Handwritten Bangla Word Recognition Using Elliptical Features

Bhowmik, Showmik; Malakar, Samir; Sarkar, Ram; Nasipuri, Mita

doi:10.1109/cicn.2014.66

Cited by 29 publications

(11 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we have compared the performance of the proposed H‐WordNet model with state‐of‐the‐art methods. For comparison, we have considered the holistic word recognition approaches reported in [4, 17–19, 36, 38]. Also, the efficacy of two deep learning models such as deep stacked autoencoder [53] and fire module based CNN [54] is compared.…”

Section: Simulation and Resultsmentioning

confidence: 99%

“…They have obtained an accuracy of 79.12% on a database including 119 town names of West Bengal state (each city name represents a class) with 300 samples from each class. In [19], elliptical features are utilised along with five different classifiers to holistically recognise the handwritten Bangla words. They have validated their method on a newly formed dataset that holds 51 samples from 20 different word classes, and have achieved a accuracy of 77.94% with the MLP classifier.…”

Section: Related Workmentioning

confidence: 99%

“…The primary concern in designing an automated word recognition system is the selection of proper feature extraction methods to uniquely represent each word image. The handcrafted features such as histogram of oriented gradients (HOG) features [17], Arnold transform features [18], elliptic features [19], kurtosis wavelet energy [20], and kurtosis curvelet energy features [21] have gained increasing popularity for achieving state‐of‐the‐art performance. In recent years, deep learning models have received significant attention from researchers because of their potential in solving various computer vision problems such as large‐scale image classification, image segmentation, object recognition etc., by learning high‐level features directly from images [22].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

H‐WordNet: a holistic convolutional neural network approach for handwritten word recognition

Das

Nayak

Dash

et al. 2020

IET Image Processing

View full text Add to dashboard Cite

Section: Simulation and Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

H‐WordNet: a holistic convolutional neural network approach for handwritten word recognition

Das

Nayak

Dash

et al. 2020

IET Image Processing

View full text Add to dashboard Cite

“…a study used HMM to recognise Bangla words and reached 85.49% efficiency [17]. Bhowmik, et al [18] applied the elliptical feature extraction method and various classifiers like the Naïve Bayes, Bagging, Dagging, SVM, MLP, to evaluate the performance of the classifiers, achieving accuracies of 74.41%, 60.00%, 69.41%, 77.35%, and 77.94%, respectively. Therefore, it can be concluded that SVM and ANN performed better in recognising Bangla words compared to the other classifiers.…”

Section: Literature Reviewmentioning

confidence: 99%

Brahmi Word Recognition by Supervised Techniques

Gautam¹,

Chai²,

Afrin³

et al. 2020

Preprint

View full text Add to dashboard Cite

Significant progress has made in pattern recognition technology. However, one obstacle that has not yet overcome is the recognition of words in the Brahmi script, specifically the recognition of characters, compound characters, and word because of complex structure. For this kind of complex pattern recognition problem, it is always difficult to decide which feature extraction and classifier would be the best choice. Moreover, it is also true that different feature extraction and classifiers offer complementary information about the patterns to be classified. Therefore, combining feature extraction and classifiers, in an intelligent way, can be beneficial compared to using any single feature extraction. This study proposed the combination of HOG +zonal density with SVM to recognize the Brahmi words. Keeping these facts in mind, in this paper, information provided by structural and statistical based features are combined using SVM classifier for script recognition (word-level) purpose from the Brahmi words images. Brahmi word dataset contains 6,475 and 536 images of Brahmi words of 170 classes for the training and testing, respectively, and the database is made freely available. The word samples from the mentioned database are classified based on the confidence scores provided by support vector machine (SVM) classifier while HOG and zonal density use to extract the features of Brahmi words. Maximum accuracy suggested by system is 95.17% which is better than previously suggested studies.

show abstract

“…x new = x old + P band * ε (1) where, x old is the existing pitch or solution from the HM, and x new is the pitch value after adjusting the existing pitch value. This basically generates a novel solution in the region of the prevailing solution by a small variation in the pitch value 22 .…”

Section: Proposed Workmentioning

confidence: 99%

A Harmony Search Based Wrapper Feature Selection Method for Holistic Bangla Word Recognition

Das

Singh

Bhowmik

et al. 2016

Procedia Computer Science

Self Cite

View full text Add to dashboard Cite

A lot of search approaches have been explored for the selection of features in pattern classification domain in order to discover significant subset of the features which produces better accuracy. In this paper, we introduced a Harmony Search (HS) algorithm based feature selection method for feature dimensionality reduction in handwritten Bangla word recognition problem. This algorithm has been implemented to reduce the feature dimensionality of a technique described in one of our previous papers by S. Bhowmik et al. 1 . In the said paper, a set of 65 elliptical features were computed for handwritten Bangla word recognition purpose and a recognition accuracy of 81.37% was achieved using Multi Layer Perceptron (MLP) classifier. In the present work, a subset containing 48 features (approximately 75% of said feature vector) has been selected by HS based wrapper feature selection method which produces an accuracy rate of 90.29%. Reasonable outcomes also validates that the introduced algorithm utilizes optimal number of features while showing higher classification accuracies when compared to two standard evolutionary algorithms like Genetic Algorithm (GA), Particle Swarm Optimization (PSO) and statistical feature dimensionality reduction technique like Principal Component Analysis (PCA). This confirms the suitability of HS algorithm to the holistic handwritten word recognition problem.

show abstract

Handwritten Bangla Word Recognition Using Elliptical Features

Cited by 29 publications

References 9 publications

H‐WordNet: a holistic convolutional neural network approach for handwritten word recognition

H‐WordNet: a holistic convolutional neural network approach for handwritten word recognition

Brahmi Word Recognition by Supervised Techniques

A Harmony Search Based Wrapper Feature Selection Method for Holistic Bangla Word Recognition

Contact Info

Product

Resources

About