Filters








68 Hits in 7.5 sec

New Radon Transform Based Texture Features of Handwritten Document [article]

Rustam Latypov, Evgeni Stolov
2019 arXiv   pre-print
In this paper, we present some new features describing the handwritten document as a texture. These features are based on the Radon transform.  ...  All values can be obtained easily and suit for the coarse classification of documents.  ...  ACKNOWLEDGMENTS The work is performed according to the Russian Government Program of Competitive Growth of Kazan Federal University. This work is also supported by the RFBR grant №18-47-16005. 8.  ... 
arXiv:1901.03068v1 fatcat:ryyxxznuxrekvitqzaoohibjjy

Recognition of Handwritten Mathematical Tex

Yassine Chajri, Belaid Bouikhalene
2016 International Journal of Future Generation Communication and Networking  
The recognition of handwritten mathematical documents is a very important field which is interested in identifying the text, graphics or notations and in extracting information.  ...  In this paper the focus will be on the handwritten mathematical text recognition and we are going to present all the necessary steps in our system (preprocessing, text lines segmentation, mathematical  ...  which is based on Radon transform.  ... 
doi:10.14257/ijfgcn.2016.9.8.30 fatcat:agvxdey3unhkdlukdp24mbd4by

Statistical Texture Features based Handwritten and Printed Text Classification in South Indian Documents [article]

Mallikarjun Hangarge, K.C. Santosh, Srikanth Doddamani, Rajmohan Pardeshi
2013 arXiv   pre-print
In this paper, we use statistical texture features for handwritten and printed text classification. We primarily aim for word level classification in south Indian scripts.  ...  Words are first extracted from the scanned document.  ...  The Radon transform has also been used to represent text that goes word-wise together with SVM for classification [13] .  ... 
arXiv:1303.3087v1 fatcat:ga56r72okvgf5kdcxar7aw2xm4

A New Approach for Texture based Script Identification At Block Level using Quad Tree Decomposition [article]

Pawan Kumar Singh, Supratim Das, Ram Sarkar, Mita Nasipuri
2020 arXiv   pre-print
The results serve to establish the efficacy of the present approach to the classification of handwritten Indic scripts  ...  In this paper, we present the significance of Gabor wavelets filters in extracting directional energy and entropy distributions for 11 official handwritten scripts namely, Bangla, Devanagari, Gujarati,  ...  (SRUVM) of Computer Science and Engineering Department, Jadavpur University, for providing infrastructure facilities during progress of the work.  ... 
arXiv:2009.07435v1 fatcat:l6dvmxz47fd2rminrhbaxm2gau

Curvelets based feature extraction of handwritten shapes for ancient manuscripts classification

Guillaume Joutel, Véronique Eglin, Stéphane Bres, Hubert Emptoz, Xiaofan Lin, Berrin A. Yanikoglu
2007 Document Recognition and Retrieval XIV  
We propose a global approach of writers' classification based on Curvelets based features in relation with two discriminative shapes properties, the curvature and the orientation.  ...  Those features are revealing of structural and directional micro-shapes and also of concavity that captures the finest variations in the contour.  ...  from the CERPI of the ENS-Lettres of Lyon to have helped us to understand the genesis of the Montesquieu's corpus and to have guided to us towards the definition of robust criteria for styles differentiation  ... 
doi:10.1117/12.704450 dblp:conf/drr/JoutelEBE07 fatcat:ifftqvsqffch7oe4piriha3zcm

Semi-automatic ground truth generation using unsupervised clustering and limited manual labeling: Application to handwritten character recognition

Szilárd Vajda, Yves Rangoni, Hubert Cecotti
2015 Pattern Recognition Letters  
In this paper, we propose a generic, semi-automatic labeling technique for large handwritten character collections.  ...  After clustering the images in each feature space, the human expert labels the cluster centers. Each data point inherits the label of its cluster's center.  ...  The discriminating power of this feature is similar to the raw pixels and the Radon transform.  ... 
doi:10.1016/j.patrec.2015.02.001 pmid:25870463 pmcid:PMC4392711 fatcat:6i7vpen2krddvlanekuqjgovki

A Complete Pyramidal Geometrical Scheme for Text Based Image Description and Retrieval [chapter]

Guillaume Joutel, Véronique Eglin, Hubert Emptoz
2008 Lecture Notes in Computer Science  
It is based on the Curvelets decomposition of images for indexing linear singularities of handwritten shapes.  ...  This paper presents a general architecture for ancient handwriting documents content description and retrieval.  ...  Conclusion We can say with confidence that Curvelets Transforms can be used as a general technique for feature detection.  ... 
doi:10.1007/978-3-540-69905-7_54 fatcat:mgpnplgwxzh3bnmientwekcopm

A comparative study of different texture features for document image retrieval

Fahimeh Alaei, Alireza Alaei, Umapada Pal, Michael Blumenstein
2019 Expert systems with applications  
Highlights:  Evaluating statistical, transform, model, and structural-based texture features for DIR  Comparative analysis of the DIR results obtained from 26 texture features  Providing a computational  ...  Twenty-six different texture feature extraction methods from four main categories of texture features, statistical, transform, model, and structural-based approaches, are considered in this research work  ...  D"Andecy of the ITESOFT Company for providing access to the ITESOFT dataset.  ... 
doi:10.1016/j.eswa.2018.12.007 fatcat:uawsnriyjzax7bsofe4xyhfu6i

Feature extraction using Radon transform and Discrete Wavelet Transform for facial emotion recognition

Hasimah Ali, Vinothan Sritharan, Muthusamy Hariharan, Siti Khadijah Zaaba, Mohamed Elshaikh
2016 2016 2nd IEEE International Symposium on Robotics and Manufacturing Automation (ROMA)  
It is of significant benefit to man-machine communication and can assist in the automatic processing of handwritten documents.  ...  On-line handwriting recognition is the task of determining what letters or words are present in handwritten text.  ...  Feature Extraction Using Multiwavelet Transform and Classification Multiwavelet transform is a new concept in the framework of wavelet transform but has some important differences.  ... 
doi:10.1109/roma.2016.7847840 fatcat:kq2td2qtpvcafcwq7wbaqs6w7q

Directional Discrete Cosine Transform for Handwritten Script Identification

Mallikarjun Hangarge, K.C. Santosh, Rajmohan Pardeshi
2013 2013 12th International Conference on Document Analysis and Recognition  
This paper presents directional discrete cosine transforms (D-DCT) based word level handwritten script identification.  ...  The conventional discrete cosine transform (DCT) emphasizes vertical and horizontal energies of an image and de-emphasizes directional edge information, which of course plays a significant role in shape  ...  Primarily, global features used in [1] - [6] are based on DCT, DWT, Gabor, steerable pyramids, and the Radon transform.  ... 
doi:10.1109/icdar.2013.76 dblp:conf/icdar/HangargeSP13 fatcat:txpfhx2utjfozamhukuiapfnva

SIGNATURE IDENTIFICATION AND VERIFICATION SYSTEMS: A COMPARATIVE STUDY ON THE ONLINE AND OFFLINE TECHNIQUES

Nehal Hamdy Al-banhawy, Al-Azhar University, Egypt, Heba Mohsen, Neveen Ghali, Future University in Egypt, Future University in Egypt
2020 Future Computing and Informatics Journal  
Handwritten signature identification and verification has become an active area of research in recent years.  ...  Handwritten signature identification systems are used for identifying the user among all users enrolled in the system while handwritten signature verification systems are used for authenticating a user  ...  73.49% 2015 from ICDAR2013 which Fourier Transform based features, accuracy (online) contains data from 11 Wavelet Transform based features writers for training set and and Global features 20 writers  ... 
doi:10.54623/fue.fcij.5.1.3 fatcat:3idf7nfq5ndpphi24h4cfulicu

Automatic processing of handwritten bank cheque images: a survey

R. Jayadevan, S. R. Kolhe, P. M. Patil, U. Pal
2011 International Journal on Document Analysis and Recognition  
An attempt is made in this paper to present the state of the art in automatic processing of handwritten cheque images.  ...  Huge volumes of handwritten bank cheques are processed manually every day in developing countries.  ...  Acknowledgments The authors are thankful to the Department of Science and Technology, Ministry of Science and Technology, New Delhi for supporting this non-commercial research under the Fast Track Scheme  ... 
doi:10.1007/s10032-011-0170-8 fatcat:kmrv6tqtbzbolks7pwmg3juqeu

Specimen Authentication System Using Pixel-Based Algorithm

HARRY ABREGANA, ROLIE CATUBURAN, NOVY HANNAH DE LOS REYES, DAISA GUPIT
2020 SMCC Higher Education Research Journal  
The textural points are computed and concatenated with coefficients of contourlet transform to structure the final feature vector.  ...  The paper provides a new fuzzy approach to off-line handwritten signature recognition. The solution is based totally on characteristic feature extraction.  ... 
doi:10.18868/ccs.03.060120.01 fatcat:tt25gbtcubcabgjdilsco2rg5e

Generic Scale-Space Architecture for Handwriting Documents Analysis [chapter]

Joutel Guillaume, Eglin Veronique, Emptoz Hubert
2010 Pattern Recognition Recent Advances  
Many of those use features based on texture, colour, … and in our case comparison would not be very easy.  ...  Features extraction DCTG2 The version of the Curvelets transform introduced in section 0 uses the Radon transform. This transform is difficult to discretize.  ...  /pattern-recognition-recentadvances/generic-scale-space-architecture-for-handwriting-documents-analysis  ... 
doi:10.5772/9358 fatcat:nky4w4k4orbn7os23qjoybxyem

M-HMOGA: A New Multi-Objective Feature Selection Algorithm for Handwritten Numeral Classification

Ritam Guha, Manosij Ghosh, Pawan Kumar Singh, Ram Sarkar, Mita Nasipuri
2019 Journal of Intelligent Systems  
In this paper, a new feature selection approach named Memory-Based Histogram-Oriented Multi-objective Genetic Algorithm (M-HMOGA) is introduced to identify the informative feature subset to be used for  ...  The proposed M-HMOGA approach is applied to two recently used feature sets, namely Mojette transform and Regional Weighted Run Length features.  ...  The authors of this paper are thankful to all those individuals who had given appropriate consents and contributed wholeheartedly in developing the handwritten numeral script database used in the current  ... 
doi:10.1515/jisys-2019-0064 fatcat:fpdy73lmovcvtpmjagw3zvtf5i
« Previous Showing results 1 — 15 out of 68 results