Directional Discrete Cosine Transform for Handwritten Script Identification

Hangarge, Mallikarjun; Santosh, K. C.; Pardeshi, Rajmohan

doi:10.1109/icdar.2013.76

Cited by 43 publications

(14 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors employed some visual discriminating features to classify them. In another work, Hangarge et al [17] discussed about directional discrete cosine transform (DCT) based features to identify six different Indic scripts. Discrete wavelet transform (DWT), radon transform (RT), DCT and statistical filters were collectively employed by Pardeshi et al [18] to perform word-level script identification from eleven official Indic scripts.…”

Section: Handwritten Script Identification -A Quick Surveymentioning

confidence: 99%

Automatic Line-Level Script Identification From Handwritten Document Images - A Region-Wise Classification Framework for Indian Subcontinent

Obaidullah

Halder

Santosh

et al. 2018

MJCS

View full text Add to dashboard Cite

Script identification is a well-studied problem for automatic processing of document images. Several attempts have been made so far, but it is still far ahead from the complete solution. In this paper, an automatic approach for line-level handwritten script identification (HSI), considering eight official Indic scripts namely: Bangla, Devanagari, Kannada, Malayalam, Oriya, Roman, Telugu, and Urdu is proposed. We consider a 148-dimensional feature vector using: image component fractal dimension, structural and visual appearance, directional stroke, interpolation and Gabor energy based texture features. For classification, we divide the whole script dataset based on different regions of India, to study a region-wise classification performance. Experimentation was carried out using the state-of-the-art classifiers: multilayer perceptron (MLP), support vector machine (SVM), random forest (RF), and fuzzy unordered rule induction algorithm (FURIA). Among all, we found that MLP as the best performer in terms of average accuracy of 98.2%, 99.5%, 99.1%, 99.5%, 99.9%, 98%, 98.9% for eight-script, bi-script, eastern, north, south Indian script groups, scripts with 'matra' vs without 'matra', and dravidian vs. non-dravidian groups respectively.

show abstract

Section: Handwritten Script Identification -A Quick Surveymentioning

confidence: 99%

Automatic Line-Level Script Identification From Handwritten Document Images - A Region-Wise Classification Framework for Indian Subcontinent

Obaidullah

Halder

Santosh

et al. 2018

MJCS

View full text Add to dashboard Cite

show abstract

“…The work was done at the block level. In a recent work Hangarge et al [11] proposed a word level script identification technique considering Roman, Devnagari and four south Indian scripts namely Kannada, Telugu, Tamil and Malayalam. Their primary investigation was capturing diagonal edge based shape information by applying 1D and 2D DCT, which they have reported as directional DCT based features.…”

Section: Releted Workmentioning

confidence: 99%

“…Average accuracy rate found using MLP is 94.4% on the test data without any rejection. (11) here t i is the target result and o i is the output result.…”

Section:  Multi Layer Perceptron (Mlp)mentioning

confidence: 99%

Convolution Based Technique for Indic Script Identification from Handwritten Document Images

Obaidullah¹,

Das²

2015

IJIGSP

View full text Add to dashboard Cite

Abstract-Determination of script type of document image is a complex real life problem for a multi-script country like India, where 23 official languages (including English) are present and 13 different scripts are used to write them. Including English and Roman those count become 23 and 13 respectively. The problem becomes more challenging when handwritten documents are considered. In this paper an approach for identifying the script type of handwritten document images written by any one of the Bangla, Devnagari, Roman and Urdu script is proposed. Two convolution based techniques, namely Gabor filter and Morphological reconstruction are combined and a feature vector of 20 dimensions is constructed. Due to unavailability of a standard data set, a corpus of 157 document images with an almost equal ratio of four types of script is prepared. During classification the dataset is divided into 2:1 ratio. An average identification accuracy rate of 94.4% is obtained on the test set. The average Bi-script and Tri-script identification accuracy rate was found to be 98.2% and 97.5% respectively. Statistical performance analysis is done using different well known classifiers.

show abstract

“…Hangarge et al [8] and Hangarge and Santhosh [9] have exploited directional discrete cosine transform (DDCT). LDA and KNN classifiers are used for classification purpose.…”

Section: Introductionmentioning

confidence: 99%

Analysis and Automation of Handwritten Word Level Script Recognition

Ravikumar

Manjunath

Guru

2015

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

In this paper, a problem of automatic selection of feature sets and suitable classifiers for recognition of handwritten scripts at word level is addressed. The problem is brought out clearly with sufficient study by comparing state of the art techniques. Based on the analysis, three different models have been proposed in this paper. To accomplish the task, combination of various features and classifiers are tried out. The proposed work is on bi-script recognition. To conduct experimentation we have considered different features and classifiers which are recommended in the literature. The proposed work has been demonstrated for its effectiveness on our own dataset of reasonably large size. Experimental results reveal that, the proposed models perform better than the existing models.

show abstract

Directional Discrete Cosine Transform for Handwritten Script Identification

Cited by 43 publications

References 13 publications

Automatic Line-Level Script Identification From Handwritten Document Images - A Region-Wise Classification Framework for Indian Subcontinent

Automatic Line-Level Script Identification From Handwritten Document Images - A Region-Wise Classification Framework for Indian Subcontinent

Convolution Based Technique for Indic Script Identification from Handwritten Document Images

Analysis and Automation of Handwritten Word Level Script Recognition

Contact Info

Product

Resources

About