Arabic and Latin Script Identification in Printed and Handwritten Types Based on Steerable Pyramid Features

Benjelil, Mohamed; Kanoun, Slim; Mullot, Rémy; Alimi, Adel M.

doi:10.1109/icdar.2009.287

Cited by 18 publications

(3 citation statements)

References 19 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Character recognition is hampered if a record has numerous scripts. Numerous scholars have conducted in-depth studies on offline handwritten character recognition based on Indic [35], [36], [37], [38], [39] and non-Indic [35], [37], [40], [41], [42] scripts. As shown in Table 2, the foundation of every study is the identification of writing in both handwritten and machineprinted texts.…”

Section: A Offline Handwriting Recognitionmentioning

confidence: 99%

“…However, the earlier studies only offered an algorithm for the recognition of printed documents in [35], [38], [39], [42], [44]. Some studies have described their work on printed and handwritten recognition [37], [40], [43], [45]. Other substantial works based on offline handwriting recognition are suggested in [46], [47], [48], [49], [50].…”

Section: A Offline Handwriting Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Literature Review on Air-written Online Handwritten Recognition

K. Jabde,

H. Patil,

D. Vibhute

et al. 2024

IJCDS

View full text Add to dashboard Cite

The COVID-19 pandemic has shifted ordinary life into a digital platform. Individuals rapidly use digital or online media to avoid the impact of touch-based platforms. In this case, touchless technology is primarily used in operation theatres, online education systems, ticket counters, etc. However, the online numerals or characters written in the air are challenging to recognize efficiently due to the writing styles of every individual. Therefore, the present research focuses on recent work on online air-written handwritten recognition. Almost eighty-plus standard articles on handwriting recognition from various journal/conference databases are considered for the current review. In addition, the generalized methodology of handwriting recognition is also provided for new research. It is observed that some online handwritten databases for some languages are freely available for research purposes. However, the online real-time air-written numeral dataset is private for Devanagari and English. Therefore, designing and developing a standard dataset for character or numeral recognition written in the air is suggested. The earlier studies achieved satisfactory results on air-writing multilingual numerals collected via or without sensors using advanced machine learning and deep learning methods. The convolutional neural network (CNN) has provided the best accuracy for several languages, excluding Devanagari.

show abstract

Section: A Offline Handwriting Recognitionmentioning

confidence: 99%

Section: A Offline Handwriting Recognitionmentioning

confidence: 99%

A Comprehensive Literature Review on Air-written Online Handwritten Recognition

K. Jabde,

H. Patil,

D. Vibhute

et al. 2024

IJCDS

View full text Add to dashboard Cite

show abstract

“…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. Rajput and Anita () identify scripts at block‐level using a technique involving discrete cosine transform and wavelets of Daubechies family for feature extraction.…”

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