Filters








31 Hits in 4.1 sec

A novel method for segmenting and straightening of text lines in handwritten Telugu documents based on smearing and regression approach

Mslb. Subrahmanyam, V Vijaya Kumar, B Eswara Reddy
2018 International Journal of Engineering & Technology  
In handwritten document images, segmenting text lines is a very challenging task due to various reasons like variability in intra baseline skew and inter line distance between text lines.  ...  To identify text lines more precisely cubic polynomial regression is used between vertical midpoints of two blocks of compound handwritten Telugu characters.  ...  In [8] Dibyayan Chakraborty proposed method for detecting base line from multi-lingual multi-turn handwritten document images.  ... 
doi:10.14419/ijet.v7i3.13286 fatcat:gxvrm3yq7zdvlcnqw3kuoqrsq4

Automatic Script and Type Identification in Bi-lingual Forms

Afef Kacem Echi
2016 International Journal of Computing and Information Sciences  
In this paper we have developed a system that can automatically discriminate between machine-printed and handwritten words in structured bi-lingual (Arabic and French) form document layout.  ...  In the used forms, handwritten data usually touch or cross the preprinted form frames and texts, creating complex problems for the recognition routines.  ...  Each minimum in the profile is considered as a separator between the text-lines (See Fig. 4 ). -Detection and removal of the connected components in the intersection with separators lines.  ... 
doi:10.21700/ijcis.2016.104 fatcat:ykevvi7p3rfjrgkk36mnzw56nq

A comprehensive survey of handwritten document benchmarks: structure, usage and evaluation

Raashid Hussain, Ahsen Raza, Imran Siddiqi, Khurram Khurshid, Chawki Djeddi
2015 EURASIP Journal on Image and Video Processing  
Research in these and similar related problems requires the availability of handwritten samples for validation of the developed techniques and algorithms.  ...  In addition to the statistics of the discussed databases, we also present a comparison of these databases on a number of dimensions.  ...  IBM UB database The IBM UB database [111] developed at the Center for Unified Biometrics and Sensors (CUBS) at the University at Buffalo is a multi-lingual online/offline database of handwritten samples  ... 
doi:10.1186/s13640-015-0102-5 fatcat:cvp7kv5vmrddnlrvudn5z4wnnm

Improving patch-based scene text script identification with ensembles of conjoined networks [article]

Lluis Gomez, Anguelos Nicolaou, Dimosthenis Karatzas
2017 arXiv   pre-print
In addition, we propose a new public benchmark dataset for the evaluation of multi-lingual scene text end-to-end reading systems.  ...  This paper focuses on the problem of script identification in scene text images.  ...  The dataset is suitable for evaluating various typical stages of end-to-end pipelines, such as multi-script text detection, joint detection and script identification, end-toend multi-lingual recognition  ... 
arXiv:1602.07480v2 fatcat:ayqfeitjonao3mfjuvhbudfm3a

Markov models for offline handwriting recognition: a survey

Thomas Plötz, Gernot A. Fink
2009 International Journal on Document Analysis and Recognition  
Since their first inception more than half a century ago, automatic reading systems have evolved substantially, thereby showing impressive performance on machine-printed text.  ...  It is therefore the goal of this survey to provide a comprehensive overview of the application of Markov models in the research field of offline handwriting recognition, covering both the widely used hidden  ...  These lines (baseline and the line above lowercase letters) are used for rotation normalization and shearing, detection of ascenders and descenders, and height normalization.  ... 
doi:10.1007/s10032-009-0098-4 fatcat:el2rdqroj5dp3bfuvzs2bwx2bm

A fine-grained approach to scene text script identification [article]

Lluis Gomez, Dimosthenis Karatzas
2016 arXiv   pre-print
The evidence provided shows that multi-lingual scene text recognition in the wild is a viable proposition. Source code of the proposed method is made available online.  ...  In addition, we propose a new public benchmark dataset for the evaluation of joint text detection and script identification in natural scenes.  ...  [5] , in the first work dealing this task, propose the use of the wavelet transform to detect edges in text line images.  ... 
arXiv:1602.07475v1 fatcat:xesy7sxekvcwvdzsuxfg6ygfcu

AUTOMATION OF INDIAN POSTAL DOCUMENTS WRITTEN IN BANGLA AND ENGLISH

S. VAJDA, K. ROY, U. PAL, B. B. CHAUDHURI, A. BELAID
2009 International journal of pattern recognition and artificial intelligence  
Here, at first, using Run Length Smoothing Approach (RLSA), non-text blocks (postal stamp, postal seal, etc.) are detected and using positional information Destination Address Block (DAB) is identified  ...  Next, lines and words of the DAB are segmented. In India, the address part of a postal document may be written by combination of two scripts: Latin (English) and a local (State/region) script.  ...  We are also thankful to the Indian Postal department for providing us space and facility to scan images of real postal documents. One of the authors (B. B.  ... 
doi:10.1142/s0218001409007776 fatcat:ov4nxyn3f5acdm5l24szp3u2py

A survey on optical character recognition for Bangla and Devanagari scripts

SOUMEN BAG, GAURAV HARIT
2013 Sadhana (Bangalore)  
Future directions of research in OCR for Indian scripts have been also given.  ...  In this paper, we present a review of OCR work on Indian scripts, mainly on Bangla and Devanagari-the two most popular scripts in India.  ...  Pal & Chaudhuri (2000) have proposed an automatic recognition scheme for unconstrained off-line Bangla handwritten numerals.  ... 
doi:10.1007/s12046-013-0121-9 fatcat:4fna65koxfhw7hwehsrjhe34ma

Cursive Character Recognition in Natural Scene Images using a Multilevel Convolutional Neural Network Fusion

Asghar Ali Chandio, Md. Asikuzzaman, Mark R. Pickering
2020 IEEE Access  
The complex backgrounds, variations in the writing, text size, orientations, low resolution and multi-language text make recognition of text in natural images a complex and challenging task.  ...  INDEX TERMS Cursive text recognition, natural scene Urdu character recognition, multi-scale feature aggregation, multi-level feature fusion, convolutional neural network (CNN) VOLUME 7, 2019  ...  ACKNOWLEDGEMENT The first author is thankful to the University of New South Wales, Australia for supporting his Ph.D. candidature with a scholarship.  ... 
doi:10.1109/access.2020.3001605 fatcat:s2sbgrsoafdl5gpyqdvlziwiw4

Graph Modeling based Segmentation of Handwritten Arabic Text into Constituent Subwords

Hashem Ghaleb, P. Nagabhushan, Umapada Pal
2016 International Journal of Image Graphics and Signal Processing  
Arabic text line can be viewed as a sequence of words which in turn can be viewed as a sequence of subwords.  ...  In this paper, the task of segmenting handwritten Arabic text at sub-word level is taken up.  ...  The author also acknowledges University of Thamar, Yemen for financial support.  ... 
doi:10.5815/ijigsp.2016.12.02 fatcat:tefif3rwi5cpdlzim2pwxi3744

Graph Modeling based Segmentation of Handwritten Arabic Text into Constituent Subwords

Hashem Ghaleb, P. Nagabhushan, Umapada Pal
2016 International Journal of Image Graphics and Signal Processing  
Arabic text line can be viewed as a sequence of words which in turn can be viewed as a sequence of subwords.  ...  In this paper, the task of segmenting handwritten Arabic text at sub-word level is taken up.  ...  The author also acknowledges University of Thamar, Yemen for financial support.  ... 
doi:10.5815/ijigsp.2015.12.02 fatcat:7mxty5yatffdxjldj2dybn7syy

A brief review of document image retrieval methods: Recent advances

Fahimeh Alaei, Alireza Alaei, Michael Blumenstein, Umapada Pal
2016 2016 International Joint Conference on Neural Networks (IJCNN)  
Due to the rapid increase of different digitized documents, the development of a system to automatically retrieve document images from a large collection of structured and unstructured document images  ...  This paper provides an overview of the methods which have been applied for document image retrieval over recent years.  ...  Skew detection and correction [19] [20] [21] , border removal [20] , and normalization of the text line width [22] are also used to enhance document images.  ... 
doi:10.1109/ijcnn.2016.7727648 dblp:conf/ijcnn/AlaeiABP16 fatcat:5tzfmk55r5hmpa3tnhcj3chuji

Word Searching in Scene Image and Video Frame in Multi-Script Scenario using Dynamic Shape Coding [article]

Partha Pratim Roy, Ayan Kumar Bhunia, Avirup Bhattacharyya, Umapada Pal
2018 arXiv   pre-print
We have used a two-stage word spotting approach using Hidden Markov Model (HMM) to detect the translated keyword in a given text line by identifying the script of the line.  ...  Retrieval of text information from natural scene images and video frames is a challenging task due to its inherent problems like complex character shapes, low resolution, background noise, etc.  ...  To the best of our knowledge, searching of scene/video text in multi-lingual scripts is hardly reported in the literature.  ... 
arXiv:1708.05529v6 fatcat:4ktrdk2khrh35m5f6o2b3msde4

Character Degradation Model and HMM Word Recognition System for Text Extracted from Maps [chapter]

Aria Pezeshk, Richard L.
2011 Recent Advances in Document Recognition and Understanding  
In the first method, the paper map is placed on top of the digitizing tablet, and the operator traces over lines and other objects of interest using a stylus or a digitizing puck (a device with crosshairs  ...  Geographic maps are one of the most abundant and valuable sources of accurate information about various features of bodies of land and water.  ...  . • Clutter Removal: The remaining non text objects consisting of buildings, dashed lines, and line fragments are removed using morphological operations, a dashed line detection algorithm, and a search  ... 
doi:10.5772/17814 fatcat:dwfxnp2clfae5kivacywi6aa6y

Learning Neural Textual Representations for Citation Recommendation

Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
Approach to Offline Handwritten Chinese and Japanese Text Line Recognition DAY 1 -Jan 12, 2021 Liebl, Bernhard; Burghardt, Manuel 1412 An Evaluation of DNN Architectures for Page Segmentation of  ...  for Historical Ciphered Manuscript Recognition DAY 1 -Jan 12, 2021 -DAY 1 -Jan 12, 2021 Quirós, Lorenzo; Vidal, Enrique 2114 OS T4.1 Learning to Sort Handwritten Text Lines in Reading Order through  ... 
doi:10.1109/icpr48806.2021.9412725 fatcat:3vge2tpd2zf7jcv5btcixnaikm
« Previous Showing results 1 — 15 out of 31 results