Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Filters








507 Hits in 6.6 sec

Extraction of reference lines and items from form document images with complicated background

D XI, S LEE
2005 Pattern Recognition  
The extraction of reference lines and items is a fundamental and crucial task in form document analysis. Most of the studies performed so far were done in connection with binary images.  ...  This paper proposes a method of extracting lines from gray-level images, by constructing a 2D pseudo Gaussian-Coiflet wavelet with adjustable rectangular support.  ...  Tang for helping us with various problems and for his valuable comments.  ... 
doi:10.1016/s0031-3203(04)00191-8 fatcat:qoenmxwdongjrbq7i6sixy7w4e

Extraction of reference lines and items from form document images with complicated background

Dihua Xi, Seong-Whan Lee
2005 Pattern Recognition  
The extraction of reference lines and items is a fundamental and crucial task in form document analysis. Most of the studies performed so far were done in connection with binary images.  ...  This paper proposes a method of extracting lines from gray-level images, by constructing a 2D pseudo Gaussian-Coiflet wavelet with adjustable rectangular support.  ...  Tang for helping us with various problems and for his valuable comments.  ... 
doi:10.1016/j.patcog.2004.04.013 fatcat:ft6qz5b7brandkw3y2xk3kmnjy

Background Extraction in Electron Microscope Images of Artificial Membranes [chapter]

A. Karathanou, J.-L. Buessler, H. Kihl, J.-P. Urban
2009 IFIP Advances in Information and Communication Technology  
A multiresolution segmentation technique has been proposed for the image partition. This paper presents an analysis of this partition to extract the background.  ...  On-line analysis of Transmission Electron Microscope (TEM) images is a field with great interest that opens up new prospects regarding automatic acquisitions.  ...  Acknowledgments This work was supported by the EU 6th framework (HT3DEM, LSHG-CT-2005-018811, in collaboration with the Biozentrum of Basel and FEI company who provided the TEM images.  ... 
doi:10.1007/978-1-4419-0221-4_21 fatcat:kfx32ojdofhkloz6cr3yvfjrxy

Binarization of document images using Hadamard multiresolution analysis

Fu Chang, Kung-Hao Liang, Tzu-Ming Tan, Wen-Liang Hwan
1999 Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318)  
The latter scheme compares the contrast of gray values within a neighborhood whose size varies with the scale of the objects being examined.  ...  To compute the scale quantity, a new wavelet model entitled Hadamard multiresolution analysis is also proposed.  ...  For those documents containing small colored patches, our method can still yield acceptable results, although some drawbacks may be seen in those areas whose gray values are deviated from the average background  ... 
doi:10.1109/icdar.1999.791748 dblp:conf/icdar/ChangLTH99 fatcat:w3fdq3x2zfc4jirpqt4u6vwsoa

Text Localization in Historical Document Images with Local Binary Patterns and Variance Models [chapter]

Tapan Kumar Bhowmik, Manika Kar
2013 Lecture Notes in Computer Science  
In our experiments, three basic reference models namely background, text and image models are used to segment various non-text information together with the text.  ...  The result of segmentation will help us to organize the document pages in a structural format, which is useful in many applications like historical document access.  ...  In this paper, we describe such a text localization scheme based on multiresolution analysis that we build as the first step of page layout system for historical documents.  ... 
doi:10.1007/978-3-642-45062-4_69 fatcat:tydqiznbpvdptjm3unpctj2e6m

Document image characterization using a multiresolution analysis of the texture: application to old documents

Nicholas Journet, Jean-Yves Ramel, Rémy Mullot, Véronique Eglin
2008 International Journal on Document Analysis and Recognition  
This characterization is carried out with the help of a multi-resolution study of the textures contained in the images of the document.  ...  Thus, by extracting five features linked to the frequencies and to the orientations in the different areas of a page, it is possible to extract and compare elements of high semantic level without expressing  ...  The only variations of gray levels are due to the digitization or to the deterioration of paper or ink. One is then very far from the grayscale variations that are to be found in natural images.  ... 
doi:10.1007/s10032-008-0064-6 fatcat:a6gckuodvnfktdokryxfmip5hy

Multiresolution local binary pattern texture analysis combined with variable selection for application to false-positive reduction in computer-aided detection of breast masses on mammograms

Jae Young Choi, Yong Man Ro
2012 Physics in Medicine and Biology  
In addition, to maximize a complementary effect on improving classification accuracy, multiresolution texture analysis has been incorporated into the extraction of LBP features.  ...  Our results also indicate that combining our multiresolution LBP features with variable selection strategy is an effective solution for reducing FP signals in computeraided detection (CAD) of mammographic  ...  Acknowledgments This paper is partially supported by the development of MEXA image enhancement and processing (A080782) of the Ministry for Health, Welfare and Family Affairs in the Republic of Korea.  ... 
doi:10.1088/0031-9155/57/21/7029 pmid:23053352 fatcat:oo77b7semjeyjjqs2k5jv27oce

Automatic Detection and Recognition of Signs From Natural Scenes

X. Chen, J. Yang, J. Zhang, A. Waibel
2004 IEEE Transactions on Image Processing  
Instead of using binary information for OCR, we extract features from an intensity image directly.  ...  The proposed approach embeds multiresolution and multiscale edge detection, adaptive searching, color analysis, and affine rectification in a hierarchical framework for sign detection, with different emphases  ...  Wang and Pavlidis showed the advantages of direct feature extraction from gray scale image for OCR [24] .  ... 
doi:10.1109/tip.2003.819223 pmid:15376960 fatcat:lufark62cfbjlfaye6zs22c5ne

Recognition of Tamil Handwritten Characters using Daubechies Wavelet Transforms and Feed-Forward Backpropagation Network

Tiji MJose, Amitabh Wahi
2013 International Journal of Computer Applications  
The proposed system concentrates on two dimensional discrete wavelet transformations for extraction of features. For multiresolution analysis of images, Wavelet Transform is used.  ...  This article suggests wavelet transform based feature extraction technique for extracting robust features from Tamil handwritten characters.  ...  These characters are compared with image patterns to predict the probable characters. Recognition of characters can be done either from printed documents or from handwritten documents.  ... 
doi:10.5120/10656-5422 fatcat:5btxerimoje6vlclb3lv76whb4

A two-stage scheme for text detection in video images

Marios Anthimopoulos, Basilis Gatos, Ioannis Pratikakis
2010 Image and Vision Computing  
In the first stage, text lines are detected based on the edge map of the image leading in a high recall rate with low computational time expenses.  ...  The whole algorithm is used in a multiresolution fashion enabling detection of characters for a broad size range.  ...  Acknowledgement Part of this research was carried out within the framework of the co-funded by the EU project CASAM (FP7-ICT-217061).  ... 
doi:10.1016/j.imavis.2010.03.004 fatcat:t5vayfq3wrcfhpsghdsggk4rki

A Comparative Analysis of Different Edge Based Algorithms for Mobile/Camera Captured Images

H.K. Chethan, G.Hemantha Kumar
2010 International Journal of Computer Applications  
The goal of the work is to extract and recognize text from camera captured images based on edge based algorithms and compare the result with the existing system under different conditions.  ...  Availability of High Resolution Camera has lead to new dimension in digital image processing. Mobile phones are ubiquitous and very powerful in nature due to their capability of multifunction.  ...  The variations in the gray level image commonly include discontinuities (step edges), local extreme (line edges) and junctions.  ... 
doi:10.5120/1143-1496 fatcat:kxmpqysdmzge5m5a5ys5afz654

Handwriting Identification using Connected Component Analysis and 2D- Discrete Wavelet Transform

S. Arunkumar, Pallab Kumar Sahu, Sudeep Gorai
2012 International Journal of Computer Applications  
It refers to the ability of the computer to receive the image of the handwritten character from sources such as paper documents, touch screens, etc and compare it with an existing database.  ...  It is also implemented in many subjective handwritten exams in cases of discrepancies.  ...  The above database constitutes documents from 30 individuals. Yes Preprocessing: Each document scanned (Fig (2) ) is first converted into gray scale image.  ... 
doi:10.5120/5762-7950 fatcat:4j4wuh6d25dctf6st7lvywgdsy

Parameter-free geometric document layout analysis

Seong-Whan Lee, Dae-Seok Ryu
2001 IEEE Transactions on Pattern Analysis and Machine Intelligence  
BACKGROUND Previous Works A number of approaches have been proposed in various ways for page segmentation and geometric document layout analysis.  ...  For the remaining regions, we extract any existing horizontal lines. The top and bottom ruling lines, which should be similar in length with the width of the region, are detected.  ... 
doi:10.1109/34.969115 fatcat:ep4ggbmeu5gehm5vumeenls6zi

Image Segmentation Using Discrete Wavelets Transform

Zobeda H. Naji
2020 Diyala Journal of Engineering Sciences  
In this paper, discrete wavelets are used with another type of technique like canny, R.G and thresholding to reduce the number of the segment and maintain the edge of an image, also in this paper presented  ...  This paper proposed the segmentation of image based on discrete wavelet transform (DWT were used "Daubechies") which its concerns with the exploitation of pixels in an image.  ...  The paper focuses on the study of extraction from color images and texture analysis after image segmentation.  ... 
doi:10.24237/djes.2020.13301 fatcat:4k7wxspbazgzlknd7smfgnjn5m

A multiresolution approach to iris synthesis

L. Wecker, F. Samavati, M. Gavrilova
2010 Computers & graphics  
In this work we develop a novel multiresolution approach to augment iris image databases.  ...  First, using a multiresolution obtained from reverse subdivision we decompose the example iris images into a set of lower resolution components.  ...  Authors would also like to acknowledge support of CFI and NSERC Granting Agencies for their partial support of this project.  ... 
doi:10.1016/j.cag.2010.05.012 fatcat:etgecncywbehdgadwcbexlnsay
« Previous Showing results 1 — 15 out of 507 results