3,068 Hits in 5.7 sec

Line Based Robust Script Identification for IndianLanguages

Bhupendra Kumar
2012 International Journal of Information and Electronics Engineering  
The feature extraction is done on the subsets of image which in turn increases the performance of algorithm.  ...  Our basic algorithm uses different feature set at different level of classifier to optimize the tradeoff between accuracy and speed.  ...  Global approaches uses texture based features comprising sub-patterns and textons.  ... 
doi:10.7763/ijiee.2012.v2.79 fatcat:iov23kqxobap5bq7slodkxqoi4

Learning-Free Text Line Segmentation for Historical Handwritten Documents

Berat Kurar Barakat, Rafi Cohen, Ahmad Droby, Irina Rabaev, Jihad El-Sana
2020 Applied Sciences  
We present a learning-free method for text line segmentation of historical handwritten document images.  ...  Historical handwritten documents contain noise, heterogeneous text line heights, skews and touching characters among text lines.  ...  Acknowledgments: This research was supported by the Frankel Center for Computer Science in Ben-Gurion University of the Negev. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app10228276 fatcat:mp277cng65e2xlyg7ui4an5k5u

TestGraphia, a software system for the early diagnosis of dysgraphia

Giovanni Dimauro, Vitoantonio Bevilacqua, Lucio Colizzi, Davide Di Pierro
2020 IEEE Access  
The system is based on known document analysis algorithms and modified or specially designed algorithms.  ...  A writing analysis is based on rules for scoring the writing quality.  ...  (Trento, Italy) for granting permission to partially reproduce in this article, the material included in [27] .  ... 
doi:10.1109/access.2020.2968367 fatcat:rcuarei625b3dduy3pdypz2cdi

Document analysis applied to fragments

Markus Diem, Florian Kleber, Robert Sablatnig
2010 Proceedings of the 8th IAPR International Workshop on Document Analysis Systems - DAS '10  
. no constraint on the detectable angle range for the skew estimation).  ...  Methods proposing algorithm for skew estimation include techniques based on projection profiles [2, 40] , the Hough transformation [1] and methods based on properties of the Fourier transform [32]  ... 
doi:10.1145/1815330.1815381 dblp:conf/das/DiemKS10 fatcat:2ytq5siu4fhthjaktlks2mwjxy

Approach for Arabic Handwritten Image Processing: Case of Text Detection in Degraded Documents

Youssef Boulid, Mohamed Youssfi Elkettani
2014 International Journal of Computer Applications  
This study presents a new approach for processing of Arabic handwritten documents based on the extraction of characteristics and mechanisms involved in the process of human visual perception.  ...  The architecture which has been developed is based on the concept of multi-agent systems, allowing the integration of different stages of character recognition process in a cooperative way.  ...  An algorithm was introduced in [4] for detection and suppression of the clutter noise attached to text from binary document images.  ... 
doi:10.5120/17758-8891 fatcat:rfi2tq5yxreq5mnsks5fcvt33m

Segmentation of historical machine-printed documents using Adaptive Run Length Smoothing and skeleton segmentation paths

Nikos Nikolaou, Michael Makridis, Basilis Gatos, Nikolaos Stamatopoulos, Nikos Papamarkos
2010 Image and Vision Computing  
, (ii) detection of noisy areas and punctuation marks that are usual in historical machine-printed documents, (iii) detection of possible obstacles formed from background areas in order to separate neighboring  ...  This kind of documents often suffer from low quality and local skew, several degradations due to the old printing matrix quality or ink diffusion, and exhibit complex and dense layout.  ...  Our algorithm is based on the segmentation algorithm described for touching numerals in [35] .  ... 
doi:10.1016/j.imavis.2009.09.013 fatcat:iqdu2sjlgngwfe4pv7ki76vok4

Text Extraction Using Component Analysis and Neuro-fuzzy Classification on Complex Backgrounds [chapter]

Michael Makridis, Nikolaos E. Mitrakis, Nikolaos Nikolaou, Nikolaos Papamarkos
2011 Lecture Notes in Computer Science  
This paper proposes a new technique for text extraction on complex color documents and cover books.  ...  Then, a set of nine local and global features is extracted for each group and finally a classification procedure detects document's text regions.  ...  For each group, a set of features is extracted and finally the classification process, based on a neuro-fuzzy system, detects those groups that correspond to text regions.  ... 
doi:10.1007/978-3-642-21227-7_69 fatcat:2nxc775jb5hrjgr2bzvc2x2ph4

Normalization of unconstrained handwritten words in terms of Slope and Slant Correction

Suman Kumar Bera, Akash Chakrabarti, Sagnik Lahiri, Elisa H. Barney Smith, Ram Sarkar
2019 Pattern Recognition Letters  
Therefore slope and slant detection in offline handwritten text and their subsequent correction have become the critical preprocessing steps for document analysis and retrieval systems to neutralize the  ...  In offline handwritten text slope (or skew) and slant are inevitably introduced, but to varying degrees depending on several factors, such as the writing style, speed and mood of the writers.  ...  To do that, we propose another simple and effective algorithm based on the skeletonized features of word images.  ... 
doi:10.1016/j.patrec.2019.10.025 fatcat:yce2qllwfbhbpktw4ettms6doi

Voronoi++: A Dynamic Page Segmentation Approach Based on Voronoi and Docstrum Features

Mudit Agrawal, David Doermann
2009 2009 10th International Conference on Document Analysis and Recognition  
Our approach builds upon one of the best algorithms, Kise et. al. work based on Area Voronoi Diagrams [10], which adapts globally to page content to determine algorithm parameters.  ...  In our approach, local thresholds are determined dynamically based on parabolic relations between components, and Docstrum based angular and neighborhood features are integrated to improve accuracy.  ...  Each edge bisects two points on contours of different components. A physical zone is a fusion of these Voronoi cells, formed by the elimination of Voronoi edges based on two features: 1.  ... 
doi:10.1109/icdar.2009.270 dblp:conf/icdar/AgrawalD09a fatcat:va34tdveejekrjpnxamzskdvfu

Textline detection in degraded historical document images

Byeongyong Ahn, Jewoong Ryu, Hyung Il Koo, Nam Ik Cho
2017 EURASIP Journal on Image and Video Processing  
This paper presents a textline detection method for degraded historical documents.  ...  In order to address the challenges in historical documents such as document degradation, structure noise, and skews, we develop new methods for the binarization and textline extraction.  ...  In this paper, we present a textline detection algorithm for historical documents, which is a key step to document understanding.  ... 
doi:10.1186/s13640-017-0229-7 fatcat:5lxz7ntmlrbg3og6wgkw2mlfn4

Survey on Segmentation and Recognition of Handwritten Arabic Script

Amani Ali Ahmed Ali, M. Suresha
2020 SN Computer Science  
This paper presents various algorithms with respect to text, word and characters segmentation and recognition of Arabic document.  ...  Various strategies used for creating a powerful recognition system have been summarized.  ...  the following forms in case a round loop is detected. • A round or elongated loop: • An ascender: • A right or left curvature: • Valleys: .  ... 
doi:10.1007/s42979-020-00187-y fatcat:qows2arqnngzbpo5p63aoecjjm

A One-Pass Approach for Slope and Slant Estimation of Tri-Script Handwritten Words

Suman Kumar Bera, Radib Kar, Souvik Saha, Akash Chakrabarty, Sagnik Lahiri, Samir Malakar, Ram Sarkar
2018 Journal of Intelligent Systems  
Handwritten words can never complement printed words because the former are mostly written in either skewed or slanted form or in both.  ...  To address this issue, we propose a novel one-pass method, based on fitting an oblique ellipse over the word images, to estimate both the slope and slant angles of the same.  ...  As a remedy, we have proposed a one-pass algorithm based on estimating the best-fitted oblique ellipse on the core region of a word image.  ... 
doi:10.1515/jisys-2018-0105 fatcat:7psnezmfwvhtxhoarlufi3rsau

Block decomposition and segmentation for fast Hough transform evaluation

Stavros J. Perantonis, Basilios Gatos, Nikos Papamarkos
1999 Pattern Recognition  
Based on this type of decomposition, a fast method for evaluating the Hough transform is introduced.  ...  A complexity analysis of the proposed block Hough transform algorithm sets constraints on the complexity of algorithms used for block decomposition, so that the total decomposition and Hough transform  ...  Fig. 9 . 9 Skew detection using HT; (a) original document. (b) skew detected and corrected version.  ... 
doi:10.1016/s0031-3203(98)00125-3 fatcat:sdmshalmnngijmlzghpexcgqga

An Efficient Word Segmentation Technique for Historical and Degraded Machine-Printed Documents

M. Makridis, N. Nikolaou, B. Gatos
2007 Proceedings of the International Conference on Document Analysis and Recognition  
It is based on: (i) a dynamic run length smoothing algorithm that helps grouping together homogeneous text regions, (ii) noise and punctuation marks removal as well as on obstacle detection in order to  ...  Word segmentation is a crucial step for segmentation-free document analysis systems and is used for creating an index based on word matching.  ...  First, noisy -non text elements are filtered out based on three features of the connected components and their corresponding bounding boxes: height, elongation (the ratio of the shorter to the longer side  ... 
doi:10.1109/icdar.2007.4378699 dblp:conf/icdar/MakridisNG07 fatcat:mbagnlsprjdb7dxugi4z55uib4

Text identification for document image analysis using a neural network

C. Strouthopoulos, N. Papamarkos
1998 Image and Vision Computing  
The neural network classifier is based on a Kohonen Self Organized Feature Map (SOFM).  ...  The proposed approach is based on a new set of features combined with a self-organized neural network classifier.  ...  The RLS algorithm imposes a smoothing on the binary form of the document using two predetermined parameters, one for the vertical and one for the horizontal smoothing of the blocks.  ... 
doi:10.1016/s0262-8856(98)00055-9 fatcat:fiszq252pfaoll3fn2mipsfmte
« Previous Showing results 1 — 15 out of 3,068 results