quadbox: Quadrilateral Bounding Box Based Scene Text Detection Using Vector Regression

Prateek Keserwani, Ankit Dhankhar, Rajkumar Saini, Partha Pratim Roy
2021 IEEE Access  
To overcome this, we have proposed a centroid-centric vector regression by utilizing the geometry of quadrilateral.  ...  In this work, we have added the philosophy of indirect regression to direct regression by shifting all points within the quadrilateral to the centroid and afterward performed vector regression from shifted  ...  Marcus Liwicki, Chaired Professor, EISLAB ML, Luleå University of Technology, Sweden, for providing the computing resources to conduct extensive experiments.  ... 
doi:10.1109/access.2021.3063030 fatcat:2c2hezixrrejhhxt6p2uapqona


1915 Minutes of the Proceedings of the Institution of Civil Engineers  
xpeedri may be obtained by means independent of train orders or signboards. 12.  ...  of the stroke with a high degree of accuracy ; it was also easy to plot, on the opposite side of the datum .of this, a diagram of the vertical parts for the corresponding points of the stroke, and the  ... 
doi:10.1680/imotp.1915.16263 fatcat:eujgyslczbc7bo4xowtkhxboae

Reading Text in the Wild with Convolutional Neural Networks [article]

Max Jaderberg, Karen Simonyan, Andrea Vedaldi, Andrew Zisserman
2014 arXiv   pre-print
These networks are trained solely on data produced by a synthetic text generation engine, requiring no human labelled data.  ...  based systems of the past.  ...  Acknowledgements This work was supported by the EPSRC and ERC grant VisRec no. 228180.  ... 
arXiv:1412.1842v1 fatcat:konqljba35hudaoh4zz7tdweki
« Previous Showing results 1 — 15 out of 57 results