Script Identification of Multi-Script Documents: a Survey

Ubul, Kurban; Tursun, Gulzira; Aysa, Alimjan; Impedovo, Donato; Pirlo, Giuseppe; Yibulayin, Tuergen

doi:10.1109/access.2017.2689159

Cited by 26 publications

(16 citation statements)

References 112 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These scripts must be identified prior to feeding the text regions to the respective OCR engines for recognition. Script recognition has been studied by researchers for text in video images as well as printed and handwritten documents [50,51]. Recognition of script in video text is naturally much more challenging as opposed to printed or handwritten documents due to low resolution of text and in some cases complex backgrounds [52,53].…”

Section: Script Recognitionmentioning

confidence: 99%

Detection and recognition of cursive text from video frames

Mirza

Zeshan

Atif

et al. 2020

J Image Video Proc.

View full text Add to dashboard Cite

Textual content appearing in videos represents an interesting index for semantic retrieval of videos (from archives), generation of alerts (live streams), as well as high level applications like opinion mining and content summarization. The key components of such systems require detection and recognition of textual content which also make the subject of our study. This paper presents a comprehensive framework for detection and recognition of textual content in video frames. More specifically, we target cursive scripts taking Urdu text as a case study. Detection of textual regions in video frames is carried out by fine-tuning deep neural networks based object detectors for the specific case of text detection. Script of the detected textual content is identified using convoluational neural networks (CNNs), while for recognition, we propose a UrduNet, a combination of CNNs and long short-term memory (LSTM) networks. A benchmark dataset containing cursive text with more than 13,000 video frame is also developed. A comprehensive series of experiments is carried out reporting an F-measure of 88.3% for detection while a recognition rate of 87%.

show abstract

Section: Script Recognitionmentioning

confidence: 99%

Detection and recognition of cursive text from video frames

Mirza

Zeshan

Atif

et al. 2020

J Image Video Proc.

View full text Add to dashboard Cite

show abstract

“…This section presents some works related to handwritten script classification proposed in the literature. A recent survey by Ubul et al () published in the year 2017 reports a few research works on script classification from handwritten Indic script documents. Benjelil, Kanoun, Mullot, and Alimi () have used steerable pyramid transforms for script identification at word‐level from printed and handwritten samples in Arabic and Latin scripts.…”

Section: Related Workmentioning

confidence: 99%

A clustering‐based feature selection framework for handwritten Indic script classification

et al. 2019

View full text Add to dashboard Cite

In India, which has numerous officially recognized scripts, there is a primary need for categorizing the documents on the basis of the scripts used therein. Identification of script used in a document is essential for its effective handling both manually and digitally. Identification of script in a document image is an important research problem in the pattern recognition field, which, at times, suffers from the issue of growing dimensionality of the feature vector and requires an efficient feature selection technique. Keeping this fact in mind, in this paper, we propose a clustering‐based filter feature selection framework in order to extract an optimal and effective feature subset from the original feature vector. The present feature selection methodology is evaluated on a script classification problem involving handwritten documents in 12 major Indic scripts. Experiments are done at word‐level, text‐line‐level, and block‐level. Experiments demonstrate that a reasonable increment in classification accuracy has been realized using comparatively lesser number of features. The proposed framework for feature selection is computationally inexpensive and can be applied to other pattern recognition problems as well.

show abstract

“…A good feature extraction method is characterised by the ability to extract similar information about similar objects and different information for different objects (Bataineh, Abdullah & Omar, 2012;Zavvar et al, 2016). The feature extraction methods comprise two approaches; local approach (Li et al, 2009) and global approach (Bataineh et al, 2012;Ubul et al, 2017). The local feature extraction is based on segmentation process wherein the text in the document images is split into several parts (character, glostrokes, primitives) to be used for extracting discreet information on features values.…”

Section: Literature Reviewmentioning

confidence: 99%

Automatic Multi-lingual Script Recognition Application

Abu-Ain

Abdullah

Omar

et al. 2018

GEMA

View full text Add to dashboard Cite

Document Image Analysis and Recognition (DIAR) technique is used to recognize text component and translate it into editable format. Scripts are a set of graphical representations used to express a particular writing system as well as subsets belonging to a particular writing system. The writing styles of more than one script family may then be adopted by one language, such as in the cases where the old Malay language (Jawi) adopts the Arabic script while the modern one adopts the Roman script. The seven major scripts used in this research are in handwritten style including Arabic, Devanagari, Hebrew, Thai, Greek, Cyrillic and Korean. Automatic Multilingual Script Recognition (AMSR) is one of the main challenges in DIAR domain. Currently, only few attempts have been made for automated script identification of off-line handwritten documents images. Most available AMSR applications only deal with printed documents and script types, and they neglect handwritten and multilingual documents. The objective of this study is to propose a multilingual AMSR framework. The research methodology consists of a proposed multilingual AMSR framework. The multilingual AMSR framework is tested on Multilingual-HW datasets, which contains more than seven international unconstraint handwritten scripts, using Grey-Level Co-occurrence Matrix and Local Binary Pattern. The average accuracy of both methods is about 97.01% and 85.29% respectively. This proposed multilingual AMSR is hoped to be beneficial to a group of community which requires automatic sorting multilingual documents. This research can also be extended to document forensic area or international relations agency to identify unknown native document.

show abstract

Script Identification of Multi-Script Documents: a Survey

Cited by 26 publications

References 112 publications

Detection and recognition of cursive text from video frames

Detection and recognition of cursive text from video frames

A clustering‐based feature selection framework for handwritten Indic script classification

Automatic Multi-lingual Script Recognition Application

Contact Info

Product

Resources

About