Recognition of Bangla Handwritten Characters Using an MLP Classifier Based on Stroke Features

Bhowmik, Tanmay; Bhattacharya, Ujjwal; Parui, Susanta Kumar

doi:10.1007/978-3-540-30499-9_125

Cited by 61 publications

(21 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although there are 12 different scripts in India, only a few research papers have been published on handwritten Indian numeral recognition and these papers are mainly on Devnagari and Bangla scripts [2,3,4,5,9]. To the best of our knowledge, only two pieces of work have been reported in the literature on Oriya handwritten numeral recognition [6,8].…”

Section: Introductionmentioning

confidence: 94%

Oriya handwritten numeral recognition system

Roy

Pal

et al. 2005

Eighth International Conference on Document Analysis and Recognition (ICDAR'05)

View full text Add to dashboard Cite

This paper deals with recognition of off-line unconstrained Oriya handwritten numerals. To take care of variability involved in the writing style of different individuals, the features are mainly considered from the contour of the numerals. At first, the bounding box of a numeral is segmented into few blocks and chain code histogram is computed in each of the blocks. Features are mainly based on the direction chain code histogram of the contour points of these blocks. Neural Network (NN) classifier and quadratic classifier are used separately for recognition and the results obtained from these two classifiers are compared. We tested the result on 3850 data collected from different individuals of various background and we obtained 90.38% (94.81%) recognition accuracy from NN (quadratic) classifier with a rejection rate of about 1.84% (1.31%), respectively.

show abstract

Section: Introductionmentioning

confidence: 94%

Oriya handwritten numeral recognition system

Roy

Pal

et al. 2005

Eighth International Conference on Document Analysis and Recognition (ICDAR'05)

View full text Add to dashboard Cite

show abstract

“…In Literature there is not enough works for Bangla handwritten characters [4][5][6][7][8]. Niaran Das et al [4] proposed an MLP and SVM based approach for recognition of bangla basic and compound characters using longest run feature.…”

Section: Previous Workmentioning

confidence: 99%

“…Rahman et al [5] and Bhowmik et al [6] used multistage approach for handwritten characters recognition and MLP is used for recognition. Feature set include matra, upper part of the characters, disjoint section of the character, vertical line and double vertical line and for the MLP classifier, the feature set is constructed from the stroke features o characters.…”

Section: Previous Workmentioning

confidence: 99%

A Hybrid Model for Recognizing Handwritten Bangla Characters using Support Vector Machine

Afroge¹,

Ahmed²

2017

IJCA

View full text Add to dashboard Cite

Considering the real time scenario, hand written bangla recognition getting a drastic part to the research community. Though various studies have been performed for Bengali handwritten recognition, but a robust model for Bangla Handwritten classification is still in practice. Therefore a hybrid model is presented in this paper, which intent to classify Bangla handwritten characters. The Proposed model combines Zernike moments, raw binary pixels and histogram of oriented gradients features for recognizing Bangla hand written characters which is feed to the Support Vector Machine classifier. It is observed that, the proposed model outsails existing models with smaller epochs. Proposed model is trained and test with "Bangla Lekha Isolated" dataset which consists of 30000 characters where 24,000 for training dataset and 6,000 for testing .This system shows 46.98% for Zernike Moments, 66.60% for Raw Binary Pixels and 87.62% for Histogram of Oriented Gradients where overall combined features achieve an accuracy of 94.88% in recognizing characters which achieves the best accuracy rate reported till date for this dataset.

show abstract

“…The work relating to OCR of Bangla script, as mentioned earlier, is found to have few references in the literature. Two such instances [3], [4], one focusing on recognition of isolated handwritten characters based on stroke features and the other concentrated on a multistage approach based on different topological features respectively, have not addressed the problem of Bangla text segmentation. The problem of Bangla text segmentation has been addressed in [5].…”

Section: Optical Character Recognition (Ocr) Of Text Documents Requiresmentioning

confidence: 99%

A Script Independent Technique for Extraction of Characters from Handwritten Word Images

Sarkar¹,

Malakar²,

Das³

et al. 2010

IJCA

View full text Add to dashboard Cite

A script independent character segmentation from word images technique has been reported here. Word to character segmentation is an important preprocessing step of optical character recognition process. But in case of handwritten text, presence of touching characters decreases the accuracy of the technique of the segmentation of the characters from the word. In this paper, segmentation of handwritten word of four different scripts namely, Bangla, Devanagri, Gurmukhi and Syloti are considered as the test samples. All these scripts are characterized by the presence of a distinct line along the top of the most of the characters forming the words, called the headline or Matra. Unlike English script, the characters of these handwritten scripts and its components often encircle the main character, making the conventional segmentation methodologies inapplicable. For the segmentation technique two fuzzy features, to identify the Matra region and potential segmentation point, are used here. Experimental results, using the proposed segmentation technique, on sample of 400 handwritten word images containing all the above mentioned scripts of Bangla, Devanagri, Gurmukhi and Syloti show a success rate of 95.41%, 93.61%, 91.23% and 92.37% respectively.

show abstract

Recognition of Bangla Handwritten Characters Using an MLP Classifier Based on Stroke Features

Cited by 61 publications

References 10 publications

Oriya handwritten numeral recognition system

Oriya handwritten numeral recognition system

A Hybrid Model for Recognizing Handwritten Bangla Characters using Support Vector Machine

A Script Independent Technique for Extraction of Characters from Handwritten Word Images

Contact Info

Product

Resources

About