2,407 Hits in 6.9 sec

Normalized SAD Method for Chinese Document Image Registration

Lijing Tong, Jing Chen, Quanyao Peng, Yifan Li
2013 Journal of Multimedia  
Then gray histogram of the matched image is normalized firstly so that the different laminations of the two document image can be eliminated.  ...  The Sum of Absolute Difference, SAD, is a similarity criterion for image registration.  ...  But because the current text row is short sometimes, we may extract some text line segments of other rows during the procedure of the extracting a text line from the text line image.  ... 
doi:10.4304/jmm.8.2.121-128 fatcat:ll6juy763nbm3mr3stnp6kfddq

Image-to-Structure Task by ChemReader

Jungkap Park, Ye Li, Gus R. Rosania, Kazuhiro Saitou
2011 Text Retrieval Conference  
Since traditional text based mining methods haven't attempt to utilize image data in documents yet, chemical OCR software will pave a new way for the development of chemical literature mining [1, 2] .  ...  Parameter values used in Test I was applied. For fair comparison, instead of our evaluation tool used in the training, we employed the evaluation tool used in the actual test.  ... 
dblp:conf/trec/ParkLRS11 fatcat:zfc7k6m6dzgjzl5ffppacjz7x4

Distance Transform Based Active Contour Approach for Document Image Rectification

Dhaval Salvi, Kang Zheng, Youjie Zhou, Song Wang
2015 2015 IEEE Winter Conference on Applications of Computer Vision  
In the domain of printed document images, the white space between the text lines carries as much information about the 2D distortion as the text lines themselves.  ...  These white space lines are extracted using a propagation technique on the distance transform of the binarized document image, guided by an open active contour algorithm.  ...  Bank of Gaussian line filters parameters: For the bank of Gaussian line filters described in 2.3, we empirically selected range of values for θ = ±10 • and l in range of 5 to 200.  ... 
doi:10.1109/wacv.2015.106 dblp:conf/wacv/SalviZZW15 fatcat:v5y6m7gl4zbajjukyl4at366qm

Quality Assurance for Document Image Collections in Digital Preservation [chapter]

Reinhold Huber-Mörk, Alexander Schindler
2012 Lecture Notes in Computer Science  
We use spatially distinctive local keypoints of contrast enhanced images and robust symmetric descriptor matching to calculate affine transformations for image registration.  ...  Structural similarity of aligned images is used for quality assessment.  ...  Acknowledgment The image data was kindly provided by the British Library. Details of the International Dunhang Project can be found at  ... 
doi:10.1007/978-3-642-33140-4_10 fatcat:o67wr47fdrhannpxagdsuqwthq

Recognition of Degraded Handwritten Characters Using Local Features

Markus Diem, Robert Sablatnig
2009 2009 10th International Conference on Document Analysis and Recognition  
Since OCR systems are based upon binary images, their results are poor if the text is degraded. In this paper a codex consisting of ancient manuscripts is investigated.  ...  The main problems of Optical Character Recognition (OCR) systems are solved if printed latin text is considered.  ...  Local Descriptors: While image matching with local features was at the beginning solely used in stereo vision tasks, Schmid and Mohr [15] proposed to use feature matching for image retrieval tasks.  ... 
doi:10.1109/icdar.2009.158 dblp:conf/icdar/DiemS09 fatcat:2wzx3c5v2za6tddtjwdsedijky

Egomotion Estimation Using Binocular Spatiotemporal Oriented Energy

Hao Zhong, Richard Wildes
2013 Procedings of the British Machine Vision Conference 2013  
This paper documents a novel algorithm for egomotion estimation based on binocularly matched spatiotemporal oriented energy distributions.  ...  It has been demonstrated to be of both theoretical and practical interest.  ...  This algorithm makes uses its own techniques for matching between images.  ... 
doi:10.5244/c.27.62 dblp:conf/bmvc/ZhongW13 fatcat:wcnm5blxqbewpiaoi6vbkfddqa

Text Region Extraction and OCR on Camera Based Images
카메라 영상 위에서의 문자 영역 추출 및 OCR

Hyun-Kyung Shin
2010 The KIPS Transactions PartD  
method of text region extraction, scale invariant method of text line segmentation, and three dimensional perspective mapping.  ...  With the integration of the methods, we developed an OCR for camera-captured images.  ...  In this section we select two sample images corresponding to the group, which described as below. We performed OCR with many of the images matched with the categories.  ... 
doi:10.3745/kipstd.2010.17d.1.059 fatcat:xprnuaextveezoreqyqyacw2yy

Intelligent Indoor Mobile Robot Navigation Using Stereo Vision

Arjun B Krishnan, Jayaram Kollipara
2014 Signal & Image Processing An International Journal  
This paper aims at describing an experimental approach for the building of a stereo vision system that helps the robots to avoid obstacles and navigate through indoor environments and at the same time  ...  Majority of the existing robot navigation systems, which facilitate the use of laser range finders, sonar sensors or artificial landmarks, has the ability to locate itself in an unknown environment and  ...  Calibration algorithm is used to extract the parameters of the image sensors and stereo rig, hence has to be executed at least once before using the system for depth calculation.  ... 
doi:10.5121/sipij.2014.5405 fatcat:3ajj7mqrhfg7fn7lr4mibiimia

Extraction of Scene Text Information from Video

Too Kipyego Boaz, Prabhakar C. J.
2016 International Journal of Image Graphics and Signal Processing  
In this paper, we present an approach for scene text extraction from natural scene video frames.  ...  The text information is extracted from reduced reference i.e. extracted planar surface through filtering using Fourier-Laplacian algorithm.  ...  RELATED WORK Text information extraction from scene images have received a great attention from researchers all over the the world when compared with video and images of document.  ... 
doi:10.5815/ijigsp.2016.01.02 fatcat:h4dj6zyvmrenhieao5ojexq7ua

Intelligent Indoor Mobile Robot Navigation Using Stereo Vision [article]

Arjun B. Krishnan, Jayaram Kollipara
2014 arXiv   pre-print
This paper aims at describing an experimental approach for the building of a stereo vision system that helps the robots to avoid obstacles and navigate through indoor environments and at the same time  ...  Majority of the existing robot navigation systems, which facilitate the use of laser range finders, sonar sensors or artificial landmarks, has the ability to locate itself in an unknown environment and  ...  and further development of the robot for outdoor navigation with the aid of Global Positioning System.  ... 
arXiv:1412.6153v1 fatcat:lkw6qg34pnfzpfqfscaia534la

Analysis of Cluttered Scenes Using an Elastic Matching Approach for Stereo Images

Christian Eckes, Jochen Triesch, Christoph von der Malsburg
2006 Neural Computation  
First, we use elastic graph matching in stereo image pairs to increase matching robustness and disambiguate occlusion relations.  ...  We present a system for the automatic interpretation of cluttered scenes containing multiple partly occluded objects in front of unknown, complex backgrounds.  ...  We thank the developers of the FLAVOR software environment, which served as the platform for this research.  ... 
doi:10.1162/neco.2006.18.6.1441 pmid:16764510 fatcat:frid5t7aajbevgno5girvzicdu

Passive 3D Imaging [chapter]

Stephen Se, Nick Pears
2012 3D Imaging, Analysis and Applications  
Much of the material is concerned with using the geometry of stereo 3D imaging to formulate estimation problems.  ...  Secondly, we discuss camera modeling and camera calibration as an essential introduction to the geometry of the imaging process and the estimation of geometric parameters.  ...  SIFT features are extracted and matched between the stereo images to obtain 3D SIFT landmarks which are used for indoor SLAM [49] and for outdoor SLAM [1].  ... 
doi:10.1007/978-1-4471-4063-4_2 fatcat:5qapfkm4lzdg5hdqwgkvw7eube

Incorporating On-demand Stereo for Real Time Recognition

T. Deselaers, A. Criminisi, J. Winn, A. Agarwal
2007 2007 IEEE Conference on Computer Vision and Pattern Recognition  
A random forest algorithm is employed which adaptively selects and combines a minimal set of appearance, shape and stereo features to achieve maximum class discrimination for a given image.  ...  Unlike previous stereo works which explicitly construct disparity maps, here the stereo matching costs are used directly as visual cue and only computed on-demand, i.e. only for pixels where they are necessary  ...  appearance 55 47 26.8 stereo 32 78 13.7 shape 13 46 37.8 For stereo features approximately 80% of the selected tests are of type 2 (absolute SSD matching cost); for appearance and shape  ... 
doi:10.1109/cvpr.2007.383136 dblp:conf/cvpr/DeselaersCWA07 fatcat:piiv53cl6ra4dm7fhop4m4f5u4

Sharing and fusing landmark information in a team of autonomous robots

Damian M. Lyons, Belur V. Dasarathy
2009 Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications 2009  
Each robot can use sonar, stereo, laser and image information to identify potential landmarks.  ...  The sonar, laser and stereo information provide the spatial dimension of the spatiogram in a landmark-centered coordinate frame while video provides the image information.  ...  Stereo camera image (a), pseudocolor disparity image (b), depth image (c) shown on this review document.  ... 
doi:10.1117/12.818363 fatcat:s4esyq55h5gllogvtuas7wv6ya

DocScanner: Robust Document Image Rectification with Progressive Learning [article]

Hao Feng, Wengang Zhou, Jiajun Deng, Qi Tian, Houqiang Li
2022 arXiv   pre-print
To this end, we present DocScanner, a novel framework for document image rectification.  ...  Compared with flatbed scanners, portable smartphones are much more convenient for physical documents digitizing.  ...  of text lines.  ... 
arXiv:2110.14968v2 fatcat:rtcobb2aabh4ba3djq4u3ep4xi
« Previous Showing results 1 — 15 out of 2,407 results