Filters








91 Hits in 5.3 sec

Word spotting in handwritten Arabic documents using bag-of-descriptors

Youssef Elfakir, Ghizlane Khaissidi, Mostafa Mrabti, Driss Chenouni, Mounim El Yacoubi
2016 Contemporary Engineerng Sciences  
This paper presents a query-by-example word spotting in handwritten Arabic documents, based on Scale Invariant Feature Transform (SIFT), without using any text word or line segmentation approach, because  ...  In the end, we represent the image's regions as histogram of visual words. The validate study is conducted under a series of controlled experiments on handwritten Arabic documents images.  ...  Many existing architectures on word spotting based on text, word or line segmentation steps [3, 4] used in the recognition systems to facilitate the search, Roy et al.  ... 
doi:10.12988/ces.2016.6688 fatcat:itjzjhdawndwhli3urol5fep34

Date-field retrieval in scene image and video frames using text enhancement and shape coding

Partha Pratim Roy, Ayan Kumar Bhunia, Umapada Pal
2018 Neurocomputing  
Next, Pyramid Histogram of Oriented Gradient (PHOG) feature has been extracted from gray image and binary images for date-spotting framework.  ...  Finally, to boost the performance further, a shape coding based scheme is used to combine the similar shape characters in same class during word spotting.  ...  We present the MLP-HMM tandem systems for our word spotting purpose in Shape Coding based Word Spotting Shape coding based text encoding approach has been used efficiently in printed documents [21  ... 
doi:10.1016/j.neucom.2016.08.141 fatcat:q4iu3zxvufd7nh4rjjrdr4akri

Zone-based Keyword Spotting in Bangla and Devanagari Documents [article]

Ayan Kumar Bhunia, Partha Pratim Roy, Umapada Pal
2017 arXiv   pre-print
Pyramid Histogram of Oriented Gradient (PHOG) feature has been used in our word spotting framework.  ...  Also, we propose a novel feature combining foreground and background information of text line images for keyword-spotting by character filler models.  ...  A pyramidal histogram of character based training approach was proposed [33] for improved word retrieval performance. Very few works have been done for keyword spotting in Indic script.  ... 
arXiv:1712.01434v1 fatcat:fwu33ixo35eibmjmccslifu64u

Integrating Visual and Textual Cues for Query-by-String Word Spotting

David Aldavert, Marcal Rusinol, Ricardo Toledo, Josep Llados
2013 2013 12th International Conference on Document Analysis and Recognition  
The textual representation is formulated in terms of character n-grams while the visual one is based on the bag-of-visual-words scheme.  ...  The proposed method is evaluated using a collection of historical documents outperforming state-of-the-art performances.  ...  ACKNOWLEDGMENT This work has been partially supported by the Spanish Ministry of Education and Science under projects TIN2009-14633-C03-03, TIN2011-25606 and TIN2012-37475-C02-02.  ... 
doi:10.1109/icdar.2013.108 dblp:conf/icdar/AldavertRTL13 fatcat:3vznvz4ayvb5haosggm2z3242y

Bag-of-features HMMs for segmentation-free Bangla word spotting

L. Rothacker, G. A. Fink, P. Banerjee, U. Bhattacharya, B. B. Chaudhuri
2013 Proceedings of the 4th International Workshop on Multilingual OCR - MOCR '13  
Furthermore, we outperform state-of-the-art results on the well-known George Washington word spotting benchmark.  ...  In this paper we present how Bag-of-Features Hidden Markov Models can be applied to printed Bangla word spotting. These statistical models allow for an easy adaption to different problem domains.  ...  In [9] , Mahmud et al. presented a Neural Network based character recognition approach depending on Freeman Chain Codes. Hasant et al. [5] proposed an open Tesseract based OCR for Bangla script.  ... 
doi:10.1145/2505377.2505384 dblp:conf/icdar/RothackerFBBC13 fatcat:kfieos5scjgvtcaznmq5265lza

Bag-of-Visual-Words for Signature-Based Multi-Script Document Retrieval [article]

Ranju Mandal and Partha Pratim Roy and Umapada Pal and Michael Blumenstein
2018 arXiv   pre-print
An end-to-end architecture for multi-script document retrieval using handwritten signatures is proposed in this paper.  ...  A bag-of-visual-words powered by SIFT descriptors in a patch-based framework is proposed to compute the features and a Support Vector Machine (SVM)-based classifier was used to separate signatures from  ...  Neural Networks and CTC Token Passing algorithms were used for the word spotting task. Hidden Markov Model (HMM)-based methods are extensively used for modeling handwritten text, word spotting, etc.  ... 
arXiv:1807.06772v1 fatcat:z2g6qunh4neevitr7lbgsu7cc4

HWNet v2: An Efficient Word Image Representation for Handwritten Documents [article]

Praveen Krishnan, C.V. Jawahar
2019 arXiv   pre-print
On the challenging IAM dataset, our method is first to report an mAP of around 0.90 for word spotting with a representation size of just 32 dimensions.  ...  Our representation leads to a state-of-the-art word spotting performance on standard handwritten datasets and historical manuscripts in different languages with minimal representation size.  ...  The method uses a new textual representation referred to as pyramidal histogram of characters (phoc), which concatenates the histogram of characters at multiple spatial regions in a pyramidal fashion.  ... 
arXiv:1802.06194v2 fatcat:mr2gvfy775hpzmncvrnprecwb4

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
This paper presents a novel word spotting framework using dynamic shape coding for text retrieval in natural scene image and video frames.  ...  A novel unsupervised dynamic shape coding based scheme has been used to group similar shape characters to avoid confusion and to improve text alignment.  ...  The efficiency of two-stage dynamic shape coding based text detection approach can be taken forward for word spotting systems in other applications such historical documents, handwritten documents, etc  ... 
arXiv:1708.05529v6 fatcat:4ktrdk2khrh35m5f6o2b3msde4

A study of Bag-of-Visual-Words representations for handwritten keyword spotting

David Aldavert, Marçal Rusiñol, Ricardo Toledo, Josep Lladós
2015 International Journal on Document Analysis and Recognition  
The Bag-of-Visual-Words (BoVW) framework has gained popularity among the document image analysis community, specifically as a representation of handwritten words for recognition or spotting purposes.  ...  Although in the computer vision field the BoVW method has been greatly improved, most of the approaches in the document image analysis domain still rely on the basic implementation of the BoVW method disregarding  ...  In the document image analysis literature, we can distinguish two different families of keyword spotting methods depending on the representation of the handwritten words [26] .  ... 
doi:10.1007/s10032-015-0245-z fatcat:krl6s2gak5cmbe344xzsts2dr4

Radial Line Fourier Descriptor for Historical Handwritten Text Representation

Anders Hast, Ekta Vats
2018 Journal of WSCG  
Recognition-free retrieval or word spotting is popularly used for information retrieval and digitization of the historical handwritten documents.  ...  The effectiveness of the RLF descriptor for segmentation-free handwritten word spotting is empirically evaluated on well-known historical handwritten datasets using standard evaluation measures.  ...  Section 3 presents the proposed method based on the RLF descriptor for segmentation-free handwritten word spotting.  ... 
doi:10.24132/jwscg.2018.26.1.4 fatcat:cxhey67jrzdd7owxweixy7chtu

Towards query-by-speech handwritten keyword spotting

Marcal Rusinol, David Aldavert, Ricardo Toledo, Josep Llados
2015 2015 13th International Conference on Document Analysis and Recognition (ICDAR)  
In this paper, we present a new querying paradigm for handwritten keyword spotting.  ...  We propose to represent handwritten word images both by visual and audio representations, enabling a query-by-speech keyword spotting system.  ...  On the one hand a query-by-speech handwritten word spotting system, and on the other hand a handwritten text-to-speech mechanism.  ... 
doi:10.1109/icdar.2015.7333812 dblp:conf/icdar/RusinolATL15 fatcat:s6hdeokmsravjjfhw333ckq7gm

Efficient segmentation-free keyword spotting in historical document collections

Marçal Rusiñol, David Aldavert, Ricardo Toledo, Josep Lladós
2015 Pattern Recognition  
The proposed method is evaluated using four different collections of historical documents achieving good performances both on handwritten and typewritten scenarios.  ...  In this paper we present an efficient segmentation-free word spotting method, applied in the context of historical document collections, that follows the query-byexample paradigm.  ...  Acknowledgments This work has been partially supported by the Spanish Ministry of Education and Science under projects TIN2011-25606 (SiMeVé), and TIN2012-37475-  ... 
doi:10.1016/j.patcog.2014.08.021 fatcat:rmkxc5odgvf5pc65okwsjjlc24

Document Specific Sparse Coding for Word Retrieval

Ravi Shekhar, C.V. Jawahar
2013 2013 12th International Conference on Document Analysis and Recognition  
We further improve the performance by defining a document specific sparse coding scheme for representing visual words (interest points) in document images.  ...  Bag of words (BoW) based retrieval is an efficient method to compare the visual similarity between two images. Recognition free methods based on BoW have shown to outperform OCR based methods.  ...  ACKNOWLEDGEMENT This work was partly supported by Ministry of Communication and Information Technology, Government of India.  ... 
doi:10.1109/icdar.2013.132 dblp:conf/icdar/ShekharJ13 fatcat:pxsd7vjphjeathhggt2t5pdeza

ICFHR 2014 Competition on Handwritten Keyword Spotting (H-KWS 2014)

Ioannis Pratikakis, Konstantinos Zagoris, Basilis Gatos, Georgios Louloudis, Nikolaos Stamatopoulos
2014 2014 14th International Conference on Frontiers in Handwriting Recognition  
H-KWS 2014 is the Handwritten Keyword Spotting Competition organized in conjunction with ICFHR 2014 conference.  ...  The main objective of the competition is to record current advances in keyword spotting algorithms using established performance evaluation measures frequently encountered in the information retrieval  ...  This method consists of the following process: First, text strings are embedded into a d−dimensional binary space -dubbed pyramidal histogram of characters or PHOC -that encodes if a particular character  ... 
doi:10.1109/icfhr.2014.142 dblp:conf/icfhr/PratikakisZGLS14 fatcat:lf34cspjtnckfnqnkr2n6n4vae

Segmentation-Free Keyword Retrieval in Historical Document Images [chapter]

Irina Rabaev, Itshak Dinstein, Jihad El-Sana, Klara Kedem
2014 Lecture Notes in Computer Science  
The document images are subdivided into overlapping patches of varying sizes, where each patch is described by the bag-of-visual-words descriptor.  ...  The proposed method works directly on the gray scale representation and does not require any pre-processing to enhance document images.  ...  FI 1494/3-2, the Ministry of Science and Technology of Israel, the Council of Higher Education of Israel, the Lynn and William Frankel Center for Computer Sciences and by the Paul Ivanier Center for Robotics  ... 
doi:10.1007/978-3-319-11758-4_40 fatcat:mo7tfs5wvndvnk3sm2ko3jb64y
« Previous Showing results 1 — 15 out of 91 results